diff --git "a/loss_log.jsonl" "b/loss_log.jsonl"
new file mode 100644--- /dev/null
+++ "b/loss_log.jsonl"
@@ -0,0 +1,15912 @@
+{"step": 0, "dynamics_loss_avg": 0.17640884220600128}
+{"step": 0, "action_loss_avg": 0.2489933967590332}
+{"step": 10, "dynamics_loss_avg": 0.17190887182950973}
+{"step": 10, "action_loss_avg": 0.2661958925426006}
+{"step": 20, "dynamics_loss_avg": 0.1524803400039673}
+{"step": 20, "action_loss_avg": 0.20449500307440757}
+{"step": 30, "dynamics_loss_avg": 0.16044300347566604}
+{"step": 30, "action_loss_avg": 0.23963396102190018}
+{"step": 40, "dynamics_loss_avg": 0.19053732454776764}
+{"step": 40, "action_loss_avg": 0.32575062811374667}
+{"step": 50, "loss": 0.4131, "learning_rate": 9.8e-07}
+{"step": 50, "dynamics_loss_avg": 0.1546848639845848}
+{"step": 50, "action_loss_avg": 0.24657674729824067}
+{"step": 60, "dynamics_loss_avg": 0.17921957448124887}
+{"step": 60, "action_loss_avg": 0.2703615739941597}
+{"step": 70, "dynamics_loss_avg": 0.18953108191490173}
+{"step": 70, "action_loss_avg": 0.3017821490764618}
+{"step": 80, "dynamics_loss_avg": 0.1608529232442379}
+{"step": 80, "action_loss_avg": 0.22439688444137573}
+{"step": 90, "dynamics_loss_avg": 0.16051228120923042}
+{"step": 90, "action_loss_avg": 0.20420529320836067}
+{"step": 100, "loss": 0.4032, "learning_rate": 1.98e-06}
+{"step": 100, "dynamics_loss_avg": 0.15350338071584702}
+{"step": 100, "action_loss_avg": 0.19350149258971214}
+{"step": 110, "dynamics_loss_avg": 0.1561502441763878}
+{"step": 110, "action_loss_avg": 0.21096567586064338}
+{"step": 120, "dynamics_loss_avg": 0.14666921868920327}
+{"step": 120, "action_loss_avg": 0.1792544551193714}
+{"step": 130, "dynamics_loss_avg": 0.16470266208052636}
+{"step": 130, "action_loss_avg": 0.1872612088918686}
+{"step": 140, "dynamics_loss_avg": 0.1699105016887188}
+{"step": 140, "action_loss_avg": 0.18137918114662172}
+{"step": 150, "loss": 0.3557, "learning_rate": 2.9800000000000003e-06}
+{"step": 150, "dynamics_loss_avg": 0.17499759793281555}
+{"step": 150, "action_loss_avg": 0.21677915677428244}
+{"step": 160, "dynamics_loss_avg": 0.17714835554361344}
+{"step": 160, "action_loss_avg": 0.21479170322418212}
+{"step": 170, "dynamics_loss_avg": 0.1606353998184204}
+{"step": 170, "action_loss_avg": 0.18584862351417542}
+{"step": 180, "dynamics_loss_avg": 0.18090662807226182}
+{"step": 180, "action_loss_avg": 0.25304377973079684}
+{"step": 190, "dynamics_loss_avg": 0.15126327723264693}
+{"step": 190, "action_loss_avg": 0.19030125066637993}
+{"step": 200, "loss": 0.3695, "learning_rate": 3.98e-06}
+{"step": 200, "dynamics_loss_avg": 0.16581472828984262}
+{"step": 200, "action_loss_avg": 0.20517078042030334}
+{"step": 210, "dynamics_loss_avg": 0.14717404395341874}
+{"step": 210, "action_loss_avg": 0.16231796219944955}
+{"step": 220, "dynamics_loss_avg": 0.15584879890084266}
+{"step": 220, "action_loss_avg": 0.19117696210741997}
+{"step": 230, "dynamics_loss_avg": 0.14349498525261878}
+{"step": 230, "action_loss_avg": 0.16888035982847213}
+{"step": 240, "dynamics_loss_avg": 0.13833538293838502}
+{"step": 240, "action_loss_avg": 0.16638477891683578}
+{"step": 250, "loss": 0.3145, "learning_rate": 4.98e-06}
+{"step": 250, "dynamics_loss_avg": 0.1538217194378376}
+{"step": 250, "action_loss_avg": 0.17657785303890705}
+{"step": 260, "dynamics_loss_avg": 0.1308735989034176}
+{"step": 260, "action_loss_avg": 0.14100533127784728}
+{"step": 270, "dynamics_loss_avg": 0.13526604175567628}
+{"step": 270, "action_loss_avg": 0.1541447900235653}
+{"step": 280, "dynamics_loss_avg": 0.12135790139436722}
+{"step": 280, "action_loss_avg": 0.1374490089714527}
+{"step": 290, "dynamics_loss_avg": 0.12039730213582515}
+{"step": 290, "action_loss_avg": 0.1430749773979187}
+{"step": 300, "loss": 0.2666, "learning_rate": 5.98e-06}
+{"step": 300, "dynamics_loss_avg": 0.11799011752009392}
+{"step": 300, "action_loss_avg": 0.12220268473029136}
+{"step": 310, "dynamics_loss_avg": 0.12277396209537983}
+{"step": 310, "action_loss_avg": 0.1465402688831091}
+{"step": 320, "dynamics_loss_avg": 0.09957646280527115}
+{"step": 320, "action_loss_avg": 0.14035568311810492}
+{"step": 330, "dynamics_loss_avg": 0.1260475240647793}
+{"step": 330, "action_loss_avg": 0.18563747368752956}
+{"step": 340, "dynamics_loss_avg": 0.0949243038892746}
+{"step": 340, "action_loss_avg": 0.11825571656227112}
+{"step": 350, "loss": 0.2419, "learning_rate": 6.98e-06}
+{"step": 350, "dynamics_loss_avg": 0.10815992280840873}
+{"step": 350, "action_loss_avg": 0.14382895156741143}
+{"step": 360, "dynamics_loss_avg": 0.08903464041650296}
+{"step": 360, "action_loss_avg": 0.11308124512434006}
+{"step": 370, "dynamics_loss_avg": 0.0902866382151842}
+{"step": 370, "action_loss_avg": 0.1374109521508217}
+{"step": 380, "dynamics_loss_avg": 0.07257495932281018}
+{"step": 380, "action_loss_avg": 0.10014848671853542}
+{"step": 390, "dynamics_loss_avg": 0.09039058089256287}
+{"step": 390, "action_loss_avg": 0.118554125726223}
+{"step": 400, "loss": 0.2094, "learning_rate": 7.98e-06}
+{"step": 400, "dynamics_loss_avg": 0.09602558389306068}
+{"step": 400, "action_loss_avg": 0.15683277547359467}
+{"step": 410, "dynamics_loss_avg": 0.07161674164235592}
+{"step": 410, "action_loss_avg": 0.0881810024380684}
+{"step": 420, "dynamics_loss_avg": 0.08572141453623772}
+{"step": 420, "action_loss_avg": 0.0994539137929678}
+{"step": 430, "dynamics_loss_avg": 0.08403245881199836}
+{"step": 430, "action_loss_avg": 0.1067172510549426}
+{"step": 440, "dynamics_loss_avg": 0.06803636401891708}
+{"step": 440, "action_loss_avg": 0.08376460336148739}
+{"step": 450, "loss": 0.1661, "learning_rate": 8.98e-06}
+{"step": 450, "dynamics_loss_avg": 0.07953903041779994}
+{"step": 450, "action_loss_avg": 0.10843892311677336}
+{"step": 460, "dynamics_loss_avg": 0.08264699280261993}
+{"step": 460, "action_loss_avg": 0.11818931642919779}
+{"step": 470, "dynamics_loss_avg": 0.07944376543164253}
+{"step": 470, "action_loss_avg": 0.09048039708286523}
+{"step": 480, "dynamics_loss_avg": 0.07242739889770747}
+{"step": 480, "action_loss_avg": 0.07653041779994965}
+{"step": 490, "dynamics_loss_avg": 0.07793002463877201}
+{"step": 490, "action_loss_avg": 0.09957306198775769}
+{"step": 500, "loss": 0.1572, "learning_rate": 9.980000000000001e-06}
+{"step": 500, "dynamics_loss_avg": 0.06365312617272138}
+{"step": 500, "action_loss_avg": 0.07912898883223533}
+{"step": 510, "dynamics_loss_avg": 0.06718760132789611}
+{"step": 510, "action_loss_avg": 0.09694140404462814}
+{"step": 520, "dynamics_loss_avg": 0.06461264193058014}
+{"step": 520, "action_loss_avg": 0.07786228470504283}
+{"step": 530, "dynamics_loss_avg": 0.059372028708457945}
+{"step": 530, "action_loss_avg": 0.056447290815413}
+{"step": 540, "dynamics_loss_avg": 0.06928445659577846}
+{"step": 540, "action_loss_avg": 0.09452702850103378}
+{"step": 550, "loss": 0.1271, "learning_rate": 1.098e-05}
+{"step": 550, "dynamics_loss_avg": 0.05987930037081242}
+{"step": 550, "action_loss_avg": 0.06752783022820949}
+{"step": 560, "dynamics_loss_avg": 0.0653644248843193}
+{"step": 560, "action_loss_avg": 0.06823472185060382}
+{"step": 570, "dynamics_loss_avg": 0.05800749566406012}
+{"step": 570, "action_loss_avg": 0.07724601048976183}
+{"step": 580, "dynamics_loss_avg": 0.05784410238265991}
+{"step": 580, "action_loss_avg": 0.05699769109487533}
+{"step": 590, "dynamics_loss_avg": 0.07110700272023678}
+{"step": 590, "action_loss_avg": 0.09366117715835572}
+{"step": 600, "loss": 0.1368, "learning_rate": 1.198e-05}
+{"step": 600, "dynamics_loss_avg": 0.06918462291359902}
+{"step": 600, "action_loss_avg": 0.07144665829837323}
+{"step": 610, "dynamics_loss_avg": 0.058880973421037194}
+{"step": 610, "action_loss_avg": 0.06575191654264927}
+{"step": 620, "dynamics_loss_avg": 0.05793977901339531}
+{"step": 620, "action_loss_avg": 0.07491361331194639}
+{"step": 630, "dynamics_loss_avg": 0.06340789385139942}
+{"step": 630, "action_loss_avg": 0.08845358118414878}
+{"step": 640, "dynamics_loss_avg": 0.06601353771984578}
+{"step": 640, "action_loss_avg": 0.09163259696215391}
+{"step": 650, "loss": 0.1374, "learning_rate": 1.2980000000000001e-05}
+{"step": 650, "dynamics_loss_avg": 0.06325901299715042}
+{"step": 650, "action_loss_avg": 0.07816524319350719}
+{"step": 660, "dynamics_loss_avg": 0.05019594542682171}
+{"step": 660, "action_loss_avg": 0.0631269147619605}
+{"step": 670, "dynamics_loss_avg": 0.0668456345796585}
+{"step": 670, "action_loss_avg": 0.10767365209758281}
+{"step": 680, "dynamics_loss_avg": 0.05770420543849468}
+{"step": 680, "action_loss_avg": 0.07875978015363216}
+{"step": 690, "dynamics_loss_avg": 0.05927947200834751}
+{"step": 690, "action_loss_avg": 0.07834573276340961}
+{"step": 700, "loss": 0.1344, "learning_rate": 1.3980000000000002e-05}
+{"step": 700, "dynamics_loss_avg": 0.06129003986716271}
+{"step": 700, "action_loss_avg": 0.07015281617641449}
+{"step": 710, "dynamics_loss_avg": 0.0614464707672596}
+{"step": 710, "action_loss_avg": 0.07851822124794125}
+{"step": 720, "dynamics_loss_avg": 0.0734769705682993}
+{"step": 720, "action_loss_avg": 0.09939382933080196}
+{"step": 730, "dynamics_loss_avg": 0.05842618830502033}
+{"step": 730, "action_loss_avg": 0.08118493780493737}
+{"step": 740, "dynamics_loss_avg": 0.05313926516100764}
+{"step": 740, "action_loss_avg": 0.06926635717973113}
+{"step": 750, "loss": 0.1321, "learning_rate": 1.4979999999999999e-05}
+{"step": 750, "dynamics_loss_avg": 0.05570547357201576}
+{"step": 750, "action_loss_avg": 0.09339708830229938}
+{"step": 760, "dynamics_loss_avg": 0.05002450328320265}
+{"step": 760, "action_loss_avg": 0.07537425216287374}
+{"step": 770, "dynamics_loss_avg": 0.0647622475400567}
+{"step": 770, "action_loss_avg": 0.09456779323518276}
+{"step": 780, "dynamics_loss_avg": 0.038693724758923055}
+{"step": 780, "action_loss_avg": 0.04136260412633419}
+{"step": 790, "dynamics_loss_avg": 0.06290768422186374}
+{"step": 790, "action_loss_avg": 0.07619449477642774}
+{"step": 800, "loss": 0.1286, "learning_rate": 1.598e-05}
+{"step": 800, "dynamics_loss_avg": 0.05822602789849043}
+{"step": 800, "action_loss_avg": 0.0745524823665619}
+{"step": 810, "dynamics_loss_avg": 0.05179535932838917}
+{"step": 810, "action_loss_avg": 0.07425978891551495}
+{"step": 820, "dynamics_loss_avg": 0.05121450321748853}
+{"step": 820, "action_loss_avg": 0.052287746034562585}
+{"step": 830, "dynamics_loss_avg": 0.05094762649387121}
+{"step": 830, "action_loss_avg": 0.06332722585648298}
+{"step": 840, "dynamics_loss_avg": 0.060864539816975594}
+{"step": 840, "action_loss_avg": 0.06795058529824019}
+{"step": 850, "loss": 0.1227, "learning_rate": 1.698e-05}
+{"step": 850, "dynamics_loss_avg": 0.0555612986907363}
+{"step": 850, "action_loss_avg": 0.06890723891556264}
+{"step": 860, "dynamics_loss_avg": 0.05465201307088137}
+{"step": 860, "action_loss_avg": 0.06604298856109381}
+{"step": 870, "dynamics_loss_avg": 0.0577197041362524}
+{"step": 870, "action_loss_avg": 0.0773347420617938}
+{"step": 880, "dynamics_loss_avg": 0.0533218540251255}
+{"step": 880, "action_loss_avg": 0.07104917075484991}
+{"step": 890, "dynamics_loss_avg": 0.054302478395402434}
+{"step": 890, "action_loss_avg": 0.0783127373084426}
+{"step": 900, "loss": 0.1214, "learning_rate": 1.798e-05}
+{"step": 900, "dynamics_loss_avg": 0.04436008632183075}
+{"step": 900, "action_loss_avg": 0.07150141634047032}
+{"step": 910, "dynamics_loss_avg": 0.050704390928149226}
+{"step": 910, "action_loss_avg": 0.07019122689962387}
+{"step": 920, "dynamics_loss_avg": 0.07006678059697151}
+{"step": 920, "action_loss_avg": 0.0901838157325983}
+{"step": 930, "dynamics_loss_avg": 0.04989906838163734}
+{"step": 930, "action_loss_avg": 0.058386290818452834}
+{"step": 940, "dynamics_loss_avg": 0.061744342744350436}
+{"step": 940, "action_loss_avg": 0.08824699893593788}
+{"step": 950, "loss": 0.1188, "learning_rate": 1.898e-05}
+{"step": 950, "dynamics_loss_avg": 0.06181049589067698}
+{"step": 950, "action_loss_avg": 0.07774877501651645}
+{"step": 960, "dynamics_loss_avg": 0.062012319825589655}
+{"step": 960, "action_loss_avg": 0.0766281470656395}
+{"step": 970, "dynamics_loss_avg": 0.0560112090781331}
+{"step": 970, "action_loss_avg": 0.07186717055737972}
+{"step": 980, "dynamics_loss_avg": 0.052636738121509555}
+{"step": 980, "action_loss_avg": 0.06615277864038945}
+{"step": 990, "dynamics_loss_avg": 0.053583865612745286}
+{"step": 990, "action_loss_avg": 0.06467948034405709}
+{"step": 1000, "loss": 0.1159, "learning_rate": 1.9980000000000002e-05}
+{"step": 1000, "dynamics_loss_avg": 0.05469804406166077}
+{"step": 1000, "action_loss_avg": 0.06667924029752612}
+{"step": 1010, "dynamics_loss_avg": 0.06080723628401756}
+{"step": 1010, "action_loss_avg": 0.07279662191867828}
+{"step": 1020, "dynamics_loss_avg": 0.05776304751634598}
+{"step": 1020, "action_loss_avg": 0.08280905522406101}
+{"step": 1030, "dynamics_loss_avg": 0.04953005556017161}
+{"step": 1030, "action_loss_avg": 0.05684455642476678}
+{"step": 1040, "dynamics_loss_avg": 0.0501399926841259}
+{"step": 1040, "action_loss_avg": 0.06081235054880381}
+{"step": 1050, "loss": 0.1176, "learning_rate": 2.098e-05}
+{"step": 1050, "dynamics_loss_avg": 0.05908319018781185}
+{"step": 1050, "action_loss_avg": 0.07507404163479806}
+{"step": 1060, "dynamics_loss_avg": 0.058740850910544394}
+{"step": 1060, "action_loss_avg": 0.09362712763249874}
+{"step": 1070, "dynamics_loss_avg": 0.06442492231726646}
+{"step": 1070, "action_loss_avg": 0.07928443904966116}
+{"step": 1080, "dynamics_loss_avg": 0.04937783787027002}
+{"step": 1080, "action_loss_avg": 0.0580103934276849}
+{"step": 1090, "dynamics_loss_avg": 0.058051745593547824}
+{"step": 1090, "action_loss_avg": 0.06153569705784321}
+{"step": 1100, "loss": 0.1231, "learning_rate": 2.198e-05}
+{"step": 1100, "dynamics_loss_avg": 0.04871407989412546}
+{"step": 1100, "action_loss_avg": 0.06123330611735582}
+{"step": 1110, "dynamics_loss_avg": 0.05074391104280949}
+{"step": 1110, "action_loss_avg": 0.062263792660087344}
+{"step": 1120, "dynamics_loss_avg": 0.05632402822375297}
+{"step": 1120, "action_loss_avg": 0.05661111772060394}
+{"step": 1130, "dynamics_loss_avg": 0.05094183050096035}
+{"step": 1130, "action_loss_avg": 0.06430048756301403}
+{"step": 1140, "dynamics_loss_avg": 0.04875540286302567}
+{"step": 1140, "action_loss_avg": 0.05362733425572515}
+{"step": 1150, "loss": 0.0995, "learning_rate": 2.298e-05}
+{"step": 1150, "dynamics_loss_avg": 0.04853116841986775}
+{"step": 1150, "action_loss_avg": 0.05381042957305908}
+{"step": 1160, "dynamics_loss_avg": 0.04624059107154608}
+{"step": 1160, "action_loss_avg": 0.04794489033520222}
+{"step": 1170, "dynamics_loss_avg": 0.03755781417712569}
+{"step": 1170, "action_loss_avg": 0.03527753872331232}
+{"step": 1180, "dynamics_loss_avg": 0.044522053189575674}
+{"step": 1180, "action_loss_avg": 0.053009592555463315}
+{"step": 1190, "dynamics_loss_avg": 0.0573886688798666}
+{"step": 1190, "action_loss_avg": 0.05103451833128929}
+{"step": 1200, "loss": 0.0939, "learning_rate": 2.398e-05}
+{"step": 1200, "dynamics_loss_avg": 0.04852320216596127}
+{"step": 1200, "action_loss_avg": 0.04783613756299019}
+{"step": 1210, "dynamics_loss_avg": 0.05285048112273216}
+{"step": 1210, "action_loss_avg": 0.05019335299730301}
+{"step": 1220, "dynamics_loss_avg": 0.06136778816580772}
+{"step": 1220, "action_loss_avg": 0.06016576178371906}
+{"step": 1230, "dynamics_loss_avg": 0.05281207803636789}
+{"step": 1230, "action_loss_avg": 0.04949547592550516}
+{"step": 1240, "dynamics_loss_avg": 0.0573091134428978}
+{"step": 1240, "action_loss_avg": 0.08142326101660728}
+{"step": 1250, "loss": 0.1103, "learning_rate": 2.498e-05}
+{"step": 1250, "dynamics_loss_avg": 0.05942497551441193}
+{"step": 1250, "action_loss_avg": 0.060321255773305896}
+{"step": 1260, "dynamics_loss_avg": 0.04505568109452725}
+{"step": 1260, "action_loss_avg": 0.037953870929777624}
+{"step": 1270, "dynamics_loss_avg": 0.04583796821534634}
+{"step": 1270, "action_loss_avg": 0.047137458063662055}
+{"step": 1280, "dynamics_loss_avg": 0.045771773904561996}
+{"step": 1280, "action_loss_avg": 0.046339186280965804}
+{"step": 1290, "dynamics_loss_avg": 0.0477931696921587}
+{"step": 1290, "action_loss_avg": 0.04875643290579319}
+{"step": 1300, "loss": 0.0861, "learning_rate": 2.598e-05}
+{"step": 1300, "dynamics_loss_avg": 0.04608360808342695}
+{"step": 1300, "action_loss_avg": 0.05324465930461884}
+{"step": 1310, "dynamics_loss_avg": 0.05014730338007212}
+{"step": 1310, "action_loss_avg": 0.04904530718922615}
+{"step": 1320, "dynamics_loss_avg": 0.0567525215446949}
+{"step": 1320, "action_loss_avg": 0.04421920962631702}
+{"step": 1330, "dynamics_loss_avg": 0.05419497825205326}
+{"step": 1330, "action_loss_avg": 0.055672813393175605}
+{"step": 1340, "dynamics_loss_avg": 0.047500976361334324}
+{"step": 1340, "action_loss_avg": 0.0428589204326272}
+{"step": 1350, "loss": 0.0924, "learning_rate": 2.698e-05}
+{"step": 1350, "dynamics_loss_avg": 0.05156325697898865}
+{"step": 1350, "action_loss_avg": 0.05682938098907471}
+{"step": 1360, "dynamics_loss_avg": 0.06258504539728164}
+{"step": 1360, "action_loss_avg": 0.06296473611146211}
+{"step": 1370, "dynamics_loss_avg": 0.05192828755825758}
+{"step": 1370, "action_loss_avg": 0.07108068317174912}
+{"step": 1380, "dynamics_loss_avg": 0.05664817336946726}
+{"step": 1380, "action_loss_avg": 0.055622382741421464}
+{"step": 1390, "dynamics_loss_avg": 0.0474602721631527}
+{"step": 1390, "action_loss_avg": 0.04272201443091035}
+{"step": 1400, "loss": 0.0998, "learning_rate": 2.798e-05}
+{"step": 1400, "dynamics_loss_avg": 0.05184114463627339}
+{"step": 1400, "action_loss_avg": 0.05275695901364088}
+{"step": 1410, "dynamics_loss_avg": 0.054576536640524864}
+{"step": 1410, "action_loss_avg": 0.06939670480787755}
+{"step": 1420, "dynamics_loss_avg": 0.04067272581160068}
+{"step": 1420, "action_loss_avg": 0.02910182154737413}
+{"step": 1430, "dynamics_loss_avg": 0.041729917749762535}
+{"step": 1430, "action_loss_avg": 0.031777257937937974}
+{"step": 1440, "dynamics_loss_avg": 0.053386075794696806}
+{"step": 1440, "action_loss_avg": 0.059812195412814614}
+{"step": 1450, "loss": 0.0861, "learning_rate": 2.898e-05}
+{"step": 1450, "dynamics_loss_avg": 0.05188748985528946}
+{"step": 1450, "action_loss_avg": 0.05821213535964489}
+{"step": 1460, "dynamics_loss_avg": 0.052115540206432345}
+{"step": 1460, "action_loss_avg": 0.04791367594152689}
+{"step": 1470, "dynamics_loss_avg": 0.04054753575474024}
+{"step": 1470, "action_loss_avg": 0.0405738553032279}
+{"step": 1480, "dynamics_loss_avg": 0.03896890915930271}
+{"step": 1480, "action_loss_avg": 0.03488192614167929}
+{"step": 1490, "dynamics_loss_avg": 0.06053646951913834}
+{"step": 1490, "action_loss_avg": 0.05718158204108477}
+{"step": 1500, "loss": 0.0913, "learning_rate": 2.998e-05}
+{"step": 1500, "dynamics_loss_avg": 0.04087630342692137}
+{"step": 1500, "action_loss_avg": 0.03890103427693248}
+{"step": 1510, "dynamics_loss_avg": 0.042417519818991424}
+{"step": 1510, "action_loss_avg": 0.04411248568212613}
+{"step": 1520, "dynamics_loss_avg": 0.04770556064322591}
+{"step": 1520, "action_loss_avg": 0.04916956080123782}
+{"step": 1530, "dynamics_loss_avg": 0.051916641369462016}
+{"step": 1530, "action_loss_avg": 0.05488669276237488}
+{"step": 1540, "dynamics_loss_avg": 0.04919280996546149}
+{"step": 1540, "action_loss_avg": 0.05597424218431115}
+{"step": 1550, "loss": 0.0919, "learning_rate": 3.0980000000000005e-05}
+{"step": 1550, "dynamics_loss_avg": 0.04935853034257889}
+{"step": 1550, "action_loss_avg": 0.044938864465802905}
+{"step": 1560, "dynamics_loss_avg": 0.04449972221627831}
+{"step": 1560, "action_loss_avg": 0.047770062601193784}
+{"step": 1570, "dynamics_loss_avg": 0.04415358267724514}
+{"step": 1570, "action_loss_avg": 0.042254552617669104}
+{"step": 1580, "dynamics_loss_avg": 0.0464834850281477}
+{"step": 1580, "action_loss_avg": 0.030962423887103796}
+{"step": 1590, "dynamics_loss_avg": 0.046661633811891076}
+{"step": 1590, "action_loss_avg": 0.04692525062710047}
+{"step": 1600, "loss": 0.0864, "learning_rate": 3.198e-05}
+{"step": 1600, "dynamics_loss_avg": 0.05679422076791525}
+{"step": 1600, "action_loss_avg": 0.0565383467823267}
+{"step": 1610, "dynamics_loss_avg": 0.04805361777544022}
+{"step": 1610, "action_loss_avg": 0.04983617328107357}
+{"step": 1620, "dynamics_loss_avg": 0.04166891667991877}
+{"step": 1620, "action_loss_avg": 0.0375211775302887}
+{"step": 1630, "dynamics_loss_avg": 0.04044452141970396}
+{"step": 1630, "action_loss_avg": 0.02982735773548484}
+{"step": 1640, "dynamics_loss_avg": 0.05435989946126938}
+{"step": 1640, "action_loss_avg": 0.05008519664406776}
+{"step": 1650, "loss": 0.0826, "learning_rate": 3.298e-05}
+{"step": 1650, "dynamics_loss_avg": 0.03926632944494486}
+{"step": 1650, "action_loss_avg": 0.043512212485074996}
+{"step": 1660, "dynamics_loss_avg": 0.04248755499720573}
+{"step": 1660, "action_loss_avg": 0.031228192523121832}
+{"step": 1670, "dynamics_loss_avg": 0.05072959307581186}
+{"step": 1670, "action_loss_avg": 0.05202874150127172}
+{"step": 1680, "dynamics_loss_avg": 0.055893213488161564}
+{"step": 1680, "action_loss_avg": 0.04714992642402649}
+{"step": 1690, "dynamics_loss_avg": 0.04153373241424561}
+{"step": 1690, "action_loss_avg": 0.03511948836967349}
+{"step": 1700, "loss": 0.0771, "learning_rate": 3.398e-05}
+{"step": 1700, "dynamics_loss_avg": 0.03041100688278675}
+{"step": 1700, "action_loss_avg": 0.03303511287085712}
+{"step": 1710, "dynamics_loss_avg": 0.04584382511675358}
+{"step": 1710, "action_loss_avg": 0.04484750591218471}
+{"step": 1720, "dynamics_loss_avg": 0.03782062716782093}
+{"step": 1720, "action_loss_avg": 0.032207930088043214}
+{"step": 1730, "dynamics_loss_avg": 0.05196050740778446}
+{"step": 1730, "action_loss_avg": 0.05018861647695303}
+{"step": 1740, "dynamics_loss_avg": 0.051417419128119944}
+{"step": 1740, "action_loss_avg": 0.04175957329571247}
+{"step": 1750, "loss": 0.0791, "learning_rate": 3.498e-05}
+{"step": 1750, "dynamics_loss_avg": 0.04428627323359251}
+{"step": 1750, "action_loss_avg": 0.031510848086327314}
+{"step": 1760, "dynamics_loss_avg": 0.03585740150883794}
+{"step": 1760, "action_loss_avg": 0.034059186838567256}
+{"step": 1770, "dynamics_loss_avg": 0.0484800074249506}
+{"step": 1770, "action_loss_avg": 0.04734794814139605}
+{"step": 1780, "dynamics_loss_avg": 0.038133068941533566}
+{"step": 1780, "action_loss_avg": 0.03177959294989705}
+{"step": 1790, "dynamics_loss_avg": 0.04843211378902197}
+{"step": 1790, "action_loss_avg": 0.04099409459158778}
+{"step": 1800, "loss": 0.0796, "learning_rate": 3.5980000000000004e-05}
+{"step": 1800, "dynamics_loss_avg": 0.04965947661548853}
+{"step": 1800, "action_loss_avg": 0.03525321967899799}
+{"step": 1810, "dynamics_loss_avg": 0.03467508470639587}
+{"step": 1810, "action_loss_avg": 0.03310660298448056}
+{"step": 1820, "dynamics_loss_avg": 0.04418120961636305}
+{"step": 1820, "action_loss_avg": 0.033184437360614535}
+{"step": 1830, "dynamics_loss_avg": 0.04184529474005103}
+{"step": 1830, "action_loss_avg": 0.03150180522352457}
+{"step": 1840, "dynamics_loss_avg": 0.04423156138509512}
+{"step": 1840, "action_loss_avg": 0.04144926629960537}
+{"step": 1850, "loss": 0.0772, "learning_rate": 3.698e-05}
+{"step": 1850, "dynamics_loss_avg": 0.0449537256732583}
+{"step": 1850, "action_loss_avg": 0.028304202109575273}
+{"step": 1860, "dynamics_loss_avg": 0.04157639164477587}
+{"step": 1860, "action_loss_avg": 0.0302226884290576}
+{"step": 1870, "dynamics_loss_avg": 0.04991121906787157}
+{"step": 1870, "action_loss_avg": 0.04851043145172298}
+{"step": 1880, "dynamics_loss_avg": 0.03962288945913315}
+{"step": 1880, "action_loss_avg": 0.03844605460762977}
+{"step": 1890, "dynamics_loss_avg": 0.04434940610080958}
+{"step": 1890, "action_loss_avg": 0.035497620701789856}
+{"step": 1900, "loss": 0.0753, "learning_rate": 3.7980000000000006e-05}
+{"step": 1900, "dynamics_loss_avg": 0.046925322711467744}
+{"step": 1900, "action_loss_avg": 0.031058948114514352}
+{"step": 1910, "dynamics_loss_avg": 0.04151752050966025}
+{"step": 1910, "action_loss_avg": 0.03771298434585333}
+{"step": 1920, "dynamics_loss_avg": 0.045593241415917876}
+{"step": 1920, "action_loss_avg": 0.03409042675048113}
+{"step": 1930, "dynamics_loss_avg": 0.03660479234531522}
+{"step": 1930, "action_loss_avg": 0.03149098302237689}
+{"step": 1940, "dynamics_loss_avg": 0.033925733901560305}
+{"step": 1940, "action_loss_avg": 0.037941555585712196}
+{"step": 1950, "loss": 0.0675, "learning_rate": 3.898e-05}
+{"step": 1950, "dynamics_loss_avg": 0.03863101066090167}
+{"step": 1950, "action_loss_avg": 0.03234293158166111}
+{"step": 1960, "dynamics_loss_avg": 0.041795267909765246}
+{"step": 1960, "action_loss_avg": 0.03592264540493488}
+{"step": 1970, "dynamics_loss_avg": 0.053562484309077264}
+{"step": 1970, "action_loss_avg": 0.04428235311061144}
+{"step": 1980, "dynamics_loss_avg": 0.04856296386569738}
+{"step": 1980, "action_loss_avg": 0.04757571276277304}
+{"step": 1990, "dynamics_loss_avg": 0.05062068030238152}
+{"step": 1990, "action_loss_avg": 0.04201392475515604}
+{"step": 2000, "loss": 0.0831, "learning_rate": 3.998e-05}
+{"step": 2000, "dynamics_loss_avg": 0.03919725436717272}
+{"step": 2000, "action_loss_avg": 0.029525809874758124}
+{"step": 2010, "dynamics_loss_avg": 0.04480024054646492}
+{"step": 2010, "action_loss_avg": 0.03326994059607387}
+{"step": 2020, "dynamics_loss_avg": 0.038938040658831594}
+{"step": 2020, "action_loss_avg": 0.034713573195040225}
+{"step": 2030, "dynamics_loss_avg": 0.03978552501648665}
+{"step": 2030, "action_loss_avg": 0.040435816440731284}
+{"step": 2040, "dynamics_loss_avg": 0.04450737349689007}
+{"step": 2040, "action_loss_avg": 0.032313913106918335}
+{"step": 2050, "loss": 0.0762, "learning_rate": 4.0980000000000004e-05}
+{"step": 2050, "dynamics_loss_avg": 0.041598315350711346}
+{"step": 2050, "action_loss_avg": 0.03173916153609753}
+{"step": 2060, "dynamics_loss_avg": 0.04148669317364693}
+{"step": 2060, "action_loss_avg": 0.030579969426617025}
+{"step": 2070, "dynamics_loss_avg": 0.04027518718503416}
+{"step": 2070, "action_loss_avg": 0.031829644343815744}
+{"step": 2080, "dynamics_loss_avg": 0.043997930735349654}
+{"step": 2080, "action_loss_avg": 0.04011685252189636}
+{"step": 2090, "dynamics_loss_avg": 0.04765055421739817}
+{"step": 2090, "action_loss_avg": 0.0419976863078773}
+{"step": 2100, "loss": 0.0744, "learning_rate": 4.198e-05}
+{"step": 2100, "dynamics_loss_avg": 0.039620837196707726}
+{"step": 2100, "action_loss_avg": 0.03121450087055564}
+{"step": 2110, "dynamics_loss_avg": 0.04847266245633364}
+{"step": 2110, "action_loss_avg": 0.04003598242998123}
+{"step": 2120, "dynamics_loss_avg": 0.034021226596087216}
+{"step": 2120, "action_loss_avg": 0.024895633198320867}
+{"step": 2130, "dynamics_loss_avg": 0.04501803014427423}
+{"step": 2130, "action_loss_avg": 0.03372619419824332}
+{"step": 2140, "dynamics_loss_avg": 0.04511238122358918}
+{"step": 2140, "action_loss_avg": 0.03301373224239797}
+{"step": 2150, "loss": 0.073, "learning_rate": 4.2980000000000005e-05}
+{"step": 2150, "dynamics_loss_avg": 0.03852694965898991}
+{"step": 2150, "action_loss_avg": 0.03320529176853597}
+{"step": 2160, "dynamics_loss_avg": 0.04360819701105356}
+{"step": 2160, "action_loss_avg": 0.029774666484445333}
+{"step": 2170, "dynamics_loss_avg": 0.05514501258730888}
+{"step": 2170, "action_loss_avg": 0.041968144848942755}
+{"step": 2180, "dynamics_loss_avg": 0.04561285022646189}
+{"step": 2180, "action_loss_avg": 0.036955790035426615}
+{"step": 2190, "dynamics_loss_avg": 0.03938615135848522}
+{"step": 2190, "action_loss_avg": 0.025843211635947227}
+{"step": 2200, "loss": 0.0737, "learning_rate": 4.398e-05}
+{"step": 2200, "dynamics_loss_avg": 0.048997354693710804}
+{"step": 2200, "action_loss_avg": 0.03669935427606106}
+{"step": 2210, "dynamics_loss_avg": 0.04553454574197531}
+{"step": 2210, "action_loss_avg": 0.05082972832024098}
+{"step": 2220, "dynamics_loss_avg": 0.04415080174803734}
+{"step": 2220, "action_loss_avg": 0.030254151299595834}
+{"step": 2230, "dynamics_loss_avg": 0.04884373415261507}
+{"step": 2230, "action_loss_avg": 0.044309332687407735}
+{"step": 2240, "dynamics_loss_avg": 0.04165576277300716}
+{"step": 2240, "action_loss_avg": 0.03669705847278237}
+{"step": 2250, "loss": 0.0729, "learning_rate": 4.498e-05}
+{"step": 2250, "dynamics_loss_avg": 0.03046601954847574}
+{"step": 2250, "action_loss_avg": 0.025674708746373655}
+{"step": 2260, "dynamics_loss_avg": 0.04708252567797899}
+{"step": 2260, "action_loss_avg": 0.04506752137094736}
+{"step": 2270, "dynamics_loss_avg": 0.04987874235957861}
+{"step": 2270, "action_loss_avg": 0.03803054399322718}
+{"step": 2280, "dynamics_loss_avg": 0.041869658045470715}
+{"step": 2280, "action_loss_avg": 0.03278314722701907}
+{"step": 2290, "dynamics_loss_avg": 0.04280047481879592}
+{"step": 2290, "action_loss_avg": 0.03636920414865017}
+{"step": 2300, "loss": 0.0776, "learning_rate": 4.5980000000000004e-05}
+{"step": 2300, "dynamics_loss_avg": 0.03968010786920786}
+{"step": 2300, "action_loss_avg": 0.02844922533258796}
+{"step": 2310, "dynamics_loss_avg": 0.03017146959900856}
+{"step": 2310, "action_loss_avg": 0.03040381260216236}
+{"step": 2320, "dynamics_loss_avg": 0.040979309007525444}
+{"step": 2320, "action_loss_avg": 0.03622004492208362}
+{"step": 2330, "dynamics_loss_avg": 0.04205046575516462}
+{"step": 2330, "action_loss_avg": 0.033460224699229005}
+{"step": 2340, "dynamics_loss_avg": 0.03913389043882489}
+{"step": 2340, "action_loss_avg": 0.026231581112369895}
+{"step": 2350, "loss": 0.068, "learning_rate": 4.698e-05}
+{"step": 2350, "dynamics_loss_avg": 0.043936383165419104}
+{"step": 2350, "action_loss_avg": 0.028180211316794157}
+{"step": 2360, "dynamics_loss_avg": 0.05132604446262121}
+{"step": 2360, "action_loss_avg": 0.032926305942237374}
+{"step": 2370, "dynamics_loss_avg": 0.038556386902928355}
+{"step": 2370, "action_loss_avg": 0.03479043357074261}
+{"step": 2380, "dynamics_loss_avg": 0.03148434720933437}
+{"step": 2380, "action_loss_avg": 0.023890951392240824}
+{"step": 2390, "dynamics_loss_avg": 0.03403973579406738}
+{"step": 2390, "action_loss_avg": 0.0283153816126287}
+{"step": 2400, "loss": 0.0739, "learning_rate": 4.7980000000000005e-05}
+{"step": 2400, "dynamics_loss_avg": 0.042246944084763524}
+{"step": 2400, "action_loss_avg": 0.042643144726753235}
+{"step": 2410, "dynamics_loss_avg": 0.03770052939653397}
+{"step": 2410, "action_loss_avg": 0.0362011881545186}
+{"step": 2420, "dynamics_loss_avg": 0.04123502038419247}
+{"step": 2420, "action_loss_avg": 0.03221377544105053}
+{"step": 2430, "dynamics_loss_avg": 0.048365142103284596}
+{"step": 2430, "action_loss_avg": 0.042372680734843016}
+{"step": 2440, "dynamics_loss_avg": 0.04737240504473448}
+{"step": 2440, "action_loss_avg": 0.03440371658653021}
+{"step": 2450, "loss": 0.076, "learning_rate": 4.898e-05}
+{"step": 2450, "dynamics_loss_avg": 0.03950468003749848}
+{"step": 2450, "action_loss_avg": 0.03656471269205212}
+{"step": 2460, "dynamics_loss_avg": 0.04915578085929155}
+{"step": 2460, "action_loss_avg": 0.03269530218094587}
+{"step": 2470, "dynamics_loss_avg": 0.04442524258047342}
+{"step": 2470, "action_loss_avg": 0.04460184406489134}
+{"step": 2480, "dynamics_loss_avg": 0.04266061000525952}
+{"step": 2480, "action_loss_avg": 0.03525048866868019}
+{"step": 2490, "dynamics_loss_avg": 0.04415222965180874}
+{"step": 2490, "action_loss_avg": 0.029863885045051573}
+{"step": 2500, "loss": 0.0762, "learning_rate": 4.9980000000000006e-05}
+{"step": 2500, "dynamics_loss_avg": 0.053543205559253695}
+{"step": 2500, "action_loss_avg": 0.038656624779105184}
+{"step": 2510, "dynamics_loss_avg": 0.036975441966205835}
+{"step": 2510, "action_loss_avg": 0.025559032103046775}
+{"step": 2520, "dynamics_loss_avg": 0.04183960258960724}
+{"step": 2520, "action_loss_avg": 0.03380361264571548}
+{"step": 2530, "dynamics_loss_avg": 0.03239416191354394}
+{"step": 2530, "action_loss_avg": 0.027340753516182304}
+{"step": 2540, "dynamics_loss_avg": 0.03790048137307167}
+{"step": 2540, "action_loss_avg": 0.040128310956060884}
+{"step": 2550, "loss": 0.0725, "learning_rate": 5.098e-05}
+{"step": 2550, "dynamics_loss_avg": 0.047511769272387025}
+{"step": 2550, "action_loss_avg": 0.037722114473581314}
+{"step": 2560, "dynamics_loss_avg": 0.04615260483697057}
+{"step": 2560, "action_loss_avg": 0.03833363419398665}
+{"step": 2570, "dynamics_loss_avg": 0.043720435723662375}
+{"step": 2570, "action_loss_avg": 0.024563255440443754}
+{"step": 2580, "dynamics_loss_avg": 0.04499716423451901}
+{"step": 2580, "action_loss_avg": 0.0350631644949317}
+{"step": 2590, "dynamics_loss_avg": 0.046551286801695825}
+{"step": 2590, "action_loss_avg": 0.03319952692836523}
+{"step": 2600, "loss": 0.071, "learning_rate": 5.198000000000001e-05}
+{"step": 2600, "dynamics_loss_avg": 0.04389179367572069}
+{"step": 2600, "action_loss_avg": 0.04416268412023783}
+{"step": 2610, "dynamics_loss_avg": 0.037078965734690425}
+{"step": 2610, "action_loss_avg": 0.026025406550616026}
+{"step": 2620, "dynamics_loss_avg": 0.03845812808722258}
+{"step": 2620, "action_loss_avg": 0.022183506190776824}
+{"step": 2630, "dynamics_loss_avg": 0.03173362649977207}
+{"step": 2630, "action_loss_avg": 0.02987297745421529}
+{"step": 2640, "dynamics_loss_avg": 0.04020787607878447}
+{"step": 2640, "action_loss_avg": 0.024669360462576152}
+{"step": 2650, "loss": 0.0615, "learning_rate": 5.2980000000000004e-05}
+{"step": 2650, "dynamics_loss_avg": 0.043106459826231}
+{"step": 2650, "action_loss_avg": 0.0317055300809443}
+{"step": 2660, "dynamics_loss_avg": 0.03541585020720959}
+{"step": 2660, "action_loss_avg": 0.025095580238848926}
+{"step": 2670, "dynamics_loss_avg": 0.04840256981551647}
+{"step": 2670, "action_loss_avg": 0.03231869647279382}
+{"step": 2680, "dynamics_loss_avg": 0.03681760746985674}
+{"step": 2680, "action_loss_avg": 0.03826742647215724}
+{"step": 2690, "dynamics_loss_avg": 0.035404380038380624}
+{"step": 2690, "action_loss_avg": 0.02973365020006895}
+{"step": 2700, "loss": 0.0703, "learning_rate": 5.3979999999999995e-05}
+{"step": 2700, "dynamics_loss_avg": 0.048369483556598425}
+{"step": 2700, "action_loss_avg": 0.033481250773184}
+{"step": 2710, "dynamics_loss_avg": 0.04101090468466282}
+{"step": 2710, "action_loss_avg": 0.02835016595199704}
+{"step": 2720, "dynamics_loss_avg": 0.04428157787770033}
+{"step": 2720, "action_loss_avg": 0.035916192643344405}
+{"step": 2730, "dynamics_loss_avg": 0.048185115307569505}
+{"step": 2730, "action_loss_avg": 0.026634909957647324}
+{"step": 2740, "dynamics_loss_avg": 0.03896329570561648}
+{"step": 2740, "action_loss_avg": 0.03187654223293066}
+{"step": 2750, "loss": 0.0708, "learning_rate": 5.498e-05}
+{"step": 2750, "dynamics_loss_avg": 0.04632456842809916}
+{"step": 2750, "action_loss_avg": 0.03036422738805413}
+{"step": 2760, "dynamics_loss_avg": 0.04029691629111767}
+{"step": 2760, "action_loss_avg": 0.024197444878518583}
+{"step": 2770, "dynamics_loss_avg": 0.05719243660569191}
+{"step": 2770, "action_loss_avg": 0.04726171772927046}
+{"step": 2780, "dynamics_loss_avg": 0.031145979650318623}
+{"step": 2780, "action_loss_avg": 0.021085683442652225}
+{"step": 2790, "dynamics_loss_avg": 0.04541426617652178}
+{"step": 2790, "action_loss_avg": 0.03953054305166006}
+{"step": 2800, "loss": 0.0697, "learning_rate": 5.5979999999999996e-05}
+{"step": 2800, "dynamics_loss_avg": 0.030985095724463462}
+{"step": 2800, "action_loss_avg": 0.02822023080661893}
+{"step": 2810, "dynamics_loss_avg": 0.04712366554886103}
+{"step": 2810, "action_loss_avg": 0.033355957642197606}
+{"step": 2820, "dynamics_loss_avg": 0.028223712323233487}
+{"step": 2820, "action_loss_avg": 0.024136140709742904}
+{"step": 2830, "dynamics_loss_avg": 0.05039715133607388}
+{"step": 2830, "action_loss_avg": 0.037696226872503756}
+{"step": 2840, "dynamics_loss_avg": 0.039349929057061674}
+{"step": 2840, "action_loss_avg": 0.034929709415882824}
+{"step": 2850, "loss": 0.0654, "learning_rate": 5.698e-05}
+{"step": 2850, "dynamics_loss_avg": 0.0377464409917593}
+{"step": 2850, "action_loss_avg": 0.02373496282380074}
+{"step": 2860, "dynamics_loss_avg": 0.03975267494097352}
+{"step": 2860, "action_loss_avg": 0.023535468708723785}
+{"step": 2870, "dynamics_loss_avg": 0.04212452732026577}
+{"step": 2870, "action_loss_avg": 0.03782416395843029}
+{"step": 2880, "dynamics_loss_avg": 0.030647218599915503}
+{"step": 2880, "action_loss_avg": 0.018571341037750246}
+{"step": 2890, "dynamics_loss_avg": 0.03753575924783945}
+{"step": 2890, "action_loss_avg": 0.035518194525502624}
+{"step": 2900, "loss": 0.0606, "learning_rate": 5.7980000000000004e-05}
+{"step": 2900, "dynamics_loss_avg": 0.034107157960534096}
+{"step": 2900, "action_loss_avg": 0.02253457373008132}
+{"step": 2910, "dynamics_loss_avg": 0.037569877691566944}
+{"step": 2910, "action_loss_avg": 0.02552098874002695}
+{"step": 2920, "dynamics_loss_avg": 0.03994416519999504}
+{"step": 2920, "action_loss_avg": 0.029519334039650857}
+{"step": 2930, "dynamics_loss_avg": 0.04657162968069315}
+{"step": 2930, "action_loss_avg": 0.0330234233289957}
+{"step": 2940, "dynamics_loss_avg": 0.03717928156256676}
+{"step": 2940, "action_loss_avg": 0.040297671873122456}
+{"step": 2950, "loss": 0.0646, "learning_rate": 5.898e-05}
+{"step": 2950, "dynamics_loss_avg": 0.03994550798088312}
+{"step": 2950, "action_loss_avg": 0.025864859484136103}
+{"step": 2960, "dynamics_loss_avg": 0.03931346023455262}
+{"step": 2960, "action_loss_avg": 0.023898232681676745}
+{"step": 2970, "dynamics_loss_avg": 0.035681710205972196}
+{"step": 2970, "action_loss_avg": 0.034732069447636606}
+{"step": 2980, "dynamics_loss_avg": 0.050240075774490835}
+{"step": 2980, "action_loss_avg": 0.033777845185250045}
+{"step": 2990, "dynamics_loss_avg": 0.04147660089656711}
+{"step": 2990, "action_loss_avg": 0.0316450641490519}
+{"step": 3000, "loss": 0.0679, "learning_rate": 5.9980000000000005e-05}
+{"step": 3000, "dynamics_loss_avg": 0.03581813219934702}
+{"step": 3000, "action_loss_avg": 0.024997542425990105}
+{"step": 3010, "dynamics_loss_avg": 0.040792541764676574}
+{"step": 3010, "action_loss_avg": 0.02591155390255153}
+{"step": 3020, "dynamics_loss_avg": 0.04014132525771856}
+{"step": 3020, "action_loss_avg": 0.027897689212113618}
+{"step": 3030, "dynamics_loss_avg": 0.04720658380538225}
+{"step": 3030, "action_loss_avg": 0.03224955452606082}
+{"step": 3040, "dynamics_loss_avg": 0.04299385342746973}
+{"step": 3040, "action_loss_avg": 0.03386198868975043}
+{"step": 3050, "loss": 0.0683, "learning_rate": 6.098e-05}
+{"step": 3050, "dynamics_loss_avg": 0.046168492268770935}
+{"step": 3050, "action_loss_avg": 0.029733015317469837}
+{"step": 3060, "dynamics_loss_avg": 0.03700006864964962}
+{"step": 3060, "action_loss_avg": 0.021876977244392037}
+{"step": 3070, "dynamics_loss_avg": 0.050913602113723755}
+{"step": 3070, "action_loss_avg": 0.032961814850568774}
+{"step": 3080, "dynamics_loss_avg": 0.03721815440803766}
+{"step": 3080, "action_loss_avg": 0.02040137266740203}
+{"step": 3090, "dynamics_loss_avg": 0.03793848529458046}
+{"step": 3090, "action_loss_avg": 0.02949686869978905}
+{"step": 3100, "loss": 0.0641, "learning_rate": 6.198e-05}
+{"step": 3100, "dynamics_loss_avg": 0.03955062422901392}
+{"step": 3100, "action_loss_avg": 0.01910050129517913}
+{"step": 3110, "dynamics_loss_avg": 0.03871195139363408}
+{"step": 3110, "action_loss_avg": 0.023746554646641015}
+{"step": 3120, "dynamics_loss_avg": 0.03702430441044271}
+{"step": 3120, "action_loss_avg": 0.03373632486909628}
+{"step": 3130, "dynamics_loss_avg": 0.04065715558826923}
+{"step": 3130, "action_loss_avg": 0.023138166510034353}
+{"step": 3140, "dynamics_loss_avg": 0.03890658337622881}
+{"step": 3140, "action_loss_avg": 0.030618497915565968}
+{"step": 3150, "loss": 0.0647, "learning_rate": 6.298000000000001e-05}
+{"step": 3150, "dynamics_loss_avg": 0.042166348174214364}
+{"step": 3150, "action_loss_avg": 0.025795821379870177}
+{"step": 3160, "dynamics_loss_avg": 0.03301654066890478}
+{"step": 3160, "action_loss_avg": 0.025761826522648336}
+{"step": 3170, "dynamics_loss_avg": 0.04907946810126305}
+{"step": 3170, "action_loss_avg": 0.03132323799654842}
+{"step": 3180, "dynamics_loss_avg": 0.038952951319515705}
+{"step": 3180, "action_loss_avg": 0.021562909614294766}
+{"step": 3190, "dynamics_loss_avg": 0.04006544817239046}
+{"step": 3190, "action_loss_avg": 0.029625556292012335}
+{"step": 3200, "loss": 0.0606, "learning_rate": 6.398000000000001e-05}
+{"step": 3200, "dynamics_loss_avg": 0.03573660627007484}
+{"step": 3200, "action_loss_avg": 0.019219221523962916}
+{"step": 3210, "dynamics_loss_avg": 0.032116469368338584}
+{"step": 3210, "action_loss_avg": 0.025404068734496833}
+{"step": 3220, "dynamics_loss_avg": 0.04084739629179239}
+{"step": 3220, "action_loss_avg": 0.021221171645447613}
+{"step": 3230, "dynamics_loss_avg": 0.04662902066484094}
+{"step": 3230, "action_loss_avg": 0.022501625400036574}
+{"step": 3240, "dynamics_loss_avg": 0.038695093244314194}
+{"step": 3240, "action_loss_avg": 0.0201533708255738}
+{"step": 3250, "loss": 0.0593, "learning_rate": 6.498e-05}
+{"step": 3250, "dynamics_loss_avg": 0.03762256260961294}
+{"step": 3250, "action_loss_avg": 0.02201535729691386}
+{"step": 3260, "dynamics_loss_avg": 0.02870223540812731}
+{"step": 3260, "action_loss_avg": 0.019019294274039568}
+{"step": 3270, "dynamics_loss_avg": 0.04468312561511993}
+{"step": 3270, "action_loss_avg": 0.024499955587089062}
+{"step": 3280, "dynamics_loss_avg": 0.041846868488937615}
+{"step": 3280, "action_loss_avg": 0.01941593042574823}
+{"step": 3290, "dynamics_loss_avg": 0.040013484004884955}
+{"step": 3290, "action_loss_avg": 0.022588977310806512}
+{"step": 3300, "loss": 0.0572, "learning_rate": 6.598e-05}
+{"step": 3300, "dynamics_loss_avg": 0.04379146061837673}
+{"step": 3300, "action_loss_avg": 0.021311491448432206}
+{"step": 3310, "dynamics_loss_avg": 0.03780382815748453}
+{"step": 3310, "action_loss_avg": 0.01690564570017159}
+{"step": 3320, "dynamics_loss_avg": 0.03498084805905819}
+{"step": 3320, "action_loss_avg": 0.020291871053632348}
+{"step": 3330, "dynamics_loss_avg": 0.03438248988240957}
+{"step": 3330, "action_loss_avg": 0.018195153586566447}
+{"step": 3340, "dynamics_loss_avg": 0.031400922872126105}
+{"step": 3340, "action_loss_avg": 0.014735525380820036}
+{"step": 3350, "loss": 0.0528, "learning_rate": 6.698e-05}
+{"step": 3350, "dynamics_loss_avg": 0.033237314131110904}
+{"step": 3350, "action_loss_avg": 0.016257043019868432}
+{"step": 3360, "dynamics_loss_avg": 0.04614159278571606}
+{"step": 3360, "action_loss_avg": 0.029521980416029693}
+{"step": 3370, "dynamics_loss_avg": 0.04581981189548969}
+{"step": 3370, "action_loss_avg": 0.026764180231839418}
+{"step": 3380, "dynamics_loss_avg": 0.032245225831866266}
+{"step": 3380, "action_loss_avg": 0.01812570565380156}
+{"step": 3390, "dynamics_loss_avg": 0.03950322587043047}
+{"step": 3390, "action_loss_avg": 0.02059394116513431}
+{"step": 3400, "loss": 0.0599, "learning_rate": 6.798e-05}
+{"step": 3400, "dynamics_loss_avg": 0.032286892831325534}
+{"step": 3400, "action_loss_avg": 0.02178456885740161}
+{"step": 3410, "dynamics_loss_avg": 0.03987069120630622}
+{"step": 3410, "action_loss_avg": 0.018656302080489694}
+{"step": 3420, "dynamics_loss_avg": 0.03369628805667162}
+{"step": 3420, "action_loss_avg": 0.014726446475833654}
+{"step": 3430, "dynamics_loss_avg": 0.04484326653182506}
+{"step": 3430, "action_loss_avg": 0.02038784953765571}
+{"step": 3440, "dynamics_loss_avg": 0.03295185985043645}
+{"step": 3440, "action_loss_avg": 0.018274851189926267}
+{"step": 3450, "loss": 0.0546, "learning_rate": 6.898e-05}
+{"step": 3450, "dynamics_loss_avg": 0.04481373280286789}
+{"step": 3450, "action_loss_avg": 0.025587058067321776}
+{"step": 3460, "dynamics_loss_avg": 0.02791198268532753}
+{"step": 3460, "action_loss_avg": 0.015718831773847343}
+{"step": 3470, "dynamics_loss_avg": 0.04341101925820112}
+{"step": 3470, "action_loss_avg": 0.02177795385941863}
+{"step": 3480, "dynamics_loss_avg": 0.036635218327865}
+{"step": 3480, "action_loss_avg": 0.01834146180190146}
+{"step": 3490, "dynamics_loss_avg": 0.03961309986189008}
+{"step": 3490, "action_loss_avg": 0.020817032735794782}
+{"step": 3500, "loss": 0.0523, "learning_rate": 6.998e-05}
+{"step": 3500, "dynamics_loss_avg": 0.043486088141798974}
+{"step": 3500, "action_loss_avg": 0.021356341848149895}
+{"step": 3510, "dynamics_loss_avg": 0.044130277913063766}
+{"step": 3510, "action_loss_avg": 0.017895432747900487}
+{"step": 3520, "dynamics_loss_avg": 0.04604286178946495}
+{"step": 3520, "action_loss_avg": 0.024951378162950278}
+{"step": 3530, "dynamics_loss_avg": 0.034725002199411395}
+{"step": 3530, "action_loss_avg": 0.018972246348857878}
+{"step": 3540, "dynamics_loss_avg": 0.03547877231612802}
+{"step": 3540, "action_loss_avg": 0.014239752292633056}
+{"step": 3550, "loss": 0.0573, "learning_rate": 7.098e-05}
+{"step": 3550, "dynamics_loss_avg": 0.03998791435733438}
+{"step": 3550, "action_loss_avg": 0.022556232078932224}
+{"step": 3560, "dynamics_loss_avg": 0.0397700259461999}
+{"step": 3560, "action_loss_avg": 0.02066680509597063}
+{"step": 3570, "dynamics_loss_avg": 0.03953773593530059}
+{"step": 3570, "action_loss_avg": 0.017044776305556297}
+{"step": 3580, "dynamics_loss_avg": 0.04054586980491877}
+{"step": 3580, "action_loss_avg": 0.017370326165109872}
+{"step": 3590, "dynamics_loss_avg": 0.044820275902748105}
+{"step": 3590, "action_loss_avg": 0.017257337225601077}
+{"step": 3600, "loss": 0.0604, "learning_rate": 7.198e-05}
+{"step": 3600, "dynamics_loss_avg": 0.05075683705508709}
+{"step": 3600, "action_loss_avg": 0.02329415678977966}
+{"step": 3610, "dynamics_loss_avg": 0.04461650950834155}
+{"step": 3610, "action_loss_avg": 0.016441755322739483}
+{"step": 3620, "dynamics_loss_avg": 0.02899720100685954}
+{"step": 3620, "action_loss_avg": 0.013987641129642726}
+{"step": 3630, "dynamics_loss_avg": 0.0362080916762352}
+{"step": 3630, "action_loss_avg": 0.016745925601571798}
+{"step": 3640, "dynamics_loss_avg": 0.04709347486495972}
+{"step": 3640, "action_loss_avg": 0.021527438331395386}
+{"step": 3650, "loss": 0.0538, "learning_rate": 7.298000000000001e-05}
+{"step": 3650, "dynamics_loss_avg": 0.038449876569211484}
+{"step": 3650, "action_loss_avg": 0.018088378943502903}
+{"step": 3660, "dynamics_loss_avg": 0.03544101491570473}
+{"step": 3660, "action_loss_avg": 0.016007187124341727}
+{"step": 3670, "dynamics_loss_avg": 0.048108928836882114}
+{"step": 3670, "action_loss_avg": 0.025476598739624025}
+{"step": 3680, "dynamics_loss_avg": 0.04541325746104121}
+{"step": 3680, "action_loss_avg": 0.016575092799030244}
+{"step": 3690, "dynamics_loss_avg": 0.03376276027411222}
+{"step": 3690, "action_loss_avg": 0.017934373999014496}
+{"step": 3700, "loss": 0.0596, "learning_rate": 7.398e-05}
+{"step": 3700, "dynamics_loss_avg": 0.046601643599569795}
+{"step": 3700, "action_loss_avg": 0.019683111272752286}
+{"step": 3710, "dynamics_loss_avg": 0.03234381154179573}
+{"step": 3710, "action_loss_avg": 0.018540881387889386}
+{"step": 3720, "dynamics_loss_avg": 0.03845567051321268}
+{"step": 3720, "action_loss_avg": 0.015136870229616762}
+{"step": 3730, "dynamics_loss_avg": 0.044381327275186774}
+{"step": 3730, "action_loss_avg": 0.020892216823995113}
+{"step": 3740, "dynamics_loss_avg": 0.05026582255959511}
+{"step": 3740, "action_loss_avg": 0.019710063375532626}
+{"step": 3750, "loss": 0.0557, "learning_rate": 7.498e-05}
+{"step": 3750, "dynamics_loss_avg": 0.038542781677097085}
+{"step": 3750, "action_loss_avg": 0.014197837607935072}
+{"step": 3760, "dynamics_loss_avg": 0.04188108453527093}
+{"step": 3760, "action_loss_avg": 0.013862844789400697}
+{"step": 3770, "dynamics_loss_avg": 0.03562977202236652}
+{"step": 3770, "action_loss_avg": 0.01783473128452897}
+{"step": 3780, "dynamics_loss_avg": 0.04028190020471811}
+{"step": 3780, "action_loss_avg": 0.017257141508162023}
+{"step": 3790, "dynamics_loss_avg": 0.043210354447364804}
+{"step": 3790, "action_loss_avg": 0.015993301337584854}
+{"step": 3800, "loss": 0.0531, "learning_rate": 7.598e-05}
+{"step": 3800, "dynamics_loss_avg": 0.03257402824237943}
+{"step": 3800, "action_loss_avg": 0.013468062225729226}
+{"step": 3810, "dynamics_loss_avg": 0.05646385867148638}
+{"step": 3810, "action_loss_avg": 0.020766145666129887}
+{"step": 3820, "dynamics_loss_avg": 0.032913665287196636}
+{"step": 3820, "action_loss_avg": 0.01261716689914465}
+{"step": 3830, "dynamics_loss_avg": 0.036629164777696135}
+{"step": 3830, "action_loss_avg": 0.017899500019848347}
+{"step": 3840, "dynamics_loss_avg": 0.040815805457532404}
+{"step": 3840, "action_loss_avg": 0.01856629131361842}
+{"step": 3850, "loss": 0.0555, "learning_rate": 7.698000000000001e-05}
+{"step": 3850, "dynamics_loss_avg": 0.03775844220072031}
+{"step": 3850, "action_loss_avg": 0.01599939363077283}
+{"step": 3860, "dynamics_loss_avg": 0.04386280784383416}
+{"step": 3860, "action_loss_avg": 0.019533228408545256}
+{"step": 3870, "dynamics_loss_avg": 0.03637006040662527}
+{"step": 3870, "action_loss_avg": 0.019241213519126176}
+{"step": 3880, "dynamics_loss_avg": 0.034762988053262237}
+{"step": 3880, "action_loss_avg": 0.01474716505035758}
+{"step": 3890, "dynamics_loss_avg": 0.03022945821285248}
+{"step": 3890, "action_loss_avg": 0.011567170615307987}
+{"step": 3900, "loss": 0.05, "learning_rate": 7.798000000000001e-05}
+{"step": 3900, "dynamics_loss_avg": 0.04540950581431389}
+{"step": 3900, "action_loss_avg": 0.018446555687114598}
+{"step": 3910, "dynamics_loss_avg": 0.04348053187131882}
+{"step": 3910, "action_loss_avg": 0.01795674003660679}
+{"step": 3920, "dynamics_loss_avg": 0.03312827656045556}
+{"step": 3920, "action_loss_avg": 0.010761327110230923}
+{"step": 3930, "dynamics_loss_avg": 0.03552855895832181}
+{"step": 3930, "action_loss_avg": 0.016384615818969904}
+{"step": 3940, "dynamics_loss_avg": 0.04767362326383591}
+{"step": 3940, "action_loss_avg": 0.01659893631003797}
+{"step": 3950, "loss": 0.0536, "learning_rate": 7.897999999999999e-05}
+{"step": 3950, "dynamics_loss_avg": 0.03769562067463994}
+{"step": 3950, "action_loss_avg": 0.014796141069382429}
+{"step": 3960, "dynamics_loss_avg": 0.03298123711720109}
+{"step": 3960, "action_loss_avg": 0.010482410108670593}
+{"step": 3970, "dynamics_loss_avg": 0.04751961324363947}
+{"step": 3970, "action_loss_avg": 0.01749492883682251}
+{"step": 3980, "dynamics_loss_avg": 0.0341399010270834}
+{"step": 3980, "action_loss_avg": 0.012275633681565524}
+{"step": 3990, "dynamics_loss_avg": 0.04035472497344017}
+{"step": 3990, "action_loss_avg": 0.013868901366367935}
+{"step": 4000, "loss": 0.0485, "learning_rate": 7.998e-05}
+{"step": 4000, "dynamics_loss_avg": 0.042779180221259594}
+{"step": 4000, "action_loss_avg": 0.013226109696552158}
+{"step": 4010, "dynamics_loss_avg": 0.047647703997790815}
+{"step": 4010, "action_loss_avg": 0.01457090312615037}
+{"step": 4020, "dynamics_loss_avg": 0.03410789240151644}
+{"step": 4020, "action_loss_avg": 0.010618948843330145}
+{"step": 4030, "dynamics_loss_avg": 0.036969931703060864}
+{"step": 4030, "action_loss_avg": 0.014671871019527317}
+{"step": 4040, "dynamics_loss_avg": 0.03922393545508385}
+{"step": 4040, "action_loss_avg": 0.012332711601629853}
+{"step": 4050, "loss": 0.0511, "learning_rate": 8.098e-05}
+{"step": 4050, "dynamics_loss_avg": 0.03087110919877887}
+{"step": 4050, "action_loss_avg": 0.009128285013139248}
+{"step": 4060, "dynamics_loss_avg": 0.02888619704172015}
+{"step": 4060, "action_loss_avg": 0.007330157165415585}
+{"step": 4070, "dynamics_loss_avg": 0.037920648045837876}
+{"step": 4070, "action_loss_avg": 0.014738998049870134}
+{"step": 4080, "dynamics_loss_avg": 0.04235035236924887}
+{"step": 4080, "action_loss_avg": 0.014846103661693633}
+{"step": 4090, "dynamics_loss_avg": 0.038168411888182166}
+{"step": 4090, "action_loss_avg": 0.014589592954143882}
+{"step": 4100, "loss": 0.042, "learning_rate": 8.198e-05}
+{"step": 4100, "dynamics_loss_avg": 0.024852386396378278}
+{"step": 4100, "action_loss_avg": 0.007290729705709964}
+{"step": 4110, "dynamics_loss_avg": 0.03977001588791609}
+{"step": 4110, "action_loss_avg": 0.01329538756981492}
+{"step": 4120, "dynamics_loss_avg": 0.03645999934524298}
+{"step": 4120, "action_loss_avg": 0.013820418249815702}
+{"step": 4130, "dynamics_loss_avg": 0.042759260162711143}
+{"step": 4130, "action_loss_avg": 0.011827667709439993}
+{"step": 4140, "dynamics_loss_avg": 0.037543842755258086}
+{"step": 4140, "action_loss_avg": 0.012577270972542465}
+{"step": 4150, "loss": 0.0498, "learning_rate": 8.298000000000001e-05}
+{"step": 4150, "dynamics_loss_avg": 0.03974127098917961}
+{"step": 4150, "action_loss_avg": 0.01910796817392111}
+{"step": 4160, "dynamics_loss_avg": 0.04321647621691227}
+{"step": 4160, "action_loss_avg": 0.014578547468408943}
+{"step": 4170, "dynamics_loss_avg": 0.0371980233117938}
+{"step": 4170, "action_loss_avg": 0.014788356074132026}
+{"step": 4180, "dynamics_loss_avg": 0.028334053745493294}
+{"step": 4180, "action_loss_avg": 0.009577593870926649}
+{"step": 4190, "dynamics_loss_avg": 0.04182753041386604}
+{"step": 4190, "action_loss_avg": 0.013247598661109805}
+{"step": 4200, "loss": 0.049, "learning_rate": 8.398e-05}
+{"step": 4200, "dynamics_loss_avg": 0.04011933654546738}
+{"step": 4200, "action_loss_avg": 0.013969466090202332}
+{"step": 4210, "dynamics_loss_avg": 0.031818109285086396}
+{"step": 4210, "action_loss_avg": 0.009904589992947877}
+{"step": 4220, "dynamics_loss_avg": 0.03721224684268236}
+{"step": 4220, "action_loss_avg": 0.013354741130024194}
+{"step": 4230, "dynamics_loss_avg": 0.03762843515723944}
+{"step": 4230, "action_loss_avg": 0.014889491908252239}
+{"step": 4240, "dynamics_loss_avg": 0.03765738913789392}
+{"step": 4240, "action_loss_avg": 0.01201427187770605}
+{"step": 4250, "loss": 0.0451, "learning_rate": 8.498e-05}
+{"step": 4250, "dynamics_loss_avg": 0.03265485828742385}
+{"step": 4250, "action_loss_avg": 0.009956411924213171}
+{"step": 4260, "dynamics_loss_avg": 0.03193873986601829}
+{"step": 4260, "action_loss_avg": 0.012051420216448606}
+{"step": 4270, "dynamics_loss_avg": 0.040517366118729116}
+{"step": 4270, "action_loss_avg": 0.0131533726118505}
+{"step": 4280, "dynamics_loss_avg": 0.03349997829645872}
+{"step": 4280, "action_loss_avg": 0.015026446478441358}
+{"step": 4290, "dynamics_loss_avg": 0.04473012685775757}
+{"step": 4290, "action_loss_avg": 0.015245288703590631}
+{"step": 4300, "loss": 0.0482, "learning_rate": 8.598e-05}
+{"step": 4300, "dynamics_loss_avg": 0.03642239775508642}
+{"step": 4300, "action_loss_avg": 0.012431161198765039}
+{"step": 4310, "dynamics_loss_avg": 0.031606811471283434}
+{"step": 4310, "action_loss_avg": 0.008622144884429871}
+{"step": 4320, "dynamics_loss_avg": 0.03731195218861103}
+{"step": 4320, "action_loss_avg": 0.017172935279086234}
+{"step": 4330, "dynamics_loss_avg": 0.04315699376165867}
+{"step": 4330, "action_loss_avg": 0.013884271774441004}
+{"step": 4340, "dynamics_loss_avg": 0.03149447310715914}
+{"step": 4340, "action_loss_avg": 0.01251079780049622}
+{"step": 4350, "loss": 0.0466, "learning_rate": 8.698000000000001e-05}
+{"step": 4350, "dynamics_loss_avg": 0.04383741784840822}
+{"step": 4350, "action_loss_avg": 0.016301509039476515}
+{"step": 4360, "dynamics_loss_avg": 0.03758808486163616}
+{"step": 4360, "action_loss_avg": 0.014768785610795022}
+{"step": 4370, "dynamics_loss_avg": 0.04207934569567442}
+{"step": 4370, "action_loss_avg": 0.018690968118607997}
+{"step": 4380, "dynamics_loss_avg": 0.03700981559231877}
+{"step": 4380, "action_loss_avg": 0.013335290597751737}
+{"step": 4390, "dynamics_loss_avg": 0.04517245888710022}
+{"step": 4390, "action_loss_avg": 0.016064167860895394}
+{"step": 4400, "loss": 0.0543, "learning_rate": 8.798000000000001e-05}
+{"step": 4400, "dynamics_loss_avg": 0.036484816763550046}
+{"step": 4400, "action_loss_avg": 0.012450539553537966}
+{"step": 4410, "dynamics_loss_avg": 0.037647375371307135}
+{"step": 4410, "action_loss_avg": 0.011751216696575284}
+{"step": 4420, "dynamics_loss_avg": 0.04362615216523409}
+{"step": 4420, "action_loss_avg": 0.014485623501241208}
+{"step": 4430, "dynamics_loss_avg": 0.03804016578942537}
+{"step": 4430, "action_loss_avg": 0.01114507638849318}
+{"step": 4440, "dynamics_loss_avg": 0.03770673219114542}
+{"step": 4440, "action_loss_avg": 0.01127228862605989}
+{"step": 4450, "loss": 0.0522, "learning_rate": 8.898e-05}
+{"step": 4450, "dynamics_loss_avg": 0.05015879105776548}
+{"step": 4450, "action_loss_avg": 0.021518914960324764}
+{"step": 4460, "dynamics_loss_avg": 0.03528552819043398}
+{"step": 4460, "action_loss_avg": 0.01133841541595757}
+{"step": 4470, "dynamics_loss_avg": 0.0434573220089078}
+{"step": 4470, "action_loss_avg": 0.014371823985129595}
+{"step": 4480, "dynamics_loss_avg": 0.04387627802789211}
+{"step": 4480, "action_loss_avg": 0.013546057464554905}
+{"step": 4490, "dynamics_loss_avg": 0.030755103565752506}
+{"step": 4490, "action_loss_avg": 0.012232169602066278}
+{"step": 4500, "loss": 0.0484, "learning_rate": 8.998e-05}
+{"step": 4500, "dynamics_loss_avg": 0.02988883340731263}
+{"step": 4500, "action_loss_avg": 0.010239024925976992}
+{"step": 4510, "dynamics_loss_avg": 0.039598139189183715}
+{"step": 4510, "action_loss_avg": 0.01270781890489161}
+{"step": 4520, "dynamics_loss_avg": 0.03199728261679411}
+{"step": 4520, "action_loss_avg": 0.00985827362164855}
+{"step": 4530, "dynamics_loss_avg": 0.03905003722757101}
+{"step": 4530, "action_loss_avg": 0.015164369065314532}
+{"step": 4540, "dynamics_loss_avg": 0.026934745162725447}
+{"step": 4540, "action_loss_avg": 0.008567409007810056}
+{"step": 4550, "loss": 0.0433, "learning_rate": 9.098000000000001e-05}
+{"step": 4550, "dynamics_loss_avg": 0.0392277579754591}
+{"step": 4550, "action_loss_avg": 0.01225354429334402}
+{"step": 4560, "dynamics_loss_avg": 0.03801591899245978}
+{"step": 4560, "action_loss_avg": 0.01237698453478515}
+{"step": 4570, "dynamics_loss_avg": 0.045785116218030456}
+{"step": 4570, "action_loss_avg": 0.013695321138948202}
+{"step": 4580, "dynamics_loss_avg": 0.030865626502782108}
+{"step": 4580, "action_loss_avg": 0.010452694981358946}
+{"step": 4590, "dynamics_loss_avg": 0.036849365942180155}
+{"step": 4590, "action_loss_avg": 0.010628162184730172}
+{"step": 4600, "loss": 0.0486, "learning_rate": 9.198e-05}
+{"step": 4600, "dynamics_loss_avg": 0.04212635429576039}
+{"step": 4600, "action_loss_avg": 0.01191654906142503}
+{"step": 4610, "dynamics_loss_avg": 0.03561155432835221}
+{"step": 4610, "action_loss_avg": 0.011930949916131795}
+{"step": 4620, "dynamics_loss_avg": 0.03658017218112945}
+{"step": 4620, "action_loss_avg": 0.009040200151503086}
+{"step": 4630, "dynamics_loss_avg": 0.03989049624651671}
+{"step": 4630, "action_loss_avg": 0.012926152348518372}
+{"step": 4640, "dynamics_loss_avg": 0.035330727323889734}
+{"step": 4640, "action_loss_avg": 0.011453780997544526}
+{"step": 4650, "loss": 0.0471, "learning_rate": 9.298e-05}
+{"step": 4650, "dynamics_loss_avg": 0.0389192228205502}
+{"step": 4650, "action_loss_avg": 0.009431852353736758}
+{"step": 4660, "dynamics_loss_avg": 0.035960853099823}
+{"step": 4660, "action_loss_avg": 0.011114166048355401}
+{"step": 4670, "dynamics_loss_avg": 0.04104794841259718}
+{"step": 4670, "action_loss_avg": 0.013760973536409437}
+{"step": 4680, "dynamics_loss_avg": 0.049668941833078864}
+{"step": 4680, "action_loss_avg": 0.019584735622629523}
+{"step": 4690, "dynamics_loss_avg": 0.043173511419445275}
+{"step": 4690, "action_loss_avg": 0.011789263971149922}
+{"step": 4700, "loss": 0.0507, "learning_rate": 9.398e-05}
+{"step": 4700, "dynamics_loss_avg": 0.02947345292195678}
+{"step": 4700, "action_loss_avg": 0.007406552624888718}
+{"step": 4710, "dynamics_loss_avg": 0.033156664855778215}
+{"step": 4710, "action_loss_avg": 0.00932053525466472}
+{"step": 4720, "dynamics_loss_avg": 0.039286742359399794}
+{"step": 4720, "action_loss_avg": 0.011719320109114051}
+{"step": 4730, "dynamics_loss_avg": 0.031513788364827634}
+{"step": 4730, "action_loss_avg": 0.010618012119084596}
+{"step": 4740, "dynamics_loss_avg": 0.04466366078704596}
+{"step": 4740, "action_loss_avg": 0.01578647622372955}
+{"step": 4750, "loss": 0.0482, "learning_rate": 9.498e-05}
+{"step": 4750, "dynamics_loss_avg": 0.04007051074877381}
+{"step": 4750, "action_loss_avg": 0.01025371765717864}
+{"step": 4760, "dynamics_loss_avg": 0.03497959980741143}
+{"step": 4760, "action_loss_avg": 0.013729370571672917}
+{"step": 4770, "dynamics_loss_avg": 0.042536938562989235}
+{"step": 4770, "action_loss_avg": 0.014654992055147887}
+{"step": 4780, "dynamics_loss_avg": 0.03871332285925746}
+{"step": 4780, "action_loss_avg": 0.016312090097926557}
+{"step": 4790, "dynamics_loss_avg": 0.04378751553595066}
+{"step": 4790, "action_loss_avg": 0.01806376874446869}
+{"step": 4800, "loss": 0.0483, "learning_rate": 9.598e-05}
+{"step": 4800, "dynamics_loss_avg": 0.03212968297302723}
+{"step": 4800, "action_loss_avg": 0.009294095356017351}
+{"step": 4810, "dynamics_loss_avg": 0.041820180136710405}
+{"step": 4810, "action_loss_avg": 0.01072050416842103}
+{"step": 4820, "dynamics_loss_avg": 0.03918132577091456}
+{"step": 4820, "action_loss_avg": 0.009269858570769429}
+{"step": 4830, "dynamics_loss_avg": 0.04832685962319374}
+{"step": 4830, "action_loss_avg": 0.012696033844258636}
+{"step": 4840, "dynamics_loss_avg": 0.04558915412053466}
+{"step": 4840, "action_loss_avg": 0.012348842038773001}
+{"step": 4850, "loss": 0.0483, "learning_rate": 9.698000000000001e-05}
+{"step": 4850, "dynamics_loss_avg": 0.029287022165954114}
+{"step": 4850, "action_loss_avg": 0.008517433435190468}
+{"step": 4860, "dynamics_loss_avg": 0.03856601556763053}
+{"step": 4860, "action_loss_avg": 0.013685105834156275}
+{"step": 4870, "dynamics_loss_avg": 0.040901880152523516}
+{"step": 4870, "action_loss_avg": 0.012277303705923259}
+{"step": 4880, "dynamics_loss_avg": 0.04420218532904983}
+{"step": 4880, "action_loss_avg": 0.014363346621394157}
+{"step": 4890, "dynamics_loss_avg": 0.04010292924940586}
+{"step": 4890, "action_loss_avg": 0.010158873163163662}
+{"step": 4900, "loss": 0.0445, "learning_rate": 9.798000000000001e-05}
+{"step": 4900, "dynamics_loss_avg": 0.04131981320679188}
+{"step": 4900, "action_loss_avg": 0.0107117950450629}
+{"step": 4910, "dynamics_loss_avg": 0.04321441911160946}
+{"step": 4910, "action_loss_avg": 0.009488299861550331}
+{"step": 4920, "dynamics_loss_avg": 0.0354629447683692}
+{"step": 4920, "action_loss_avg": 0.008465611794963478}
+{"step": 4930, "dynamics_loss_avg": 0.041886611469089986}
+{"step": 4930, "action_loss_avg": 0.01388505999930203}
+{"step": 4940, "dynamics_loss_avg": 0.02752379681915045}
+{"step": 4940, "action_loss_avg": 0.007198077486827969}
+{"step": 4950, "loss": 0.0437, "learning_rate": 9.898e-05}
+{"step": 4950, "dynamics_loss_avg": 0.03596535548567772}
+{"step": 4950, "action_loss_avg": 0.010279760556295514}
+{"step": 4960, "dynamics_loss_avg": 0.03979031257331371}
+{"step": 4960, "action_loss_avg": 0.009962510736659169}
+{"step": 4970, "dynamics_loss_avg": 0.040054849721491335}
+{"step": 4970, "action_loss_avg": 0.011833624704740942}
+{"step": 4980, "dynamics_loss_avg": 0.037287873961031434}
+{"step": 4980, "action_loss_avg": 0.01118732513859868}
+{"step": 4990, "dynamics_loss_avg": 0.031321694143116474}
+{"step": 4990, "action_loss_avg": 0.010306437080726028}
+{"step": 5000, "loss": 0.0452, "learning_rate": 9.998e-05}
+{"step": 5000, "dynamics_loss_avg": 0.04075060794129968}
+{"step": 5000, "action_loss_avg": 0.010238418611697853}
+{"step": 5010, "dynamics_loss_avg": 0.044263135828077796}
+{"step": 5010, "action_loss_avg": 0.012797054648399354}
+{"step": 5020, "dynamics_loss_avg": 0.042794493632391094}
+{"step": 5020, "action_loss_avg": 0.012461108749266713}
+{"step": 5030, "dynamics_loss_avg": 0.03856637813150883}
+{"step": 5030, "action_loss_avg": 0.012006677826866508}
+{"step": 5040, "dynamics_loss_avg": 0.026761702820658685}
+{"step": 5040, "action_loss_avg": 0.008271577162668109}
+{"step": 5050, "loss": 0.0438, "learning_rate": 9.999993435757623e-05}
+{"step": 5050, "dynamics_loss_avg": 0.03383980495855212}
+{"step": 5050, "action_loss_avg": 0.008980890084058047}
+{"step": 5060, "dynamics_loss_avg": 0.03089102078229189}
+{"step": 5060, "action_loss_avg": 0.009171422384679318}
+{"step": 5070, "dynamics_loss_avg": 0.033614815864712}
+{"step": 5070, "action_loss_avg": 0.010217060463037341}
+{"step": 5080, "dynamics_loss_avg": 0.039833986479789016}
+{"step": 5080, "action_loss_avg": 0.009608287597075105}
+{"step": 5090, "dynamics_loss_avg": 0.03740807455033064}
+{"step": 5090, "action_loss_avg": 0.011842202092520893}
+{"step": 5100, "loss": 0.0479, "learning_rate": 9.99997320445808e-05}
+{"step": 5100, "dynamics_loss_avg": 0.048155561462044714}
+{"step": 5100, "action_loss_avg": 0.012024511955678463}
+{"step": 5110, "dynamics_loss_avg": 0.03349944148212671}
+{"step": 5110, "action_loss_avg": 0.01034265363123268}
+{"step": 5120, "dynamics_loss_avg": 0.035713762231171134}
+{"step": 5120, "action_loss_avg": 0.011851567169651389}
+{"step": 5130, "dynamics_loss_avg": 0.035320733883418144}
+{"step": 5130, "action_loss_avg": 0.010058093396946789}
+{"step": 5140, "dynamics_loss_avg": 0.04957262128591537}
+{"step": 5140, "action_loss_avg": 0.01658981288783252}
+{"step": 5150, "loss": 0.0472, "learning_rate": 9.999939303422718e-05}
+{"step": 5150, "dynamics_loss_avg": 0.03664840459823608}
+{"step": 5150, "action_loss_avg": 0.009271641750819981}
+{"step": 5160, "dynamics_loss_avg": 0.04087917413562536}
+{"step": 5160, "action_loss_avg": 0.011670109094120562}
+{"step": 5170, "dynamics_loss_avg": 0.04612810835242272}
+{"step": 5170, "action_loss_avg": 0.01632990804500878}
+{"step": 5180, "dynamics_loss_avg": 0.041354402899742126}
+{"step": 5180, "action_loss_avg": 0.00988541841506958}
+{"step": 5190, "dynamics_loss_avg": 0.03527660258114338}
+{"step": 5190, "action_loss_avg": 0.010388841317035259}
+{"step": 5200, "loss": 0.0502, "learning_rate": 9.999891732744224e-05}
+{"step": 5200, "dynamics_loss_avg": 0.04498683335259557}
+{"step": 5200, "action_loss_avg": 0.013170419726520777}
+{"step": 5210, "dynamics_loss_avg": 0.04408948887139559}
+{"step": 5210, "action_loss_avg": 0.009959191223606468}
+{"step": 5220, "dynamics_loss_avg": 0.03904237095266581}
+{"step": 5220, "action_loss_avg": 0.010080225067213178}
+{"step": 5230, "dynamics_loss_avg": 0.032051433250308035}
+{"step": 5230, "action_loss_avg": 0.008445036492776125}
+{"step": 5240, "dynamics_loss_avg": 0.03547193519771099}
+{"step": 5240, "action_loss_avg": 0.010568688111379742}
+{"step": 5250, "loss": 0.044, "learning_rate": 9.99983049255265e-05}
+{"step": 5250, "dynamics_loss_avg": 0.04019618779420853}
+{"step": 5250, "action_loss_avg": 0.009903175849467516}
+{"step": 5260, "dynamics_loss_avg": 0.04161137454211712}
+{"step": 5260, "action_loss_avg": 0.011603309982456267}
+{"step": 5270, "dynamics_loss_avg": 0.039212037529796365}
+{"step": 5270, "action_loss_avg": 0.011523967928951606}
+{"step": 5280, "dynamics_loss_avg": 0.04801881229504943}
+{"step": 5280, "action_loss_avg": 0.012029768573120237}
+{"step": 5290, "dynamics_loss_avg": 0.034475178457796574}
+{"step": 5290, "action_loss_avg": 0.007345994864590466}
+{"step": 5300, "loss": 0.0457, "learning_rate": 9.999755583015431e-05}
+{"step": 5300, "dynamics_loss_avg": 0.03801638577133417}
+{"step": 5300, "action_loss_avg": 0.008852743497118353}
+{"step": 5310, "dynamics_loss_avg": 0.035701708495616914}
+{"step": 5310, "action_loss_avg": 0.009190456429496407}
+{"step": 5320, "dynamics_loss_avg": 0.03515978483483195}
+{"step": 5320, "action_loss_avg": 0.010685603064484895}
+{"step": 5330, "dynamics_loss_avg": 0.032023852691054344}
+{"step": 5330, "action_loss_avg": 0.009346755454316735}
+{"step": 5340, "dynamics_loss_avg": 0.0404240507632494}
+{"step": 5340, "action_loss_avg": 0.011203988082706928}
+{"step": 5350, "loss": 0.0469, "learning_rate": 9.999667004337362e-05}
+{"step": 5350, "dynamics_loss_avg": 0.038868758268654345}
+{"step": 5350, "action_loss_avg": 0.012479538191109895}
+{"step": 5360, "dynamics_loss_avg": 0.044906329922378065}
+{"step": 5360, "action_loss_avg": 0.010642113210633398}
+{"step": 5370, "dynamics_loss_avg": 0.04150366997346282}
+{"step": 5370, "action_loss_avg": 0.013194211153313517}
+{"step": 5380, "dynamics_loss_avg": 0.03675007214769721}
+{"step": 5380, "action_loss_avg": 0.010464276466518641}
+{"step": 5390, "dynamics_loss_avg": 0.041583899036049844}
+{"step": 5390, "action_loss_avg": 0.010719961067661644}
+{"step": 5400, "loss": 0.0475, "learning_rate": 9.999564756760615e-05}
+{"step": 5400, "dynamics_loss_avg": 0.04111408630851656}
+{"step": 5400, "action_loss_avg": 0.009729410219006241}
+{"step": 5410, "dynamics_loss_avg": 0.03689142102375627}
+{"step": 5410, "action_loss_avg": 0.009839288727380335}
+{"step": 5420, "dynamics_loss_avg": 0.04322763253003359}
+{"step": 5420, "action_loss_avg": 0.010047769779339433}
+{"step": 5430, "dynamics_loss_avg": 0.03888002010062337}
+{"step": 5430, "action_loss_avg": 0.010389601706992834}
+{"step": 5440, "dynamics_loss_avg": 0.038577414490282534}
+{"step": 5440, "action_loss_avg": 0.010082018747925758}
+{"step": 5450, "loss": 0.0491, "learning_rate": 9.999448840564731e-05}
+{"step": 5450, "dynamics_loss_avg": 0.04109269054606557}
+{"step": 5450, "action_loss_avg": 0.011195976007729768}
+{"step": 5460, "dynamics_loss_avg": 0.04000293407589197}
+{"step": 5460, "action_loss_avg": 0.010574784781783819}
+{"step": 5470, "dynamics_loss_avg": 0.03767484091222286}
+{"step": 5470, "action_loss_avg": 0.01413962123915553}
+{"step": 5480, "dynamics_loss_avg": 0.036099843122065066}
+{"step": 5480, "action_loss_avg": 0.008760020881891251}
+{"step": 5490, "dynamics_loss_avg": 0.05215207980945706}
+{"step": 5490, "action_loss_avg": 0.017056997446343303}
+{"step": 5500, "loss": 0.0507, "learning_rate": 9.99931925606662e-05}
+{"step": 5500, "dynamics_loss_avg": 0.04330828972160816}
+{"step": 5500, "action_loss_avg": 0.010621938295662403}
+{"step": 5510, "dynamics_loss_avg": 0.04101681997999549}
+{"step": 5510, "action_loss_avg": 0.011909172730520367}
+{"step": 5520, "dynamics_loss_avg": 0.047820933256298305}
+{"step": 5520, "action_loss_avg": 0.014898932538926601}
+{"step": 5530, "dynamics_loss_avg": 0.045554399490356445}
+{"step": 5530, "action_loss_avg": 0.009898262051865458}
+{"step": 5540, "dynamics_loss_avg": 0.027593125961720942}
+{"step": 5540, "action_loss_avg": 0.006586442072875798}
+{"step": 5550, "loss": 0.0443, "learning_rate": 9.999176003620561e-05}
+{"step": 5550, "dynamics_loss_avg": 0.030745424889028074}
+{"step": 5550, "action_loss_avg": 0.010983823356218636}
+{"step": 5560, "dynamics_loss_avg": 0.0492327269166708}
+{"step": 5560, "action_loss_avg": 0.011965414020232856}
+{"step": 5570, "dynamics_loss_avg": 0.029313473403453826}
+{"step": 5570, "action_loss_avg": 0.009054910158738494}
+{"step": 5580, "dynamics_loss_avg": 0.047871414385735986}
+{"step": 5580, "action_loss_avg": 0.012234576093032957}
+{"step": 5590, "dynamics_loss_avg": 0.03664644323289394}
+{"step": 5590, "action_loss_avg": 0.00885161655023694}
+{"step": 5600, "loss": 0.046, "learning_rate": 9.999019083618202e-05}
+{"step": 5600, "dynamics_loss_avg": 0.03175194761715829}
+{"step": 5600, "action_loss_avg": 0.011279958277009427}
+{"step": 5610, "dynamics_loss_avg": 0.03766187876462936}
+{"step": 5610, "action_loss_avg": 0.008886035229079426}
+{"step": 5620, "dynamics_loss_avg": 0.034723004512488845}
+{"step": 5620, "action_loss_avg": 0.008463972411118448}
+{"step": 5630, "dynamics_loss_avg": 0.04197823768481612}
+{"step": 5630, "action_loss_avg": 0.011652672267518937}
+{"step": 5640, "dynamics_loss_avg": 0.04370759036391973}
+{"step": 5640, "action_loss_avg": 0.011252067564055324}
+{"step": 5650, "loss": 0.0454, "learning_rate": 9.998848496488556e-05}
+{"step": 5650, "dynamics_loss_avg": 0.03309574807062745}
+{"step": 5650, "action_loss_avg": 0.008736266102641822}
+{"step": 5660, "dynamics_loss_avg": 0.04003755040466785}
+{"step": 5660, "action_loss_avg": 0.00971366201993078}
+{"step": 5670, "dynamics_loss_avg": 0.04197998531162739}
+{"step": 5670, "action_loss_avg": 0.013084343215450645}
+{"step": 5680, "dynamics_loss_avg": 0.04220176674425602}
+{"step": 5680, "action_loss_avg": 0.009852588456124068}
+{"step": 5690, "dynamics_loss_avg": 0.045183562114834784}
+{"step": 5690, "action_loss_avg": 0.011679024528712034}
+{"step": 5700, "loss": 0.0459, "learning_rate": 9.998664242698e-05}
+{"step": 5700, "dynamics_loss_avg": 0.033738456945866344}
+{"step": 5700, "action_loss_avg": 0.008121145982295274}
+{"step": 5710, "dynamics_loss_avg": 0.03936161547899246}
+{"step": 5710, "action_loss_avg": 0.011155297420918942}
+{"step": 5720, "dynamics_loss_avg": 0.04427520260214805}
+{"step": 5720, "action_loss_avg": 0.011163779953494667}
+{"step": 5730, "dynamics_loss_avg": 0.039867323264479636}
+{"step": 5730, "action_loss_avg": 0.010047085955739022}
+{"step": 5740, "dynamics_loss_avg": 0.04056972209364176}
+{"step": 5740, "action_loss_avg": 0.009165908955037595}
+{"step": 5750, "loss": 0.0481, "learning_rate": 9.998466322750278e-05}
+{"step": 5750, "dynamics_loss_avg": 0.03851835476234555}
+{"step": 5750, "action_loss_avg": 0.008075687650125474}
+{"step": 5760, "dynamics_loss_avg": 0.03694655783474445}
+{"step": 5760, "action_loss_avg": 0.008146814350038768}
+{"step": 5770, "dynamics_loss_avg": 0.03610433358699083}
+{"step": 5770, "action_loss_avg": 0.009500093571841717}
+{"step": 5780, "dynamics_loss_avg": 0.03484469000250101}
+{"step": 5780, "action_loss_avg": 0.006692626141011715}
+{"step": 5790, "dynamics_loss_avg": 0.03391055855900049}
+{"step": 5790, "action_loss_avg": 0.008936888515017926}
+{"step": 5800, "loss": 0.0421, "learning_rate": 9.998254737186496e-05}
+{"step": 5800, "dynamics_loss_avg": 0.030314137134701012}
+{"step": 5800, "action_loss_avg": 0.007881533296313137}
+{"step": 5810, "dynamics_loss_avg": 0.03455552216619253}
+{"step": 5810, "action_loss_avg": 0.007690942077897489}
+{"step": 5820, "dynamics_loss_avg": 0.05185496397316456}
+{"step": 5820, "action_loss_avg": 0.014988023415207863}
+{"step": 5830, "dynamics_loss_avg": 0.03572063678875566}
+{"step": 5830, "action_loss_avg": 0.009367301303427666}
+{"step": 5840, "dynamics_loss_avg": 0.028540079575031997}
+{"step": 5840, "action_loss_avg": 0.0074874389916658405}
+{"step": 5850, "loss": 0.0458, "learning_rate": 9.99802948658512e-05}
+{"step": 5850, "dynamics_loss_avg": 0.04144113250076771}
+{"step": 5850, "action_loss_avg": 0.012144274218007923}
+{"step": 5860, "dynamics_loss_avg": 0.04219719674438238}
+{"step": 5860, "action_loss_avg": 0.010692483885213733}
+{"step": 5870, "dynamics_loss_avg": 0.04555683070793748}
+{"step": 5870, "action_loss_avg": 0.013100062916055321}
+{"step": 5880, "dynamics_loss_avg": 0.03428178913891315}
+{"step": 5880, "action_loss_avg": 0.009890221373643726}
+{"step": 5890, "dynamics_loss_avg": 0.024593292269855738}
+{"step": 5890, "action_loss_avg": 0.005516088649164886}
+{"step": 5900, "loss": 0.0448, "learning_rate": 9.997790571561978e-05}
+{"step": 5900, "dynamics_loss_avg": 0.03470110353082419}
+{"step": 5900, "action_loss_avg": 0.010202586511150002}
+{"step": 5910, "dynamics_loss_avg": 0.03819309882819653}
+{"step": 5910, "action_loss_avg": 0.012172606121748687}
+{"step": 5920, "dynamics_loss_avg": 0.03698347853496671}
+{"step": 5920, "action_loss_avg": 0.010813318938016892}
+{"step": 5930, "dynamics_loss_avg": 0.038877705670893194}
+{"step": 5930, "action_loss_avg": 0.009911479707807303}
+{"step": 5940, "dynamics_loss_avg": 0.03419105522334576}
+{"step": 5940, "action_loss_avg": 0.007195547572337091}
+{"step": 5950, "loss": 0.0418, "learning_rate": 9.997537992770252e-05}
+{"step": 5950, "dynamics_loss_avg": 0.035838084388524295}
+{"step": 5950, "action_loss_avg": 0.008385492768138648}
+{"step": 5960, "dynamics_loss_avg": 0.03642168324440718}
+{"step": 5960, "action_loss_avg": 0.010027825785800814}
+{"step": 5970, "dynamics_loss_avg": 0.04178188890218735}
+{"step": 5970, "action_loss_avg": 0.009756684675812722}
+{"step": 5980, "dynamics_loss_avg": 0.040987618081271646}
+{"step": 5980, "action_loss_avg": 0.009328320017084479}
+{"step": 5990, "dynamics_loss_avg": 0.04954051803797484}
+{"step": 5990, "action_loss_avg": 0.01250924365594983}
+{"step": 6000, "loss": 0.0452, "learning_rate": 9.997271750900486e-05}
+{"step": 6000, "dynamics_loss_avg": 0.03824748583137989}
+{"step": 6000, "action_loss_avg": 0.008029318181797862}
+{"step": 6010, "dynamics_loss_avg": 0.04544186042621732}
+{"step": 6010, "action_loss_avg": 0.011040348466485739}
+{"step": 6020, "dynamics_loss_avg": 0.04179268386214972}
+{"step": 6020, "action_loss_avg": 0.009447410516440869}
+{"step": 6030, "dynamics_loss_avg": 0.05078297508880496}
+{"step": 6030, "action_loss_avg": 0.013276751607190818}
+{"step": 6040, "dynamics_loss_avg": 0.03203498553484678}
+{"step": 6040, "action_loss_avg": 0.008398693567141891}
+{"step": 6050, "loss": 0.0475, "learning_rate": 9.996991846680572e-05}
+{"step": 6050, "dynamics_loss_avg": 0.044550946820527314}
+{"step": 6050, "action_loss_avg": 0.010203228611499072}
+{"step": 6060, "dynamics_loss_avg": 0.042876843549311164}
+{"step": 6060, "action_loss_avg": 0.011037351610139013}
+{"step": 6070, "dynamics_loss_avg": 0.028173681534826755}
+{"step": 6070, "action_loss_avg": 0.009308416722342372}
+{"step": 6080, "dynamics_loss_avg": 0.03650148492306471}
+{"step": 6080, "action_loss_avg": 0.00862096408382058}
+{"step": 6090, "dynamics_loss_avg": 0.036820020712912085}
+{"step": 6090, "action_loss_avg": 0.008959836279973387}
+{"step": 6100, "loss": 0.0444, "learning_rate": 9.996698280875759e-05}
+{"step": 6100, "dynamics_loss_avg": 0.035043015517294406}
+{"step": 6100, "action_loss_avg": 0.007198851590510457}
+{"step": 6110, "dynamics_loss_avg": 0.03356611840426922}
+{"step": 6110, "action_loss_avg": 0.007581884961109608}
+{"step": 6120, "dynamics_loss_avg": 0.03292624950408936}
+{"step": 6120, "action_loss_avg": 0.009357933094725013}
+{"step": 6130, "dynamics_loss_avg": 0.04163856487721205}
+{"step": 6130, "action_loss_avg": 0.01200635782442987}
+{"step": 6140, "dynamics_loss_avg": 0.03733694925904274}
+{"step": 6140, "action_loss_avg": 0.009737009392119944}
+{"step": 6150, "loss": 0.0464, "learning_rate": 9.996391054288646e-05}
+{"step": 6150, "dynamics_loss_avg": 0.03403553888201714}
+{"step": 6150, "action_loss_avg": 0.007377533824183047}
+{"step": 6160, "dynamics_loss_avg": 0.032960515841841696}
+{"step": 6160, "action_loss_avg": 0.007729178923182189}
+{"step": 6170, "dynamics_loss_avg": 0.034298472292721274}
+{"step": 6170, "action_loss_avg": 0.0101140639744699}
+{"step": 6180, "dynamics_loss_avg": 0.035673401597887275}
+{"step": 6180, "action_loss_avg": 0.007447266671806574}
+{"step": 6190, "dynamics_loss_avg": 0.030811468511819838}
+{"step": 6190, "action_loss_avg": 0.006306955497711897}
+{"step": 6200, "loss": 0.0396, "learning_rate": 9.996070167759175e-05}
+{"step": 6200, "dynamics_loss_avg": 0.02994765043258667}
+{"step": 6200, "action_loss_avg": 0.006247377506224438}
+{"step": 6210, "dynamics_loss_avg": 0.047011691890656945}
+{"step": 6210, "action_loss_avg": 0.012305783550255}
+{"step": 6220, "dynamics_loss_avg": 0.03366022817790508}
+{"step": 6220, "action_loss_avg": 0.007780553633347153}
+{"step": 6230, "dynamics_loss_avg": 0.043655759654939175}
+{"step": 6230, "action_loss_avg": 0.00969090494327247}
+{"step": 6240, "dynamics_loss_avg": 0.038040165044367316}
+{"step": 6240, "action_loss_avg": 0.008059475314803421}
+{"step": 6250, "loss": 0.0423, "learning_rate": 9.995735622164641e-05}
+{"step": 6250, "dynamics_loss_avg": 0.03301556147634983}
+{"step": 6250, "action_loss_avg": 0.007810522732324898}
+{"step": 6260, "dynamics_loss_avg": 0.04555429834872484}
+{"step": 6260, "action_loss_avg": 0.013801405020058156}
+{"step": 6270, "dynamics_loss_avg": 0.042206096835434435}
+{"step": 6270, "action_loss_avg": 0.012455080216750503}
+{"step": 6280, "dynamics_loss_avg": 0.04059477467089891}
+{"step": 6280, "action_loss_avg": 0.011976997600868344}
+{"step": 6290, "dynamics_loss_avg": 0.03694322118535638}
+{"step": 6290, "action_loss_avg": 0.009993872349150478}
+{"step": 6300, "loss": 0.0465, "learning_rate": 9.995387418419677e-05}
+{"step": 6300, "dynamics_loss_avg": 0.03691779039800167}
+{"step": 6300, "action_loss_avg": 0.007142846297938377}
+{"step": 6310, "dynamics_loss_avg": 0.03847887245938182}
+{"step": 6310, "action_loss_avg": 0.010169144649989904}
+{"step": 6320, "dynamics_loss_avg": 0.03798536965623498}
+{"step": 6320, "action_loss_avg": 0.007768772286362946}
+{"step": 6330, "dynamics_loss_avg": 0.03209472084417939}
+{"step": 6330, "action_loss_avg": 0.007604949153028428}
+{"step": 6340, "dynamics_loss_avg": 0.043524004984647036}
+{"step": 6340, "action_loss_avg": 0.0097347786067985}
+{"step": 6350, "loss": 0.0448, "learning_rate": 9.995025557476261e-05}
+{"step": 6350, "dynamics_loss_avg": 0.03209642563015223}
+{"step": 6350, "action_loss_avg": 0.006329851248301566}
+{"step": 6360, "dynamics_loss_avg": 0.03792449962347746}
+{"step": 6360, "action_loss_avg": 0.008360018162056804}
+{"step": 6370, "dynamics_loss_avg": 0.04674376491457224}
+{"step": 6370, "action_loss_avg": 0.010009511024691164}
+{"step": 6380, "dynamics_loss_avg": 0.037451432645320894}
+{"step": 6380, "action_loss_avg": 0.008785898226778954}
+{"step": 6390, "dynamics_loss_avg": 0.03590495903044939}
+{"step": 6390, "action_loss_avg": 0.00845004036091268}
+{"step": 6400, "loss": 0.045, "learning_rate": 9.994650040323704e-05}
+{"step": 6400, "dynamics_loss_avg": 0.03699026210233569}
+{"step": 6400, "action_loss_avg": 0.008009397413115949}
+{"step": 6410, "dynamics_loss_avg": 0.04592387927696109}
+{"step": 6410, "action_loss_avg": 0.010829492378979922}
+{"step": 6420, "dynamics_loss_avg": 0.03375158850103617}
+{"step": 6420, "action_loss_avg": 0.007369643473066389}
+{"step": 6430, "dynamics_loss_avg": 0.03709773705340922}
+{"step": 6430, "action_loss_avg": 0.010282940394245089}
+{"step": 6440, "dynamics_loss_avg": 0.04396823514252901}
+{"step": 6440, "action_loss_avg": 0.011848906800150872}
+{"step": 6450, "loss": 0.0435, "learning_rate": 9.994260867988658e-05}
+{"step": 6450, "dynamics_loss_avg": 0.03403318468481302}
+{"step": 6450, "action_loss_avg": 0.006957390112802386}
+{"step": 6460, "dynamics_loss_avg": 0.03864329867064953}
+{"step": 6460, "action_loss_avg": 0.01160327682737261}
+{"step": 6470, "dynamics_loss_avg": 0.032444890774786475}
+{"step": 6470, "action_loss_avg": 0.006642678286880255}
+{"step": 6480, "dynamics_loss_avg": 0.04229014785960317}
+{"step": 6480, "action_loss_avg": 0.009859804972074926}
+{"step": 6490, "dynamics_loss_avg": 0.037810597522184256}
+{"step": 6490, "action_loss_avg": 0.011444403545465321}
+{"step": 6500, "loss": 0.043, "learning_rate": 9.993858041535104e-05}
+{"step": 6500, "dynamics_loss_avg": 0.03307959018275142}
+{"step": 6500, "action_loss_avg": 0.010455558728426694}
+{"step": 6510, "dynamics_loss_avg": 0.03596498472616076}
+{"step": 6510, "action_loss_avg": 0.009357978124171495}
+{"step": 6520, "dynamics_loss_avg": 0.03389511192217469}
+{"step": 6520, "action_loss_avg": 0.006675618677400052}
+{"step": 6530, "dynamics_loss_avg": 0.03133180420845747}
+{"step": 6530, "action_loss_avg": 0.007784721138887107}
+{"step": 6540, "dynamics_loss_avg": 0.03070654682815075}
+{"step": 6540, "action_loss_avg": 0.005654427455738187}
+{"step": 6550, "loss": 0.042, "learning_rate": 9.993441562064354e-05}
+{"step": 6550, "dynamics_loss_avg": 0.04531122464686632}
+{"step": 6550, "action_loss_avg": 0.010571081773377955}
+{"step": 6560, "dynamics_loss_avg": 0.03669419512152672}
+{"step": 6560, "action_loss_avg": 0.009768302598968149}
+{"step": 6570, "dynamics_loss_avg": 0.055364372581243514}
+{"step": 6570, "action_loss_avg": 0.01080425176769495}
+{"step": 6580, "dynamics_loss_avg": 0.03184650894254446}
+{"step": 6580, "action_loss_avg": 0.007470513205043971}
+{"step": 6590, "dynamics_loss_avg": 0.0386008670553565}
+{"step": 6590, "action_loss_avg": 0.008924052794463932}
+{"step": 6600, "loss": 0.0473, "learning_rate": 9.993011430715047e-05}
+{"step": 6600, "dynamics_loss_avg": 0.03107635546475649}
+{"step": 6600, "action_loss_avg": 0.006985014281235635}
+{"step": 6610, "dynamics_loss_avg": 0.03317762054502964}
+{"step": 6610, "action_loss_avg": 0.006591058359481395}
+{"step": 6620, "dynamics_loss_avg": 0.04210204835981131}
+{"step": 6620, "action_loss_avg": 0.011562904552556574}
+{"step": 6630, "dynamics_loss_avg": 0.030877893231809138}
+{"step": 6630, "action_loss_avg": 0.007473013736307621}
+{"step": 6640, "dynamics_loss_avg": 0.03552483366802335}
+{"step": 6640, "action_loss_avg": 0.008723970269784331}
+{"step": 6650, "loss": 0.0414, "learning_rate": 9.992567648663147e-05}
+{"step": 6650, "dynamics_loss_avg": 0.04016697201877832}
+{"step": 6650, "action_loss_avg": 0.008392747025936842}
+{"step": 6660, "dynamics_loss_avg": 0.04074012488126755}
+{"step": 6660, "action_loss_avg": 0.00983977442374453}
+{"step": 6670, "dynamics_loss_avg": 0.042003974318504333}
+{"step": 6670, "action_loss_avg": 0.012431339547038078}
+{"step": 6680, "dynamics_loss_avg": 0.036489838175475596}
+{"step": 6680, "action_loss_avg": 0.006888557993806899}
+{"step": 6690, "dynamics_loss_avg": 0.038242340087890625}
+{"step": 6690, "action_loss_avg": 0.009899030672386289}
+{"step": 6700, "loss": 0.0446, "learning_rate": 9.992110217121936e-05}
+{"step": 6700, "dynamics_loss_avg": 0.04639312848448753}
+{"step": 6700, "action_loss_avg": 0.010227856785058975}
+{"step": 6710, "dynamics_loss_avg": 0.03829111009836197}
+{"step": 6710, "action_loss_avg": 0.007863302750047296}
+{"step": 6720, "dynamics_loss_avg": 0.04036466893739998}
+{"step": 6720, "action_loss_avg": 0.00715523324906826}
+{"step": 6730, "dynamics_loss_avg": 0.027441130205988883}
+{"step": 6730, "action_loss_avg": 0.0072260163724422455}
+{"step": 6740, "dynamics_loss_avg": 0.0325434735044837}
+{"step": 6740, "action_loss_avg": 0.007593327830545604}
+{"step": 6750, "loss": 0.0402, "learning_rate": 9.991639137342015e-05}
+{"step": 6750, "dynamics_loss_avg": 0.023809529095888137}
+{"step": 6750, "action_loss_avg": 0.005090093589387834}
+{"step": 6760, "dynamics_loss_avg": 0.03403814509510994}
+{"step": 6760, "action_loss_avg": 0.007563252642285079}
+{"step": 6770, "dynamics_loss_avg": 0.03666308335959911}
+{"step": 6770, "action_loss_avg": 0.010199391143396496}
+{"step": 6780, "dynamics_loss_avg": 0.03477196814492345}
+{"step": 6780, "action_loss_avg": 0.006562222074717283}
+{"step": 6790, "dynamics_loss_avg": 0.04232061961665749}
+{"step": 6790, "action_loss_avg": 0.009657312359195203}
+{"step": 6800, "loss": 0.041, "learning_rate": 9.991154410611296e-05}
+{"step": 6800, "dynamics_loss_avg": 0.03636720180511475}
+{"step": 6800, "action_loss_avg": 0.007102297456003726}
+{"step": 6810, "dynamics_loss_avg": 0.02846612697467208}
+{"step": 6810, "action_loss_avg": 0.006037987838499248}
+{"step": 6820, "dynamics_loss_avg": 0.037650673370808366}
+{"step": 6820, "action_loss_avg": 0.007379241846501827}
+{"step": 6830, "dynamics_loss_avg": 0.02615797258913517}
+{"step": 6830, "action_loss_avg": 0.005514882225543261}
+{"step": 6840, "dynamics_loss_avg": 0.03107052147388458}
+{"step": 6840, "action_loss_avg": 0.006773494312074036}
+{"step": 6850, "loss": 0.0386, "learning_rate": 9.990656038255006e-05}
+{"step": 6850, "dynamics_loss_avg": 0.04078778447583318}
+{"step": 6850, "action_loss_avg": 0.010331665654666722}
+{"step": 6860, "dynamics_loss_avg": 0.03833623146638274}
+{"step": 6860, "action_loss_avg": 0.010212162788957358}
+{"step": 6870, "dynamics_loss_avg": 0.033477078191936016}
+{"step": 6870, "action_loss_avg": 0.008752612164244056}
+{"step": 6880, "dynamics_loss_avg": 0.022828527633100747}
+{"step": 6880, "action_loss_avg": 0.0047380679869093}
+{"step": 6890, "dynamics_loss_avg": 0.03359432872384786}
+{"step": 6890, "action_loss_avg": 0.006489511439576745}
+{"step": 6900, "loss": 0.0415, "learning_rate": 9.990144021635677e-05}
+{"step": 6900, "dynamics_loss_avg": 0.03738134652376175}
+{"step": 6900, "action_loss_avg": 0.008003445295616984}
+{"step": 6910, "dynamics_loss_avg": 0.03295444990508258}
+{"step": 6910, "action_loss_avg": 0.00795175191015005}
+{"step": 6920, "dynamics_loss_avg": 0.03357906863093376}
+{"step": 6920, "action_loss_avg": 0.0072968028485775}
+{"step": 6930, "dynamics_loss_avg": 0.031837865989655253}
+{"step": 6930, "action_loss_avg": 0.007281278120353818}
+{"step": 6940, "dynamics_loss_avg": 0.026920161303132774}
+{"step": 6940, "action_loss_avg": 0.007132628653198481}
+{"step": 6950, "loss": 0.0432, "learning_rate": 9.989618362153139e-05}
+{"step": 6950, "dynamics_loss_avg": 0.034479746129363775}
+{"step": 6950, "action_loss_avg": 0.008003152278251945}
+{"step": 6960, "dynamics_loss_avg": 0.03451833724975586}
+{"step": 6960, "action_loss_avg": 0.01101858140900731}
+{"step": 6970, "dynamics_loss_avg": 0.04198173377662897}
+{"step": 6970, "action_loss_avg": 0.013405535370111465}
+{"step": 6980, "dynamics_loss_avg": 0.03266797794494778}
+{"step": 6980, "action_loss_avg": 0.006944658650900238}
+{"step": 6990, "dynamics_loss_avg": 0.034320294950157405}
+{"step": 6990, "action_loss_avg": 0.008579203765839339}
+{"step": 7000, "loss": 0.044, "learning_rate": 9.989079061244528e-05}
+{"step": 7000, "dynamics_loss_avg": 0.03462942903861403}
+{"step": 7000, "action_loss_avg": 0.007021385454572737}
+{"step": 7010, "dynamics_loss_avg": 0.04276801105588675}
+{"step": 7010, "action_loss_avg": 0.009431641665287316}
+{"step": 7020, "dynamics_loss_avg": 0.04003324210643768}
+{"step": 7020, "action_loss_avg": 0.00907434280961752}
+{"step": 7030, "dynamics_loss_avg": 0.04239668175578117}
+{"step": 7030, "action_loss_avg": 0.009684487106278538}
+{"step": 7040, "dynamics_loss_avg": 0.035572487860918045}
+{"step": 7040, "action_loss_avg": 0.009456258686259388}
+{"step": 7050, "loss": 0.0458, "learning_rate": 9.98852612038427e-05}
+{"step": 7050, "dynamics_loss_avg": 0.036910297628492114}
+{"step": 7050, "action_loss_avg": 0.011902846395969391}
+{"step": 7060, "dynamics_loss_avg": 0.038650949764996764}
+{"step": 7060, "action_loss_avg": 0.01088798432610929}
+{"step": 7070, "dynamics_loss_avg": 0.035132867842912675}
+{"step": 7070, "action_loss_avg": 0.007466869754716754}
+{"step": 7080, "dynamics_loss_avg": 0.03253346821293235}
+{"step": 7080, "action_loss_avg": 0.008399997744709254}
+{"step": 7090, "dynamics_loss_avg": 0.031610500812530515}
+{"step": 7090, "action_loss_avg": 0.008185631688684225}
+{"step": 7100, "loss": 0.0432, "learning_rate": 9.987959541084087e-05}
+{"step": 7100, "dynamics_loss_avg": 0.02821101164445281}
+{"step": 7100, "action_loss_avg": 0.006652118754573166}
+{"step": 7110, "dynamics_loss_avg": 0.038876757957041264}
+{"step": 7110, "action_loss_avg": 0.009138666884973645}
+{"step": 7120, "dynamics_loss_avg": 0.03455213345587253}
+{"step": 7120, "action_loss_avg": 0.009066463075578212}
+{"step": 7130, "dynamics_loss_avg": 0.030831674952059983}
+{"step": 7130, "action_loss_avg": 0.0070088128326460716}
+{"step": 7140, "dynamics_loss_avg": 0.0413666432723403}
+{"step": 7140, "action_loss_avg": 0.01005902315955609}
+{"step": 7150, "loss": 0.0398, "learning_rate": 9.987379324892982e-05}
+{"step": 7150, "dynamics_loss_avg": 0.035306116193532945}
+{"step": 7150, "action_loss_avg": 0.007896980969235301}
+{"step": 7160, "dynamics_loss_avg": 0.030338710360229015}
+{"step": 7160, "action_loss_avg": 0.007901477022096514}
+{"step": 7170, "dynamics_loss_avg": 0.04105395758524537}
+{"step": 7170, "action_loss_avg": 0.011616201023571193}
+{"step": 7180, "dynamics_loss_avg": 0.029399740044027567}
+{"step": 7180, "action_loss_avg": 0.006739597884006798}
+{"step": 7190, "dynamics_loss_avg": 0.03384399376809597}
+{"step": 7190, "action_loss_avg": 0.008221774781122803}
+{"step": 7200, "loss": 0.0462, "learning_rate": 9.986785473397245e-05}
+{"step": 7200, "dynamics_loss_avg": 0.04588471483439207}
+{"step": 7200, "action_loss_avg": 0.011687436979264021}
+{"step": 7210, "dynamics_loss_avg": 0.03878487199544907}
+{"step": 7210, "action_loss_avg": 0.012111680442467332}
+{"step": 7220, "dynamics_loss_avg": 0.03873926009982824}
+{"step": 7220, "action_loss_avg": 0.00991043853573501}
+{"step": 7230, "dynamics_loss_avg": 0.033040885720402}
+{"step": 7230, "action_loss_avg": 0.00934079228900373}
+{"step": 7240, "dynamics_loss_avg": 0.03255293322727084}
+{"step": 7240, "action_loss_avg": 0.007841694611124694}
+{"step": 7250, "loss": 0.041, "learning_rate": 9.986177988220444e-05}
+{"step": 7250, "dynamics_loss_avg": 0.038002921268343925}
+{"step": 7250, "action_loss_avg": 0.009818078111857175}
+{"step": 7260, "dynamics_loss_avg": 0.04961707005277276}
+{"step": 7260, "action_loss_avg": 0.015583458147011698}
+{"step": 7270, "dynamics_loss_avg": 0.03306460827589035}
+{"step": 7270, "action_loss_avg": 0.007933155260980129}
+{"step": 7280, "dynamics_loss_avg": 0.03058987855911255}
+{"step": 7280, "action_loss_avg": 0.004991256608627736}
+{"step": 7290, "dynamics_loss_avg": 0.03485062420368194}
+{"step": 7290, "action_loss_avg": 0.008641180861741305}
+{"step": 7300, "loss": 0.0434, "learning_rate": 9.98555687102342e-05}
+{"step": 7300, "dynamics_loss_avg": 0.0385696510784328}
+{"step": 7300, "action_loss_avg": 0.009448103874456137}
+{"step": 7310, "dynamics_loss_avg": 0.02935124272480607}
+{"step": 7310, "action_loss_avg": 0.0052024220349267125}
+{"step": 7320, "dynamics_loss_avg": 0.034828289039433004}
+{"step": 7320, "action_loss_avg": 0.006556417047977448}
+{"step": 7330, "dynamics_loss_avg": 0.03616399187594652}
+{"step": 7330, "action_loss_avg": 0.010648569418117404}
+{"step": 7340, "dynamics_loss_avg": 0.033379679545760155}
+{"step": 7340, "action_loss_avg": 0.007729392359033227}
+{"step": 7350, "loss": 0.0402, "learning_rate": 9.984922123504286e-05}
+{"step": 7350, "dynamics_loss_avg": 0.04235990326851606}
+{"step": 7350, "action_loss_avg": 0.010870214505121111}
+{"step": 7360, "dynamics_loss_avg": 0.03495975839905441}
+{"step": 7360, "action_loss_avg": 0.007247971917968244}
+{"step": 7370, "dynamics_loss_avg": 0.03979915995150805}
+{"step": 7370, "action_loss_avg": 0.010259050340391696}
+{"step": 7380, "dynamics_loss_avg": 0.03533716546371579}
+{"step": 7380, "action_loss_avg": 0.00844348631799221}
+{"step": 7390, "dynamics_loss_avg": 0.030649512354284526}
+{"step": 7390, "action_loss_avg": 0.007670271466486156}
+{"step": 7400, "loss": 0.0412, "learning_rate": 9.984273747398411e-05}
+{"step": 7400, "dynamics_loss_avg": 0.029340942949056627}
+{"step": 7400, "action_loss_avg": 0.006588148919399827}
+{"step": 7410, "dynamics_loss_avg": 0.03210050854831934}
+{"step": 7410, "action_loss_avg": 0.00800349903292954}
+{"step": 7420, "dynamics_loss_avg": 0.034287319611757995}
+{"step": 7420, "action_loss_avg": 0.007434854633174837}
+{"step": 7430, "dynamics_loss_avg": 0.035567670688033105}
+{"step": 7430, "action_loss_avg": 0.009658811776898802}
+{"step": 7440, "dynamics_loss_avg": 0.029348219092935324}
+{"step": 7440, "action_loss_avg": 0.007145209144800902}
+{"step": 7450, "loss": 0.0392, "learning_rate": 9.983611744478438e-05}
+{"step": 7450, "dynamics_loss_avg": 0.029391685966402292}
+{"step": 7450, "action_loss_avg": 0.006048403843306005}
+{"step": 7460, "dynamics_loss_avg": 0.04021466095000505}
+{"step": 7460, "action_loss_avg": 0.008437657495960593}
+{"step": 7470, "dynamics_loss_avg": 0.04524140991270542}
+{"step": 7470, "action_loss_avg": 0.012373217800632118}
+{"step": 7480, "dynamics_loss_avg": 0.04411490224301815}
+{"step": 7480, "action_loss_avg": 0.008626763487700372}
+{"step": 7490, "dynamics_loss_avg": 0.05113190282136202}
+{"step": 7490, "action_loss_avg": 0.011340358899906278}
+{"step": 7500, "loss": 0.0472, "learning_rate": 9.982936116554254e-05}
+{"step": 7500, "dynamics_loss_avg": 0.031070013996213675}
+{"step": 7500, "action_loss_avg": 0.007190209324471652}
+{"step": 7510, "dynamics_loss_avg": 0.044863862171769145}
+{"step": 7510, "action_loss_avg": 0.011026988551020623}
+{"step": 7520, "dynamics_loss_avg": 0.03443545363843441}
+{"step": 7520, "action_loss_avg": 0.007414566376246512}
+{"step": 7530, "dynamics_loss_avg": 0.0418500654399395}
+{"step": 7530, "action_loss_avg": 0.010839615948498249}
+{"step": 7540, "dynamics_loss_avg": 0.04337476249784231}
+{"step": 7540, "action_loss_avg": 0.00995067129842937}
+{"step": 7550, "loss": 0.0475, "learning_rate": 9.982246865472998e-05}
+{"step": 7550, "dynamics_loss_avg": 0.04330262346193194}
+{"step": 7550, "action_loss_avg": 0.009304895246168598}
+{"step": 7560, "dynamics_loss_avg": 0.03614207934588194}
+{"step": 7560, "action_loss_avg": 0.00956837038975209}
+{"step": 7570, "dynamics_loss_avg": 0.03871225155889988}
+{"step": 7570, "action_loss_avg": 0.00986528831999749}
+{"step": 7580, "dynamics_loss_avg": 0.03384786117821932}
+{"step": 7580, "action_loss_avg": 0.007551721658091992}
+{"step": 7590, "dynamics_loss_avg": 0.03684083297848702}
+{"step": 7590, "action_loss_avg": 0.007055661221966147}
+{"step": 7600, "loss": 0.0429, "learning_rate": 9.98154399311906e-05}
+{"step": 7600, "dynamics_loss_avg": 0.029344790242612363}
+{"step": 7600, "action_loss_avg": 0.0057863306254148485}
+{"step": 7610, "dynamics_loss_avg": 0.044411569088697436}
+{"step": 7610, "action_loss_avg": 0.012193154031410813}
+{"step": 7620, "dynamics_loss_avg": 0.0363921076990664}
+{"step": 7620, "action_loss_avg": 0.006191798055078834}
+{"step": 7630, "dynamics_loss_avg": 0.038854926079511645}
+{"step": 7630, "action_loss_avg": 0.009840148082002998}
+{"step": 7640, "dynamics_loss_avg": 0.035237247869372365}
+{"step": 7640, "action_loss_avg": 0.007714218297041953}
+{"step": 7650, "loss": 0.0464, "learning_rate": 9.980827501414064e-05}
+{"step": 7650, "dynamics_loss_avg": 0.04260251969099045}
+{"step": 7650, "action_loss_avg": 0.009803187858778983}
+{"step": 7660, "dynamics_loss_avg": 0.03914688210934401}
+{"step": 7660, "action_loss_avg": 0.009969811607152223}
+{"step": 7670, "dynamics_loss_avg": 0.038398079574108124}
+{"step": 7670, "action_loss_avg": 0.010249017318710685}
+{"step": 7680, "dynamics_loss_avg": 0.03670622985810042}
+{"step": 7680, "action_loss_avg": 0.00860305952373892}
+{"step": 7690, "dynamics_loss_avg": 0.04467574367299676}
+{"step": 7690, "action_loss_avg": 0.009068416897207499}
+{"step": 7700, "loss": 0.0436, "learning_rate": 9.980097392316872e-05}
+{"step": 7700, "dynamics_loss_avg": 0.031164181977510454}
+{"step": 7700, "action_loss_avg": 0.007341078971512616}
+{"step": 7710, "dynamics_loss_avg": 0.03882020181044936}
+{"step": 7710, "action_loss_avg": 0.008135526324622333}
+{"step": 7720, "dynamics_loss_avg": 0.03679395960643887}
+{"step": 7720, "action_loss_avg": 0.007259033783338964}
+{"step": 7730, "dynamics_loss_avg": 0.033912020921707156}
+{"step": 7730, "action_loss_avg": 0.0064299200428649785}
+{"step": 7740, "dynamics_loss_avg": 0.0394044179469347}
+{"step": 7740, "action_loss_avg": 0.008513847133144736}
+{"step": 7750, "loss": 0.0429, "learning_rate": 9.979353667823574e-05}
+{"step": 7750, "dynamics_loss_avg": 0.03519333191215992}
+{"step": 7750, "action_loss_avg": 0.009475872246548533}
+{"step": 7760, "dynamics_loss_avg": 0.03375862687826157}
+{"step": 7760, "action_loss_avg": 0.009761387063190342}
+{"step": 7770, "dynamics_loss_avg": 0.03693261183798313}
+{"step": 7770, "action_loss_avg": 0.007668666599784046}
+{"step": 7780, "dynamics_loss_avg": 0.038969387765973806}
+{"step": 7780, "action_loss_avg": 0.009528947924263776}
+{"step": 7790, "dynamics_loss_avg": 0.03552203038707376}
+{"step": 7790, "action_loss_avg": 0.007621741364710033}
+{"step": 7800, "loss": 0.0449, "learning_rate": 9.978596329967484e-05}
+{"step": 7800, "dynamics_loss_avg": 0.03792349239811301}
+{"step": 7800, "action_loss_avg": 0.008828977239318192}
+{"step": 7810, "dynamics_loss_avg": 0.041335703991353515}
+{"step": 7810, "action_loss_avg": 0.00792427125852555}
+{"step": 7820, "dynamics_loss_avg": 0.02872179914265871}
+{"step": 7820, "action_loss_avg": 0.006459331058431416}
+{"step": 7830, "dynamics_loss_avg": 0.04023175798356533}
+{"step": 7830, "action_loss_avg": 0.009135837142821401}
+{"step": 7840, "dynamics_loss_avg": 0.03610623376443982}
+{"step": 7840, "action_loss_avg": 0.006482806371059269}
+{"step": 7850, "loss": 0.0431, "learning_rate": 9.977825380819135e-05}
+{"step": 7850, "dynamics_loss_avg": 0.04225571230053902}
+{"step": 7850, "action_loss_avg": 0.007076780777424574}
+{"step": 7860, "dynamics_loss_avg": 0.04466015100479126}
+{"step": 7860, "action_loss_avg": 0.009972347225993872}
+{"step": 7870, "dynamics_loss_avg": 0.025760275404900314}
+{"step": 7870, "action_loss_avg": 0.0071411473385524}
+{"step": 7880, "dynamics_loss_avg": 0.035588428191840646}
+{"step": 7880, "action_loss_avg": 0.007426881324499845}
+{"step": 7890, "dynamics_loss_avg": 0.04267270509153605}
+{"step": 7890, "action_loss_avg": 0.007986722490750253}
+{"step": 7900, "loss": 0.0405, "learning_rate": 9.977040822486273e-05}
+{"step": 7900, "dynamics_loss_avg": 0.03476479034870863}
+{"step": 7900, "action_loss_avg": 0.006393275689333677}
+{"step": 7910, "dynamics_loss_avg": 0.0335262936539948}
+{"step": 7910, "action_loss_avg": 0.007161202584393322}
+{"step": 7920, "dynamics_loss_avg": 0.0373935466632247}
+{"step": 7920, "action_loss_avg": 0.010091857030056417}
+{"step": 7930, "dynamics_loss_avg": 0.04091170784085989}
+{"step": 7930, "action_loss_avg": 0.009451036853715778}
+{"step": 7940, "dynamics_loss_avg": 0.027885893592610955}
+{"step": 7940, "action_loss_avg": 0.007333937741350383}
+{"step": 7950, "loss": 0.0417, "learning_rate": 9.97624265711385e-05}
+{"step": 7950, "dynamics_loss_avg": 0.0380086318589747}
+{"step": 7950, "action_loss_avg": 0.007871459377929569}
+{"step": 7960, "dynamics_loss_avg": 0.04187715444713831}
+{"step": 7960, "action_loss_avg": 0.008748620375990867}
+{"step": 7970, "dynamics_loss_avg": 0.040770767349749805}
+{"step": 7970, "action_loss_avg": 0.009522264217957854}
+{"step": 7980, "dynamics_loss_avg": 0.04538009315729141}
+{"step": 7980, "action_loss_avg": 0.009414083720184863}
+{"step": 7990, "dynamics_loss_avg": 0.03922876464203}
+{"step": 7990, "action_loss_avg": 0.006864206166937947}
+{"step": 8000, "loss": 0.0461, "learning_rate": 9.97543088688402e-05}
+{"step": 8000, "dynamics_loss_avg": 0.04331239853054285}
+{"step": 8000, "action_loss_avg": 0.00876117548905313}
+{"step": 8010, "dynamics_loss_avg": 0.04349393788725138}
+{"step": 8010, "action_loss_avg": 0.008817099733278155}
+{"step": 8020, "dynamics_loss_avg": 0.030950752552598715}
+{"step": 8020, "action_loss_avg": 0.005849142093211412}
+{"step": 8030, "dynamics_loss_avg": 0.029698236845433712}
+{"step": 8030, "action_loss_avg": 0.006774674030020833}
+{"step": 8040, "dynamics_loss_avg": 0.037257037870585916}
+{"step": 8040, "action_loss_avg": 0.007191964890807867}
+{"step": 8050, "loss": 0.0413, "learning_rate": 9.974605514016131e-05}
+{"step": 8050, "dynamics_loss_avg": 0.03787142653018236}
+{"step": 8050, "action_loss_avg": 0.007113577052950859}
+{"step": 8060, "dynamics_loss_avg": 0.045065717212855814}
+{"step": 8060, "action_loss_avg": 0.008426014380529524}
+{"step": 8070, "dynamics_loss_avg": 0.037756177969276904}
+{"step": 8070, "action_loss_avg": 0.006195540516637265}
+{"step": 8080, "dynamics_loss_avg": 0.037444699183106424}
+{"step": 8080, "action_loss_avg": 0.006184105877764523}
+{"step": 8090, "dynamics_loss_avg": 0.03225564807653427}
+{"step": 8090, "action_loss_avg": 0.006917709996923804}
+{"step": 8100, "loss": 0.0408, "learning_rate": 9.973766540766722e-05}
+{"step": 8100, "dynamics_loss_avg": 0.030294481851160526}
+{"step": 8100, "action_loss_avg": 0.006790798867587}
+{"step": 8110, "dynamics_loss_avg": 0.04058500975370407}
+{"step": 8110, "action_loss_avg": 0.008766607521101833}
+{"step": 8120, "dynamics_loss_avg": 0.031305951066315174}
+{"step": 8120, "action_loss_avg": 0.006176299229264259}
+{"step": 8130, "dynamics_loss_avg": 0.04333866592496634}
+{"step": 8130, "action_loss_avg": 0.007911331625655294}
+{"step": 8140, "dynamics_loss_avg": 0.03840992152690888}
+{"step": 8140, "action_loss_avg": 0.007396729825995862}
+{"step": 8150, "loss": 0.0442, "learning_rate": 9.972913969429513e-05}
+{"step": 8150, "dynamics_loss_avg": 0.046939882822334765}
+{"step": 8150, "action_loss_avg": 0.010214446298778056}
+{"step": 8160, "dynamics_loss_avg": 0.03095517398323864}
+{"step": 8160, "action_loss_avg": 0.006428105005761608}
+{"step": 8170, "dynamics_loss_avg": 0.038339142128825186}
+{"step": 8170, "action_loss_avg": 0.008292854018509387}
+{"step": 8180, "dynamics_loss_avg": 0.030031876917928458}
+{"step": 8180, "action_loss_avg": 0.005381673993542791}
+{"step": 8190, "dynamics_loss_avg": 0.03952675517648459}
+{"step": 8190, "action_loss_avg": 0.007418990228325128}
+{"step": 8200, "loss": 0.0414, "learning_rate": 9.972047802335403e-05}
+{"step": 8200, "dynamics_loss_avg": 0.03536789640784264}
+{"step": 8200, "action_loss_avg": 0.007157043321058154}
+{"step": 8210, "dynamics_loss_avg": 0.034123478643596175}
+{"step": 8210, "action_loss_avg": 0.006520315608941019}
+{"step": 8220, "dynamics_loss_avg": 0.03675132477656007}
+{"step": 8220, "action_loss_avg": 0.006733466242440045}
+{"step": 8230, "dynamics_loss_avg": 0.041782967373728754}
+{"step": 8230, "action_loss_avg": 0.007882275152951479}
+{"step": 8240, "dynamics_loss_avg": 0.03135445937514305}
+{"step": 8240, "action_loss_avg": 0.005095204175449908}
+{"step": 8250, "loss": 0.039, "learning_rate": 9.971168041852456e-05}
+{"step": 8250, "dynamics_loss_avg": 0.03191796150058508}
+{"step": 8250, "action_loss_avg": 0.006302715488709509}
+{"step": 8260, "dynamics_loss_avg": 0.028853837330825628}
+{"step": 8260, "action_loss_avg": 0.005704551935195923}
+{"step": 8270, "dynamics_loss_avg": 0.03611369989812374}
+{"step": 8270, "action_loss_avg": 0.006483198143541813}
+{"step": 8280, "dynamics_loss_avg": 0.03831959487870336}
+{"step": 8280, "action_loss_avg": 0.008236100268550216}
+{"step": 8290, "dynamics_loss_avg": 0.04043169850483537}
+{"step": 8290, "action_loss_avg": 0.007528731971979142}
+{"step": 8300, "loss": 0.0424, "learning_rate": 9.970274690385909e-05}
+{"step": 8300, "dynamics_loss_avg": 0.04146707691252231}
+{"step": 8300, "action_loss_avg": 0.007775352313183248}
+{"step": 8310, "dynamics_loss_avg": 0.031622938252985476}
+{"step": 8310, "action_loss_avg": 0.005672216031234712}
+{"step": 8320, "dynamics_loss_avg": 0.034365221951156856}
+{"step": 8320, "action_loss_avg": 0.006515338714234531}
+{"step": 8330, "dynamics_loss_avg": 0.03522096863016486}
+{"step": 8330, "action_loss_avg": 0.007134346850216388}
+{"step": 8340, "dynamics_loss_avg": 0.04072707928717136}
+{"step": 8340, "action_loss_avg": 0.006983141042292118}
+{"step": 8350, "loss": 0.039, "learning_rate": 9.969367750378147e-05}
+{"step": 8350, "dynamics_loss_avg": 0.03404129166156054}
+{"step": 8350, "action_loss_avg": 0.005775142461061478}
+{"step": 8360, "dynamics_loss_avg": 0.028009750228375197}
+{"step": 8360, "action_loss_avg": 0.004344269027933478}
+{"step": 8370, "dynamics_loss_avg": 0.0364663939923048}
+{"step": 8370, "action_loss_avg": 0.007447768514975905}
+{"step": 8380, "dynamics_loss_avg": 0.04135040361434221}
+{"step": 8380, "action_loss_avg": 0.006458924198523164}
+{"step": 8390, "dynamics_loss_avg": 0.03644289001822472}
+{"step": 8390, "action_loss_avg": 0.006537317798938602}
+{"step": 8400, "loss": 0.0393, "learning_rate": 9.96844722430871e-05}
+{"step": 8400, "dynamics_loss_avg": 0.03552326411008835}
+{"step": 8400, "action_loss_avg": 0.004415850166697055}
+{"step": 8410, "dynamics_loss_avg": 0.040763736516237256}
+{"step": 8410, "action_loss_avg": 0.009266106807626785}
+{"step": 8420, "dynamics_loss_avg": 0.03789717275649309}
+{"step": 8420, "action_loss_avg": 0.005870132939890027}
+{"step": 8430, "dynamics_loss_avg": 0.03853419693186879}
+{"step": 8430, "action_loss_avg": 0.008416372770443558}
+{"step": 8440, "dynamics_loss_avg": 0.03512506270781159}
+{"step": 8440, "action_loss_avg": 0.005495337879983709}
+{"step": 8450, "loss": 0.0414, "learning_rate": 9.967513114694282e-05}
+{"step": 8450, "dynamics_loss_avg": 0.03128990475088358}
+{"step": 8450, "action_loss_avg": 0.005251471512019634}
+{"step": 8460, "dynamics_loss_avg": 0.041536118183284995}
+{"step": 8460, "action_loss_avg": 0.008399028424173593}
+{"step": 8470, "dynamics_loss_avg": 0.03470735773444176}
+{"step": 8470, "action_loss_avg": 0.007253909902647138}
+{"step": 8480, "dynamics_loss_avg": 0.03294649943709373}
+{"step": 8480, "action_loss_avg": 0.005789145908784122}
+{"step": 8490, "dynamics_loss_avg": 0.039289123564958575}
+{"step": 8490, "action_loss_avg": 0.006894447619561106}
+{"step": 8500, "loss": 0.0422, "learning_rate": 9.966565424088681e-05}
+{"step": 8500, "dynamics_loss_avg": 0.03748929481953382}
+{"step": 8500, "action_loss_avg": 0.0069119342602789405}
+{"step": 8510, "dynamics_loss_avg": 0.049367434810847044}
+{"step": 8510, "action_loss_avg": 0.009144482342526317}
+{"step": 8520, "dynamics_loss_avg": 0.036472005676478146}
+{"step": 8520, "action_loss_avg": 0.007193013536743819}
+{"step": 8530, "dynamics_loss_avg": 0.029733129031956195}
+{"step": 8530, "action_loss_avg": 0.004321381589397788}
+{"step": 8540, "dynamics_loss_avg": 0.03503987677395344}
+{"step": 8540, "action_loss_avg": 0.005265175946988165}
+{"step": 8550, "loss": 0.0426, "learning_rate": 9.96560415508286e-05}
+{"step": 8550, "dynamics_loss_avg": 0.05175977740436792}
+{"step": 8550, "action_loss_avg": 0.012132567120715976}
+{"step": 8560, "dynamics_loss_avg": 0.03502710051834583}
+{"step": 8560, "action_loss_avg": 0.009467399795539677}
+{"step": 8570, "dynamics_loss_avg": 0.022771252458915113}
+{"step": 8570, "action_loss_avg": 0.004639134922763332}
+{"step": 8580, "dynamics_loss_avg": 0.03336900658905506}
+{"step": 8580, "action_loss_avg": 0.007575613504741341}
+{"step": 8590, "dynamics_loss_avg": 0.04144542794674635}
+{"step": 8590, "action_loss_avg": 0.007088611810468137}
+{"step": 8600, "loss": 0.0378, "learning_rate": 9.96462931030489e-05}
+{"step": 8600, "dynamics_loss_avg": 0.026400241255760192}
+{"step": 8600, "action_loss_avg": 0.004397318430710584}
+{"step": 8610, "dynamics_loss_avg": 0.0303837975487113}
+{"step": 8610, "action_loss_avg": 0.005580470873974263}
+{"step": 8620, "dynamics_loss_avg": 0.03825507406145334}
+{"step": 8620, "action_loss_avg": 0.00728668044321239}
+{"step": 8630, "dynamics_loss_avg": 0.03429176975041628}
+{"step": 8630, "action_loss_avg": 0.006580552319064736}
+{"step": 8640, "dynamics_loss_avg": 0.033433913439512256}
+{"step": 8640, "action_loss_avg": 0.006450463458895684}
+{"step": 8650, "loss": 0.0395, "learning_rate": 9.963640892419958e-05}
+{"step": 8650, "dynamics_loss_avg": 0.037445122934877874}
+{"step": 8650, "action_loss_avg": 0.007613333780318499}
+{"step": 8660, "dynamics_loss_avg": 0.03775378633290529}
+{"step": 8660, "action_loss_avg": 0.005242493725381792}
+{"step": 8670, "dynamics_loss_avg": 0.03780832383781672}
+{"step": 8670, "action_loss_avg": 0.007664030825253576}
+{"step": 8680, "dynamics_loss_avg": 0.032943313103169204}
+{"step": 8680, "action_loss_avg": 0.006246495596133173}
+{"step": 8690, "dynamics_loss_avg": 0.03809488657861948}
+{"step": 8690, "action_loss_avg": 0.00813800625037402}
+{"step": 8700, "loss": 0.0417, "learning_rate": 9.962638904130363e-05}
+{"step": 8700, "dynamics_loss_avg": 0.04295050036162138}
+{"step": 8700, "action_loss_avg": 0.008480214234441518}
+{"step": 8710, "dynamics_loss_avg": 0.043346638418734075}
+{"step": 8710, "action_loss_avg": 0.009279442951083183}
+{"step": 8720, "dynamics_loss_avg": 0.03750587236136198}
+{"step": 8720, "action_loss_avg": 0.007061493443325162}
+{"step": 8730, "dynamics_loss_avg": 0.033814332261681554}
+{"step": 8730, "action_loss_avg": 0.007253747852519155}
+{"step": 8740, "dynamics_loss_avg": 0.04206268535926938}
+{"step": 8740, "action_loss_avg": 0.010738862247671932}
+{"step": 8750, "loss": 0.0434, "learning_rate": 9.961623348175501e-05}
+{"step": 8750, "dynamics_loss_avg": 0.03962323917075992}
+{"step": 8750, "action_loss_avg": 0.008866334264166654}
+{"step": 8760, "dynamics_loss_avg": 0.031287718657404186}
+{"step": 8760, "action_loss_avg": 0.006764282775111497}
+{"step": 8770, "dynamics_loss_avg": 0.030868349876254798}
+{"step": 8770, "action_loss_avg": 0.006633522175252438}
+{"step": 8780, "dynamics_loss_avg": 0.038696129061281684}
+{"step": 8780, "action_loss_avg": 0.00749573822831735}
+{"step": 8790, "dynamics_loss_avg": 0.0405389511026442}
+{"step": 8790, "action_loss_avg": 0.007843938516452908}
+{"step": 8800, "loss": 0.045, "learning_rate": 9.960594227331866e-05}
+{"step": 8800, "dynamics_loss_avg": 0.042039523273706435}
+{"step": 8800, "action_loss_avg": 0.010591788333840668}
+{"step": 8810, "dynamics_loss_avg": 0.038665051385760305}
+{"step": 8810, "action_loss_avg": 0.009730588295497}
+{"step": 8820, "dynamics_loss_avg": 0.037238113954663275}
+{"step": 8820, "action_loss_avg": 0.010369472252205015}
+{"step": 8830, "dynamics_loss_avg": 0.03801842899993062}
+{"step": 8830, "action_loss_avg": 0.008427213900722564}
+{"step": 8840, "dynamics_loss_avg": 0.037869201973080635}
+{"step": 8840, "action_loss_avg": 0.007599315431434661}
+{"step": 8850, "loss": 0.0417, "learning_rate": 9.959551544413033e-05}
+{"step": 8850, "dynamics_loss_avg": 0.02632987853139639}
+{"step": 8850, "action_loss_avg": 0.0045074628666043285}
+{"step": 8860, "dynamics_loss_avg": 0.030654170643538238}
+{"step": 8860, "action_loss_avg": 0.00631480785086751}
+{"step": 8870, "dynamics_loss_avg": 0.04285213807597756}
+{"step": 8870, "action_loss_avg": 0.00998801300302148}
+{"step": 8880, "dynamics_loss_avg": 0.036955620534718035}
+{"step": 8880, "action_loss_avg": 0.007443954632617533}
+{"step": 8890, "dynamics_loss_avg": 0.0289423119276762}
+{"step": 8890, "action_loss_avg": 0.006651821918785572}
+{"step": 8900, "loss": 0.0404, "learning_rate": 9.958495302269657e-05}
+{"step": 8900, "dynamics_loss_avg": 0.037711957655847075}
+{"step": 8900, "action_loss_avg": 0.00646512929815799}
+{"step": 8910, "dynamics_loss_avg": 0.038051421474665406}
+{"step": 8910, "action_loss_avg": 0.0077000686433166265}
+{"step": 8920, "dynamics_loss_avg": 0.03312800731509924}
+{"step": 8920, "action_loss_avg": 0.0066670035943388935}
+{"step": 8930, "dynamics_loss_avg": 0.030727563239634038}
+{"step": 8930, "action_loss_avg": 0.006452389666810632}
+{"step": 8940, "dynamics_loss_avg": 0.03934166561812162}
+{"step": 8940, "action_loss_avg": 0.006793041061609983}
+{"step": 8950, "loss": 0.0424, "learning_rate": 9.957425503789466e-05}
+{"step": 8950, "dynamics_loss_avg": 0.033105815201997756}
+{"step": 8950, "action_loss_avg": 0.006888968707062304}
+{"step": 8960, "dynamics_loss_avg": 0.029868469573557377}
+{"step": 8960, "action_loss_avg": 0.00604692492634058}
+{"step": 8970, "dynamics_loss_avg": 0.03515606066212058}
+{"step": 8970, "action_loss_avg": 0.00812302737031132}
+{"step": 8980, "dynamics_loss_avg": 0.035798951797187326}
+{"step": 8980, "action_loss_avg": 0.007528485916554928}
+{"step": 8990, "dynamics_loss_avg": 0.03202951634302735}
+{"step": 8990, "action_loss_avg": 0.004607508948538452}
+{"step": 9000, "loss": 0.0391, "learning_rate": 9.956342151897245e-05}
+{"step": 9000, "dynamics_loss_avg": 0.04024657690897584}
+{"step": 9000, "action_loss_avg": 0.006904306774958968}
+{"step": 9010, "dynamics_loss_avg": 0.04719003802165389}
+{"step": 9010, "action_loss_avg": 0.007177558145485818}
+{"step": 9020, "dynamics_loss_avg": 0.03903769683092832}
+{"step": 9020, "action_loss_avg": 0.008514457591809332}
+{"step": 9030, "dynamics_loss_avg": 0.03192514227703214}
+{"step": 9030, "action_loss_avg": 0.007776028837542981}
+{"step": 9040, "dynamics_loss_avg": 0.03209746442735195}
+{"step": 9040, "action_loss_avg": 0.006420780625194311}
+{"step": 9050, "loss": 0.0429, "learning_rate": 9.955245249554837e-05}
+{"step": 9050, "dynamics_loss_avg": 0.04046264179050922}
+{"step": 9050, "action_loss_avg": 0.0062006831751205025}
+{"step": 9060, "dynamics_loss_avg": 0.04649309907108545}
+{"step": 9060, "action_loss_avg": 0.01060778871178627}
+{"step": 9070, "dynamics_loss_avg": 0.04500721134245396}
+{"step": 9070, "action_loss_avg": 0.009685466717928647}
+{"step": 9080, "dynamics_loss_avg": 0.037023517116904256}
+{"step": 9080, "action_loss_avg": 0.0069782468257471916}
+{"step": 9090, "dynamics_loss_avg": 0.04882394503802061}
+{"step": 9090, "action_loss_avg": 0.009256653964985161}
+{"step": 9100, "loss": 0.0525, "learning_rate": 9.954134799761135e-05}
+{"step": 9100, "dynamics_loss_avg": 0.043178775254637}
+{"step": 9100, "action_loss_avg": 0.009510043170303106}
+{"step": 9110, "dynamics_loss_avg": 0.041563906520605085}
+{"step": 9110, "action_loss_avg": 0.008900982979685067}
+{"step": 9120, "dynamics_loss_avg": 0.023299265000969172}
+{"step": 9120, "action_loss_avg": 0.004252709820866585}
+{"step": 9130, "dynamics_loss_avg": 0.03438834324479103}
+{"step": 9130, "action_loss_avg": 0.006601145979948342}
+{"step": 9140, "dynamics_loss_avg": 0.026109398528933524}
+{"step": 9140, "action_loss_avg": 0.008133200538577513}
+{"step": 9150, "loss": 0.0341, "learning_rate": 9.95301080555206e-05}
+{"step": 9150, "dynamics_loss_avg": 0.025701825972646475}
+{"step": 9150, "action_loss_avg": 0.004593035951256752}
+{"step": 9160, "dynamics_loss_avg": 0.029866758733987808}
+{"step": 9160, "action_loss_avg": 0.005934475921094418}
+{"step": 9170, "dynamics_loss_avg": 0.03755838014185429}
+{"step": 9170, "action_loss_avg": 0.006400652462616563}
+{"step": 9180, "dynamics_loss_avg": 0.0411204089410603}
+{"step": 9180, "action_loss_avg": 0.009123411634936929}
+{"step": 9190, "dynamics_loss_avg": 0.051139548886567354}
+{"step": 9190, "action_loss_avg": 0.010498257901053876}
+{"step": 9200, "loss": 0.0432, "learning_rate": 9.951873270000576e-05}
+{"step": 9200, "dynamics_loss_avg": 0.03134685028344393}
+{"step": 9200, "action_loss_avg": 0.005904053314588964}
+{"step": 9210, "dynamics_loss_avg": 0.029095500241965055}
+{"step": 9210, "action_loss_avg": 0.006664043292403221}
+{"step": 9220, "dynamics_loss_avg": 0.030543951038271188}
+{"step": 9220, "action_loss_avg": 0.006148838240187615}
+{"step": 9230, "dynamics_loss_avg": 0.039648327976465225}
+{"step": 9230, "action_loss_avg": 0.007437727204523981}
+{"step": 9240, "dynamics_loss_avg": 0.038927932549268005}
+{"step": 9240, "action_loss_avg": 0.007709336769767106}
+{"step": 9250, "loss": 0.0374, "learning_rate": 9.950722196216658e-05}
+{"step": 9250, "dynamics_loss_avg": 0.026876673568040133}
+{"step": 9250, "action_loss_avg": 0.0055392120033502575}
+{"step": 9260, "dynamics_loss_avg": 0.02484835833311081}
+{"step": 9260, "action_loss_avg": 0.0071889088838361205}
+{"step": 9270, "dynamics_loss_avg": 0.055548632703721526}
+{"step": 9270, "action_loss_avg": 0.011698900791816413}
+{"step": 9280, "dynamics_loss_avg": 0.03841656651347876}
+{"step": 9280, "action_loss_avg": 0.008599953190423549}
+{"step": 9290, "dynamics_loss_avg": 0.047927196510136126}
+{"step": 9290, "action_loss_avg": 0.011302779614925384}
+{"step": 9300, "loss": 0.0457, "learning_rate": 9.949557587347298e-05}
+{"step": 9300, "dynamics_loss_avg": 0.034809700399637225}
+{"step": 9300, "action_loss_avg": 0.0048513242218177766}
+{"step": 9310, "dynamics_loss_avg": 0.051750529045239094}
+{"step": 9310, "action_loss_avg": 0.01329738338245079}
+{"step": 9320, "dynamics_loss_avg": 0.031107694283127783}
+{"step": 9320, "action_loss_avg": 0.006163925625151024}
+{"step": 9330, "dynamics_loss_avg": 0.027744921296834944}
+{"step": 9330, "action_loss_avg": 0.0073106478899717334}
+{"step": 9340, "dynamics_loss_avg": 0.03668122561648488}
+{"step": 9340, "action_loss_avg": 0.007236229965928942}
+{"step": 9350, "loss": 0.0424, "learning_rate": 9.948379446576493e-05}
+{"step": 9350, "dynamics_loss_avg": 0.03993573673069477}
+{"step": 9350, "action_loss_avg": 0.00701394968200475}
+{"step": 9360, "dynamics_loss_avg": 0.03987137023359537}
+{"step": 9360, "action_loss_avg": 0.006687492155469954}
+{"step": 9370, "dynamics_loss_avg": 0.038285964354872706}
+{"step": 9370, "action_loss_avg": 0.008072296972386539}
+{"step": 9380, "dynamics_loss_avg": 0.0391031326726079}
+{"step": 9380, "action_loss_avg": 0.008350019110366702}
+{"step": 9390, "dynamics_loss_avg": 0.03538866871967912}
+{"step": 9390, "action_loss_avg": 0.006175863440148532}
+{"step": 9400, "loss": 0.0427, "learning_rate": 9.947187777125233e-05}
+{"step": 9400, "dynamics_loss_avg": 0.04056557659059763}
+{"step": 9400, "action_loss_avg": 0.0061129430076107385}
+{"step": 9410, "dynamics_loss_avg": 0.045933152176439764}
+{"step": 9410, "action_loss_avg": 0.009319855668582021}
+{"step": 9420, "dynamics_loss_avg": 0.030212733149528503}
+{"step": 9420, "action_loss_avg": 0.005116094020195305}
+{"step": 9430, "dynamics_loss_avg": 0.03870224095880985}
+{"step": 9430, "action_loss_avg": 0.007611462520435453}
+{"step": 9440, "dynamics_loss_avg": 0.04252043105661869}
+{"step": 9440, "action_loss_avg": 0.008011583448387682}
+{"step": 9450, "loss": 0.0422, "learning_rate": 9.945982582251498e-05}
+{"step": 9450, "dynamics_loss_avg": 0.04623817186802626}
+{"step": 9450, "action_loss_avg": 0.0076372426934540275}
+{"step": 9460, "dynamics_loss_avg": 0.03554683802649379}
+{"step": 9460, "action_loss_avg": 0.00740282058250159}
+{"step": 9470, "dynamics_loss_avg": 0.0398795266635716}
+{"step": 9470, "action_loss_avg": 0.008277312712743878}
+{"step": 9480, "dynamics_loss_avg": 0.03249704274348915}
+{"step": 9480, "action_loss_avg": 0.005306995683349669}
+{"step": 9490, "dynamics_loss_avg": 0.03961111521348357}
+{"step": 9490, "action_loss_avg": 0.007247490109875798}
+{"step": 9500, "loss": 0.0405, "learning_rate": 9.944763865250248e-05}
+{"step": 9500, "dynamics_loss_avg": 0.030348243936896325}
+{"step": 9500, "action_loss_avg": 0.005627844762057066}
+{"step": 9510, "dynamics_loss_avg": 0.02506676549091935}
+{"step": 9510, "action_loss_avg": 0.004464815347455442}
+{"step": 9520, "dynamics_loss_avg": 0.032109071779996154}
+{"step": 9520, "action_loss_avg": 0.007085419073700905}
+{"step": 9530, "dynamics_loss_avg": 0.03831479689106345}
+{"step": 9530, "action_loss_avg": 0.007661952916532755}
+{"step": 9540, "dynamics_loss_avg": 0.031017352407798172}
+{"step": 9540, "action_loss_avg": 0.006324976403266192}
+{"step": 9550, "loss": 0.0364, "learning_rate": 9.943531629453403e-05}
+{"step": 9550, "dynamics_loss_avg": 0.026165534369647504}
+{"step": 9550, "action_loss_avg": 0.005134098761482164}
+{"step": 9560, "dynamics_loss_avg": 0.03897210480645299}
+{"step": 9560, "action_loss_avg": 0.009568964503705502}
+{"step": 9570, "dynamics_loss_avg": 0.04007441811263561}
+{"step": 9570, "action_loss_avg": 0.006607106211595238}
+{"step": 9580, "dynamics_loss_avg": 0.034582863375544545}
+{"step": 9580, "action_loss_avg": 0.00611046701669693}
+{"step": 9590, "dynamics_loss_avg": 0.030623587593436242}
+{"step": 9590, "action_loss_avg": 0.006731101759942249}
+{"step": 9600, "loss": 0.0412, "learning_rate": 9.942285878229853e-05}
+{"step": 9600, "dynamics_loss_avg": 0.038767090626060964}
+{"step": 9600, "action_loss_avg": 0.008237772330176085}
+{"step": 9610, "dynamics_loss_avg": 0.03410810828208923}
+{"step": 9610, "action_loss_avg": 0.006830002274364233}
+{"step": 9620, "dynamics_loss_avg": 0.028602068405598403}
+{"step": 9620, "action_loss_avg": 0.004669747012667358}
+{"step": 9630, "dynamics_loss_avg": 0.03573602512478828}
+{"step": 9630, "action_loss_avg": 0.0068547629285603765}
+{"step": 9640, "dynamics_loss_avg": 0.026850951742380856}
+{"step": 9640, "action_loss_avg": 0.00538556172978133}
+{"step": 9650, "loss": 0.0354, "learning_rate": 9.941026614985431e-05}
+{"step": 9650, "dynamics_loss_avg": 0.03173295566812158}
+{"step": 9650, "action_loss_avg": 0.004959093127399683}
+{"step": 9660, "dynamics_loss_avg": 0.041780820582062006}
+{"step": 9660, "action_loss_avg": 0.006877620960585773}
+{"step": 9670, "dynamics_loss_avg": 0.03626437652856111}
+{"step": 9670, "action_loss_avg": 0.006142198597081006}
+{"step": 9680, "dynamics_loss_avg": 0.03728379365056753}
+{"step": 9680, "action_loss_avg": 0.006434768554754555}
+{"step": 9690, "dynamics_loss_avg": 0.03181992918252945}
+{"step": 9690, "action_loss_avg": 0.004770417755935341}
+{"step": 9700, "loss": 0.0432, "learning_rate": 9.939753843162918e-05}
+{"step": 9700, "dynamics_loss_avg": 0.04064999856054783}
+{"step": 9700, "action_loss_avg": 0.006650264095515013}
+{"step": 9710, "dynamics_loss_avg": 0.02987033035606146}
+{"step": 9710, "action_loss_avg": 0.004967701877467335}
+{"step": 9720, "dynamics_loss_avg": 0.03602411225438118}
+{"step": 9720, "action_loss_avg": 0.007696396624669433}
+{"step": 9730, "dynamics_loss_avg": 0.02978320373222232}
+{"step": 9730, "action_loss_avg": 0.006451532896608114}
+{"step": 9740, "dynamics_loss_avg": 0.03458975348621607}
+{"step": 9740, "action_loss_avg": 0.005819278280250728}
+{"step": 9750, "loss": 0.0372, "learning_rate": 9.93846756624202e-05}
+{"step": 9750, "dynamics_loss_avg": 0.035287040192633866}
+{"step": 9750, "action_loss_avg": 0.0074532496277242895}
+{"step": 9760, "dynamics_loss_avg": 0.0288275639526546}
+{"step": 9760, "action_loss_avg": 0.005425214255228639}
+{"step": 9770, "dynamics_loss_avg": 0.0366265507414937}
+{"step": 9770, "action_loss_avg": 0.0062162267859093845}
+{"step": 9780, "dynamics_loss_avg": 0.037921492382884024}
+{"step": 9780, "action_loss_avg": 0.007971980143338442}
+{"step": 9790, "dynamics_loss_avg": 0.04500509072095156}
+{"step": 9790, "action_loss_avg": 0.007979385554790497}
+{"step": 9800, "loss": 0.0426, "learning_rate": 9.937167787739372e-05}
+{"step": 9800, "dynamics_loss_avg": 0.03444060841575265}
+{"step": 9800, "action_loss_avg": 0.006560068065300584}
+{"step": 9810, "dynamics_loss_avg": 0.0283617882989347}
+{"step": 9810, "action_loss_avg": 0.0043561629252508284}
+{"step": 9820, "dynamics_loss_avg": 0.03208618257194758}
+{"step": 9820, "action_loss_avg": 0.005448806169442833}
+{"step": 9830, "dynamics_loss_avg": 0.039983831346035004}
+{"step": 9830, "action_loss_avg": 0.007231471035629511}
+{"step": 9840, "dynamics_loss_avg": 0.04276917465031147}
+{"step": 9840, "action_loss_avg": 0.0072031054645776745}
+{"step": 9850, "loss": 0.0396, "learning_rate": 9.935854511208518e-05}
+{"step": 9850, "dynamics_loss_avg": 0.04218354756012559}
+{"step": 9850, "action_loss_avg": 0.006178143864963204}
+{"step": 9860, "dynamics_loss_avg": 0.036145143769681455}
+{"step": 9860, "action_loss_avg": 0.006450987048447132}
+{"step": 9870, "dynamics_loss_avg": 0.030728964228183032}
+{"step": 9870, "action_loss_avg": 0.007012054696679116}
+{"step": 9880, "dynamics_loss_avg": 0.03855554582551122}
+{"step": 9880, "action_loss_avg": 0.00799682957585901}
+{"step": 9890, "dynamics_loss_avg": 0.036497585102915765}
+{"step": 9890, "action_loss_avg": 0.007854061503894626}
+{"step": 9900, "loss": 0.042, "learning_rate": 9.934527740239906e-05}
+{"step": 9900, "dynamics_loss_avg": 0.046044205967336896}
+{"step": 9900, "action_loss_avg": 0.010290762223303319}
+{"step": 9910, "dynamics_loss_avg": 0.02925046756863594}
+{"step": 9910, "action_loss_avg": 0.004828594799619168}
+{"step": 9920, "dynamics_loss_avg": 0.03886387078091502}
+{"step": 9920, "action_loss_avg": 0.007275933073833585}
+{"step": 9930, "dynamics_loss_avg": 0.04009619504213333}
+{"step": 9930, "action_loss_avg": 0.0071681914385408165}
+{"step": 9940, "dynamics_loss_avg": 0.04654306909069419}
+{"step": 9940, "action_loss_avg": 0.008990566339343786}
+{"step": 9950, "loss": 0.0457, "learning_rate": 9.933187478460875e-05}
+{"step": 9950, "dynamics_loss_avg": 0.04627144169062376}
+{"step": 9950, "action_loss_avg": 0.009158410131931305}
+{"step": 9960, "dynamics_loss_avg": 0.036915600579231975}
+{"step": 9960, "action_loss_avg": 0.006890476052649319}
+{"step": 9970, "dynamics_loss_avg": 0.039431563951075076}
+{"step": 9970, "action_loss_avg": 0.007781549682840705}
+{"step": 9980, "dynamics_loss_avg": 0.028941622003912926}
+{"step": 9980, "action_loss_avg": 0.004975597362499684}
+{"step": 9990, "dynamics_loss_avg": 0.03282387629151344}
+{"step": 9990, "action_loss_avg": 0.007919688359834254}
+{"step": 10000, "loss": 0.0417, "learning_rate": 9.931833729535651e-05}
+{"step": 10000, "dynamics_loss_avg": 0.03676786422729492}
+{"step": 10000, "action_loss_avg": 0.005787311878520995}
+{"step": 10010, "dynamics_loss_avg": 0.03499491708353162}
+{"step": 10010, "action_loss_avg": 0.00751125505194068}
+{"step": 10020, "dynamics_loss_avg": 0.03634779565036297}
+{"step": 10020, "action_loss_avg": 0.006525756814517081}
+{"step": 10030, "dynamics_loss_avg": 0.03482917072251439}
+{"step": 10030, "action_loss_avg": 0.0051864430191926655}
+{"step": 10040, "dynamics_loss_avg": 0.03694023145362735}
+{"step": 10040, "action_loss_avg": 0.0064857193734496835}
+{"step": 10050, "loss": 0.0404, "learning_rate": 9.930466497165333e-05}
+{"step": 10050, "dynamics_loss_avg": 0.030630042683333157}
+{"step": 10050, "action_loss_avg": 0.006341834890190512}
+{"step": 10060, "dynamics_loss_avg": 0.032290342077612874}
+{"step": 10060, "action_loss_avg": 0.005197475932072848}
+{"step": 10070, "dynamics_loss_avg": 0.034727406967431304}
+{"step": 10070, "action_loss_avg": 0.0062318864511325955}
+{"step": 10080, "dynamics_loss_avg": 0.0329252134077251}
+{"step": 10080, "action_loss_avg": 0.004747442121151834}
+{"step": 10090, "dynamics_loss_avg": 0.0334184623323381}
+{"step": 10090, "action_loss_avg": 0.006688625947572291}
+{"step": 10100, "loss": 0.0395, "learning_rate": 9.92908578508788e-05}
+{"step": 10100, "dynamics_loss_avg": 0.040772701241075994}
+{"step": 10100, "action_loss_avg": 0.008689259737730026}
+{"step": 10110, "dynamics_loss_avg": 0.04113386776298285}
+{"step": 10110, "action_loss_avg": 0.007862564618699252}
+{"step": 10120, "dynamics_loss_avg": 0.03761820048093796}
+{"step": 10120, "action_loss_avg": 0.005895820376463234}
+{"step": 10130, "dynamics_loss_avg": 0.03246449576690793}
+{"step": 10130, "action_loss_avg": 0.00484096291474998}
+{"step": 10140, "dynamics_loss_avg": 0.034026100859045984}
+{"step": 10140, "action_loss_avg": 0.005141873378306627}
+{"step": 10150, "loss": 0.0399, "learning_rate": 9.927691597078108e-05}
+{"step": 10150, "dynamics_loss_avg": 0.030679627787321806}
+{"step": 10150, "action_loss_avg": 0.00651542420964688}
+{"step": 10160, "dynamics_loss_avg": 0.037718052975833416}
+{"step": 10160, "action_loss_avg": 0.005909350840374828}
+{"step": 10170, "dynamics_loss_avg": 0.03223352963104844}
+{"step": 10170, "action_loss_avg": 0.006035479670390487}
+{"step": 10180, "dynamics_loss_avg": 0.0383117732591927}
+{"step": 10180, "action_loss_avg": 0.006611407338641584}
+{"step": 10190, "dynamics_loss_avg": 0.03702214099466801}
+{"step": 10190, "action_loss_avg": 0.006760397995822132}
+{"step": 10200, "loss": 0.0373, "learning_rate": 9.926283936947673e-05}
+{"step": 10200, "dynamics_loss_avg": 0.02872909903526306}
+{"step": 10200, "action_loss_avg": 0.0045497462851926684}
+{"step": 10210, "dynamics_loss_avg": 0.029557434562593698}
+{"step": 10210, "action_loss_avg": 0.005012514523696154}
+{"step": 10220, "dynamics_loss_avg": 0.04311578925698996}
+{"step": 10220, "action_loss_avg": 0.008558166143484414}
+{"step": 10230, "dynamics_loss_avg": 0.02764400262385607}
+{"step": 10230, "action_loss_avg": 0.0042244738433510065}
+{"step": 10240, "dynamics_loss_avg": 0.03921316992491484}
+{"step": 10240, "action_loss_avg": 0.007687687408179045}
+{"step": 10250, "loss": 0.038, "learning_rate": 9.924862808545066e-05}
+{"step": 10250, "dynamics_loss_avg": 0.03281268058344722}
+{"step": 10250, "action_loss_avg": 0.005543742259033024}
+{"step": 10260, "dynamics_loss_avg": 0.03444581213407218}
+{"step": 10260, "action_loss_avg": 0.008144186181016266}
+{"step": 10270, "dynamics_loss_avg": 0.03040858404710889}
+{"step": 10270, "action_loss_avg": 0.005692674871534109}
+{"step": 10280, "dynamics_loss_avg": 0.03722298890352249}
+{"step": 10280, "action_loss_avg": 0.007032776554115117}
+{"step": 10290, "dynamics_loss_avg": 0.05063630007207394}
+{"step": 10290, "action_loss_avg": 0.007141046132892371}
+{"step": 10300, "loss": 0.0395, "learning_rate": 9.923428215755594e-05}
+{"step": 10300, "dynamics_loss_avg": 0.0352241775020957}
+{"step": 10300, "action_loss_avg": 0.006077802274376154}
+{"step": 10310, "dynamics_loss_avg": 0.036554085090756416}
+{"step": 10310, "action_loss_avg": 0.006386995513457805}
+{"step": 10320, "dynamics_loss_avg": 0.03614521352574229}
+{"step": 10320, "action_loss_avg": 0.006324826716445386}
+{"step": 10330, "dynamics_loss_avg": 0.03498898455873132}
+{"step": 10330, "action_loss_avg": 0.004696726915426552}
+{"step": 10340, "dynamics_loss_avg": 0.03295757696032524}
+{"step": 10340, "action_loss_avg": 0.005579893698450178}
+{"step": 10350, "loss": 0.0391, "learning_rate": 9.92198016250138e-05}
+{"step": 10350, "dynamics_loss_avg": 0.03749660337343812}
+{"step": 10350, "action_loss_avg": 0.006322345696389675}
+{"step": 10360, "dynamics_loss_avg": 0.04451317377388477}
+{"step": 10360, "action_loss_avg": 0.006960625760257244}
+{"step": 10370, "dynamics_loss_avg": 0.03514862023293972}
+{"step": 10370, "action_loss_avg": 0.006071920925751329}
+{"step": 10380, "dynamics_loss_avg": 0.04448676630854607}
+{"step": 10380, "action_loss_avg": 0.005994556425139308}
+{"step": 10390, "dynamics_loss_avg": 0.03372426382265985}
+{"step": 10390, "action_loss_avg": 0.006412010476924479}
+{"step": 10400, "loss": 0.0436, "learning_rate": 9.920518652741348e-05}
+{"step": 10400, "dynamics_loss_avg": 0.040964478999376296}
+{"step": 10400, "action_loss_avg": 0.005732369562610984}
+{"step": 10410, "dynamics_loss_avg": 0.028502728324383497}
+{"step": 10410, "action_loss_avg": 0.005407273769378662}
+{"step": 10420, "dynamics_loss_avg": 0.030540068075060843}
+{"step": 10420, "action_loss_avg": 0.004962414829060435}
+{"step": 10430, "dynamics_loss_avg": 0.03623641533777118}
+{"step": 10430, "action_loss_avg": 0.0064566910965368155}
+{"step": 10440, "dynamics_loss_avg": 0.036368650011718275}
+{"step": 10440, "action_loss_avg": 0.006428901036269963}
+{"step": 10450, "loss": 0.0373, "learning_rate": 9.919043690471209e-05}
+{"step": 10450, "dynamics_loss_avg": 0.03402977399528027}
+{"step": 10450, "action_loss_avg": 0.006057297973893583}
+{"step": 10460, "dynamics_loss_avg": 0.027477431669831277}
+{"step": 10460, "action_loss_avg": 0.00447339090751484}
+{"step": 10470, "dynamics_loss_avg": 0.03471923712641001}
+{"step": 10470, "action_loss_avg": 0.008476701984182}
+{"step": 10480, "dynamics_loss_avg": 0.03823002781718969}
+{"step": 10480, "action_loss_avg": 0.006324198888614773}
+{"step": 10490, "dynamics_loss_avg": 0.03637971244752407}
+{"step": 10490, "action_loss_avg": 0.0070093173766508695}
+{"step": 10500, "loss": 0.0396, "learning_rate": 9.917555279723454e-05}
+{"step": 10500, "dynamics_loss_avg": 0.03571290522813797}
+{"step": 10500, "action_loss_avg": 0.007220757473260164}
+{"step": 10510, "dynamics_loss_avg": 0.03023743648082018}
+{"step": 10510, "action_loss_avg": 0.0038276724983006714}
+{"step": 10520, "dynamics_loss_avg": 0.03786745462566614}
+{"step": 10520, "action_loss_avg": 0.005954861757345498}
+{"step": 10530, "dynamics_loss_avg": 0.031898930482566354}
+{"step": 10530, "action_loss_avg": 0.00462084348546341}
+{"step": 10540, "dynamics_loss_avg": 0.03154083173722029}
+{"step": 10540, "action_loss_avg": 0.004687973926775157}
+{"step": 10550, "loss": 0.0371, "learning_rate": 9.91605342456734e-05}
+{"step": 10550, "dynamics_loss_avg": 0.043454508483409884}
+{"step": 10550, "action_loss_avg": 0.0073406514944508675}
+{"step": 10560, "dynamics_loss_avg": 0.0406217242591083}
+{"step": 10560, "action_loss_avg": 0.006727123004384339}
+{"step": 10570, "dynamics_loss_avg": 0.03926269728690386}
+{"step": 10570, "action_loss_avg": 0.006719744205474854}
+{"step": 10580, "dynamics_loss_avg": 0.02827362362295389}
+{"step": 10580, "action_loss_avg": 0.005434792477171868}
+{"step": 10590, "dynamics_loss_avg": 0.029332554480060936}
+{"step": 10590, "action_loss_avg": 0.005195961834397167}
+{"step": 10600, "loss": 0.0394, "learning_rate": 9.914538129108882e-05}
+{"step": 10600, "dynamics_loss_avg": 0.036403220705688}
+{"step": 10600, "action_loss_avg": 0.00831092505250126}
+{"step": 10610, "dynamics_loss_avg": 0.03581358902156353}
+{"step": 10610, "action_loss_avg": 0.005894770473241806}
+{"step": 10620, "dynamics_loss_avg": 0.041636605933308604}
+{"step": 10620, "action_loss_avg": 0.0058644724311307074}
+{"step": 10630, "dynamics_loss_avg": 0.04863490089774132}
+{"step": 10630, "action_loss_avg": 0.006664918316528201}
+{"step": 10640, "dynamics_loss_avg": 0.037531979661434886}
+{"step": 10640, "action_loss_avg": 0.007742211106233299}
+{"step": 10650, "loss": 0.0437, "learning_rate": 9.91300939749084e-05}
+{"step": 10650, "dynamics_loss_avg": 0.03727419087663293}
+{"step": 10650, "action_loss_avg": 0.006871700217016041}
+{"step": 10660, "dynamics_loss_avg": 0.03803478023037314}
+{"step": 10660, "action_loss_avg": 0.006135802873177454}
+{"step": 10670, "dynamics_loss_avg": 0.03744667824357748}
+{"step": 10670, "action_loss_avg": 0.005476038495544344}
+{"step": 10680, "dynamics_loss_avg": 0.04061036305502057}
+{"step": 10680, "action_loss_avg": 0.00695476676337421}
+{"step": 10690, "dynamics_loss_avg": 0.03753156643360853}
+{"step": 10690, "action_loss_avg": 0.007099012262187898}
+{"step": 10700, "loss": 0.0405, "learning_rate": 9.911467233892709e-05}
+{"step": 10700, "dynamics_loss_avg": 0.025896441377699374}
+{"step": 10700, "action_loss_avg": 0.004084391228388995}
+{"step": 10710, "dynamics_loss_avg": 0.032023072522133586}
+{"step": 10710, "action_loss_avg": 0.005964209546800703}
+{"step": 10720, "dynamics_loss_avg": 0.039063917100429536}
+{"step": 10720, "action_loss_avg": 0.007449326966889202}
+{"step": 10730, "dynamics_loss_avg": 0.042523091100156306}
+{"step": 10730, "action_loss_avg": 0.0063526748912408944}
+{"step": 10740, "dynamics_loss_avg": 0.03739444715902209}
+{"step": 10740, "action_loss_avg": 0.008132359804585576}
+{"step": 10750, "loss": 0.0418, "learning_rate": 9.909911642530703e-05}
+{"step": 10750, "dynamics_loss_avg": 0.03969652131199837}
+{"step": 10750, "action_loss_avg": 0.006731411698274315}
+{"step": 10760, "dynamics_loss_avg": 0.04124191021546721}
+{"step": 10760, "action_loss_avg": 0.008807698055170477}
+{"step": 10770, "dynamics_loss_avg": 0.02950994558632374}
+{"step": 10770, "action_loss_avg": 0.004772566782776266}
+{"step": 10780, "dynamics_loss_avg": 0.03313184194266796}
+{"step": 10780, "action_loss_avg": 0.005596781964413822}
+{"step": 10790, "dynamics_loss_avg": 0.03878823760896921}
+{"step": 10790, "action_loss_avg": 0.00717449658550322}
+{"step": 10800, "loss": 0.0413, "learning_rate": 9.908342627657751e-05}
+{"step": 10800, "dynamics_loss_avg": 0.0401411060243845}
+{"step": 10800, "action_loss_avg": 0.006681786978151649}
+{"step": 10810, "dynamics_loss_avg": 0.0345801554620266}
+{"step": 10810, "action_loss_avg": 0.005458628199994564}
+{"step": 10820, "dynamics_loss_avg": 0.027058014739304782}
+{"step": 10820, "action_loss_avg": 0.00571582696866244}
+{"step": 10830, "dynamics_loss_avg": 0.042103099264204503}
+{"step": 10830, "action_loss_avg": 0.005445084604434669}
+{"step": 10840, "dynamics_loss_avg": 0.03071286417543888}
+{"step": 10840, "action_loss_avg": 0.004802250023931265}
+{"step": 10850, "loss": 0.037, "learning_rate": 9.906760193563482e-05}
+{"step": 10850, "dynamics_loss_avg": 0.029412855859845877}
+{"step": 10850, "action_loss_avg": 0.0049423627206124365}
+{"step": 10860, "dynamics_loss_avg": 0.03649186473339796}
+{"step": 10860, "action_loss_avg": 0.007355495519004762}
+{"step": 10870, "dynamics_loss_avg": 0.034688552981242536}
+{"step": 10870, "action_loss_avg": 0.007056665513664484}
+{"step": 10880, "dynamics_loss_avg": 0.04303268222138286}
+{"step": 10880, "action_loss_avg": 0.007933483831584454}
+{"step": 10890, "dynamics_loss_avg": 0.039300255570560695}
+{"step": 10890, "action_loss_avg": 0.007146847870899364}
+{"step": 10900, "loss": 0.0436, "learning_rate": 9.905164344574205e-05}
+{"step": 10900, "dynamics_loss_avg": 0.040906406845897435}
+{"step": 10900, "action_loss_avg": 0.00618506099563092}
+{"step": 10910, "dynamics_loss_avg": 0.042755620554089546}
+{"step": 10910, "action_loss_avg": 0.006560657930094749}
+{"step": 10920, "dynamics_loss_avg": 0.04229761073365808}
+{"step": 10920, "action_loss_avg": 0.007010202563833445}
+{"step": 10930, "dynamics_loss_avg": 0.038756207935512064}
+{"step": 10930, "action_loss_avg": 0.006318428367376327}
+{"step": 10940, "dynamics_loss_avg": 0.035042078513652083}
+{"step": 10940, "action_loss_avg": 0.006141312117688358}
+{"step": 10950, "loss": 0.0418, "learning_rate": 9.903555085052915e-05}
+{"step": 10950, "dynamics_loss_avg": 0.03483164682984352}
+{"step": 10950, "action_loss_avg": 0.0058422501431778075}
+{"step": 10960, "dynamics_loss_avg": 0.03657720135524869}
+{"step": 10960, "action_loss_avg": 0.005300489312503487}
+{"step": 10970, "dynamics_loss_avg": 0.03357179835438728}
+{"step": 10970, "action_loss_avg": 0.006555536389350891}
+{"step": 10980, "dynamics_loss_avg": 0.034880765900015834}
+{"step": 10980, "action_loss_avg": 0.005458784219808876}
+{"step": 10990, "dynamics_loss_avg": 0.036309616174548864}
+{"step": 10990, "action_loss_avg": 0.006526259751990437}
+{"step": 11000, "loss": 0.0397, "learning_rate": 9.901932419399264e-05}
+{"step": 11000, "dynamics_loss_avg": 0.029762714728713037}
+{"step": 11000, "action_loss_avg": 0.005212636815849691}
+{"step": 11010, "dynamics_loss_avg": 0.03658488430082798}
+{"step": 11010, "action_loss_avg": 0.004958405718207359}
+{"step": 11020, "dynamics_loss_avg": 0.03802175251767039}
+{"step": 11020, "action_loss_avg": 0.008176096924580633}
+{"step": 11030, "dynamics_loss_avg": 0.037260739225894214}
+{"step": 11030, "action_loss_avg": 0.00527477425057441}
+{"step": 11040, "dynamics_loss_avg": 0.03501892806962133}
+{"step": 11040, "action_loss_avg": 0.006105330970603973}
+{"step": 11050, "loss": 0.0367, "learning_rate": 9.900296352049558e-05}
+{"step": 11050, "dynamics_loss_avg": 0.032781082578003405}
+{"step": 11050, "action_loss_avg": 0.005216614669188857}
+{"step": 11060, "dynamics_loss_avg": 0.031008686311542986}
+{"step": 11060, "action_loss_avg": 0.005063263862393796}
+{"step": 11070, "dynamics_loss_avg": 0.0363606440834701}
+{"step": 11070, "action_loss_avg": 0.0068110496038571}
+{"step": 11080, "dynamics_loss_avg": 0.04562402330338955}
+{"step": 11080, "action_loss_avg": 0.005422782874666155}
+{"step": 11090, "dynamics_loss_avg": 0.02674394811037928}
+{"step": 11090, "action_loss_avg": 0.0040600420790724455}
+{"step": 11100, "loss": 0.0366, "learning_rate": 9.898646887476741e-05}
+{"step": 11100, "dynamics_loss_avg": 0.03997351601719856}
+{"step": 11100, "action_loss_avg": 0.006451048061717301}
+{"step": 11110, "dynamics_loss_avg": 0.03221920179203153}
+{"step": 11110, "action_loss_avg": 0.005958602391183376}
+{"step": 11120, "dynamics_loss_avg": 0.031973912939429285}
+{"step": 11120, "action_loss_avg": 0.004331166320480406}
+{"step": 11130, "dynamics_loss_avg": 0.019558735191822052}
+{"step": 11130, "action_loss_avg": 0.0029589328332804143}
+{"step": 11140, "dynamics_loss_avg": 0.03059917949140072}
+{"step": 11140, "action_loss_avg": 0.006181244796607643}
+{"step": 11150, "loss": 0.0337, "learning_rate": 9.89698403019039e-05}
+{"step": 11150, "dynamics_loss_avg": 0.04326061094179749}
+{"step": 11150, "action_loss_avg": 0.007608629576861858}
+{"step": 11160, "dynamics_loss_avg": 0.03791353479027748}
+{"step": 11160, "action_loss_avg": 0.00585816606762819}
+{"step": 11170, "dynamics_loss_avg": 0.030932772252708674}
+{"step": 11170, "action_loss_avg": 0.004528565856162459}
+{"step": 11180, "dynamics_loss_avg": 0.026318442635238172}
+{"step": 11180, "action_loss_avg": 0.003952218894846737}
+{"step": 11190, "dynamics_loss_avg": 0.03232643324881792}
+{"step": 11190, "action_loss_avg": 0.006624214502517134}
+{"step": 11200, "loss": 0.035, "learning_rate": 9.895307784736691e-05}
+{"step": 11200, "dynamics_loss_avg": 0.03251598328351975}
+{"step": 11200, "action_loss_avg": 0.0047560094622895125}
+{"step": 11210, "dynamics_loss_avg": 0.03805839996784925}
+{"step": 11210, "action_loss_avg": 0.007763064606115222}
+{"step": 11220, "dynamics_loss_avg": 0.02732934569939971}
+{"step": 11220, "action_loss_avg": 0.005211470334324985}
+{"step": 11230, "dynamics_loss_avg": 0.03516300935298204}
+{"step": 11230, "action_loss_avg": 0.007667226390913129}
+{"step": 11240, "dynamics_loss_avg": 0.027087752148509024}
+{"step": 11240, "action_loss_avg": 0.004643838375341147}
+{"step": 11250, "loss": 0.0358, "learning_rate": 9.893618155698436e-05}
+{"step": 11250, "dynamics_loss_avg": 0.03833699785172939}
+{"step": 11250, "action_loss_avg": 0.005334318242967128}
+{"step": 11260, "dynamics_loss_avg": 0.03198006497696042}
+{"step": 11260, "action_loss_avg": 0.005292746599297971}
+{"step": 11270, "dynamics_loss_avg": 0.03529280424118042}
+{"step": 11270, "action_loss_avg": 0.005127760907635092}
+{"step": 11280, "dynamics_loss_avg": 0.03090454814955592}
+{"step": 11280, "action_loss_avg": 0.006275713630020619}
+{"step": 11290, "dynamics_loss_avg": 0.0329139965120703}
+{"step": 11290, "action_loss_avg": 0.004913069691974669}
+{"step": 11300, "loss": 0.0347, "learning_rate": 9.891915147695006e-05}
+{"step": 11300, "dynamics_loss_avg": 0.026207871735095978}
+{"step": 11300, "action_loss_avg": 0.003997623920440674}
+{"step": 11310, "dynamics_loss_avg": 0.031074190326035023}
+{"step": 11310, "action_loss_avg": 0.0036859602900221945}
+{"step": 11320, "dynamics_loss_avg": 0.0403459370136261}
+{"step": 11320, "action_loss_avg": 0.006817412615055219}
+{"step": 11330, "dynamics_loss_avg": 0.031179005280137062}
+{"step": 11330, "action_loss_avg": 0.004189634462818503}
+{"step": 11340, "dynamics_loss_avg": 0.034671629313379526}
+{"step": 11340, "action_loss_avg": 0.00573821160942316}
+{"step": 11350, "loss": 0.0376, "learning_rate": 9.890198765382357e-05}
+{"step": 11350, "dynamics_loss_avg": 0.03952764617279172}
+{"step": 11350, "action_loss_avg": 0.00721468924311921}
+{"step": 11360, "dynamics_loss_avg": 0.03663748558610678}
+{"step": 11360, "action_loss_avg": 0.007213088974822313}
+{"step": 11370, "dynamics_loss_avg": 0.0429969672113657}
+{"step": 11370, "action_loss_avg": 0.008102493965998292}
+{"step": 11380, "dynamics_loss_avg": 0.0326392974704504}
+{"step": 11380, "action_loss_avg": 0.0045880045974627135}
+{"step": 11390, "dynamics_loss_avg": 0.03458151910454035}
+{"step": 11390, "action_loss_avg": 0.005025016097351909}
+{"step": 11400, "loss": 0.0408, "learning_rate": 9.888469013453018e-05}
+{"step": 11400, "dynamics_loss_avg": 0.036181623302400115}
+{"step": 11400, "action_loss_avg": 0.007079360436182469}
+{"step": 11410, "dynamics_loss_avg": 0.03396511785686016}
+{"step": 11410, "action_loss_avg": 0.006505496986210346}
+{"step": 11420, "dynamics_loss_avg": 0.030693016946315765}
+{"step": 11420, "action_loss_avg": 0.005436113337054849}
+{"step": 11430, "dynamics_loss_avg": 0.03835501708090305}
+{"step": 11430, "action_loss_avg": 0.005577467987313867}
+{"step": 11440, "dynamics_loss_avg": 0.029360542166978122}
+{"step": 11440, "action_loss_avg": 0.0043759347638115285}
+{"step": 11450, "loss": 0.0353, "learning_rate": 9.88672589663606e-05}
+{"step": 11450, "dynamics_loss_avg": 0.030834102630615236}
+{"step": 11450, "action_loss_avg": 0.004864068940514698}
+{"step": 11460, "dynamics_loss_avg": 0.03024101462215185}
+{"step": 11460, "action_loss_avg": 0.004425274836830795}
+{"step": 11470, "dynamics_loss_avg": 0.028939093835651873}
+{"step": 11470, "action_loss_avg": 0.004515951173380018}
+{"step": 11480, "dynamics_loss_avg": 0.03745747869834304}
+{"step": 11480, "action_loss_avg": 0.006357872404623777}
+{"step": 11490, "dynamics_loss_avg": 0.03948287200182676}
+{"step": 11490, "action_loss_avg": 0.007027690066024661}
+{"step": 11500, "loss": 0.0381, "learning_rate": 9.884969419697101e-05}
+{"step": 11500, "dynamics_loss_avg": 0.03813536185771227}
+{"step": 11500, "action_loss_avg": 0.005709980078972876}
+{"step": 11510, "dynamics_loss_avg": 0.027365957852452993}
+{"step": 11510, "action_loss_avg": 0.005066586320754141}
+{"step": 11520, "dynamics_loss_avg": 0.03605564059689641}
+{"step": 11520, "action_loss_avg": 0.006866178498603404}
+{"step": 11530, "dynamics_loss_avg": 0.048068413697183135}
+{"step": 11530, "action_loss_avg": 0.007290918997023254}
+{"step": 11540, "dynamics_loss_avg": 0.03641426954418421}
+{"step": 11540, "action_loss_avg": 0.005812504212372005}
+{"step": 11550, "loss": 0.0393, "learning_rate": 9.88319958743828e-05}
+{"step": 11550, "dynamics_loss_avg": 0.03474212996661663}
+{"step": 11550, "action_loss_avg": 0.004376164101995528}
+{"step": 11560, "dynamics_loss_avg": 0.031000287737697363}
+{"step": 11560, "action_loss_avg": 0.005275095021352172}
+{"step": 11570, "dynamics_loss_avg": 0.0352994479238987}
+{"step": 11570, "action_loss_avg": 0.0049957050592638556}
+{"step": 11580, "dynamics_loss_avg": 0.029719084966927767}
+{"step": 11580, "action_loss_avg": 0.004846603178884834}
+{"step": 11590, "dynamics_loss_avg": 0.030244603101164103}
+{"step": 11590, "action_loss_avg": 0.004315688263159245}
+{"step": 11600, "loss": 0.036, "learning_rate": 9.881416404698252e-05}
+{"step": 11600, "dynamics_loss_avg": 0.032097015623003246}
+{"step": 11600, "action_loss_avg": 0.004563993134070188}
+{"step": 11610, "dynamics_loss_avg": 0.026615022076293827}
+{"step": 11610, "action_loss_avg": 0.004836892674211413}
+{"step": 11620, "dynamics_loss_avg": 0.03127704653888941}
+{"step": 11620, "action_loss_avg": 0.004184178588911891}
+{"step": 11630, "dynamics_loss_avg": 0.02667855875333771}
+{"step": 11630, "action_loss_avg": 0.003431836568051949}
+{"step": 11640, "dynamics_loss_avg": 0.04168177600950003}
+{"step": 11640, "action_loss_avg": 0.007194085570517927}
+{"step": 11650, "loss": 0.0355, "learning_rate": 9.879619876352168e-05}
+{"step": 11650, "dynamics_loss_avg": 0.029697785805910825}
+{"step": 11650, "action_loss_avg": 0.004071384901180863}
+{"step": 11660, "dynamics_loss_avg": 0.031119208969175815}
+{"step": 11660, "action_loss_avg": 0.004269942222163081}
+{"step": 11670, "dynamics_loss_avg": 0.038444002345204356}
+{"step": 11670, "action_loss_avg": 0.006263776984997094}
+{"step": 11680, "dynamics_loss_avg": 0.048314265254884955}
+{"step": 11680, "action_loss_avg": 0.009639511618297547}
+{"step": 11690, "dynamics_loss_avg": 0.03662173161283135}
+{"step": 11690, "action_loss_avg": 0.005102229421027005}
+{"step": 11700, "loss": 0.0414, "learning_rate": 9.877810007311671e-05}
+{"step": 11700, "dynamics_loss_avg": 0.03494855659082532}
+{"step": 11700, "action_loss_avg": 0.0050075822975486515}
+{"step": 11710, "dynamics_loss_avg": 0.02979191327467561}
+{"step": 11710, "action_loss_avg": 0.005221980367787182}
+{"step": 11720, "dynamics_loss_avg": 0.03597135539166629}
+{"step": 11720, "action_loss_avg": 0.004821447376161814}
+{"step": 11730, "dynamics_loss_avg": 0.0383083158172667}
+{"step": 11730, "action_loss_avg": 0.005765191093087196}
+{"step": 11740, "dynamics_loss_avg": 0.03278360813856125}
+{"step": 11740, "action_loss_avg": 0.004920907597988844}
+{"step": 11750, "loss": 0.0394, "learning_rate": 9.875986802524875e-05}
+{"step": 11750, "dynamics_loss_avg": 0.04292109198868275}
+{"step": 11750, "action_loss_avg": 0.005287108989432454}
+{"step": 11760, "dynamics_loss_avg": 0.036699379328638315}
+{"step": 11760, "action_loss_avg": 0.005750295415055007}
+{"step": 11770, "dynamics_loss_avg": 0.03662390951067209}
+{"step": 11770, "action_loss_avg": 0.007483660586876795}
+{"step": 11780, "dynamics_loss_avg": 0.031010177452117205}
+{"step": 11780, "action_loss_avg": 0.004432396544143557}
+{"step": 11790, "dynamics_loss_avg": 0.03347165221348405}
+{"step": 11790, "action_loss_avg": 0.0046846328768879175}
+{"step": 11800, "loss": 0.0368, "learning_rate": 9.874150266976347e-05}
+{"step": 11800, "dynamics_loss_avg": 0.03080323515459895}
+{"step": 11800, "action_loss_avg": 0.0054566238890402016}
+{"step": 11810, "dynamics_loss_avg": 0.02733597354963422}
+{"step": 11810, "action_loss_avg": 0.004431770002702251}
+{"step": 11820, "dynamics_loss_avg": 0.031229445058852435}
+{"step": 11820, "action_loss_avg": 0.005855651065940037}
+{"step": 11830, "dynamics_loss_avg": 0.033972352277487516}
+{"step": 11830, "action_loss_avg": 0.006284406560007482}
+{"step": 11840, "dynamics_loss_avg": 0.0339824496768415}
+{"step": 11840, "action_loss_avg": 0.004533225356135517}
+{"step": 11850, "loss": 0.0361, "learning_rate": 9.872300405687109e-05}
+{"step": 11850, "dynamics_loss_avg": 0.03657908132299781}
+{"step": 11850, "action_loss_avg": 0.006050189770758152}
+{"step": 11860, "dynamics_loss_avg": 0.02847816552966833}
+{"step": 11860, "action_loss_avg": 0.004317191313020885}
+{"step": 11870, "dynamics_loss_avg": 0.03448354145511985}
+{"step": 11870, "action_loss_avg": 0.0050160840153694155}
+{"step": 11880, "dynamics_loss_avg": 0.037973203137516974}
+{"step": 11880, "action_loss_avg": 0.005223739927168935}
+{"step": 11890, "dynamics_loss_avg": 0.040192775707691905}
+{"step": 11890, "action_loss_avg": 0.008077873778529466}
+{"step": 11900, "loss": 0.0389, "learning_rate": 9.870437223714612e-05}
+{"step": 11900, "dynamics_loss_avg": 0.04163242820650339}
+{"step": 11900, "action_loss_avg": 0.005559963476844132}
+{"step": 11910, "dynamics_loss_avg": 0.04142678566277027}
+{"step": 11910, "action_loss_avg": 0.006804212986025959}
+{"step": 11920, "dynamics_loss_avg": 0.03635256141424179}
+{"step": 11920, "action_loss_avg": 0.005866979970596731}
+{"step": 11930, "dynamics_loss_avg": 0.030793775152415038}
+{"step": 11930, "action_loss_avg": 0.005702211265452206}
+{"step": 11940, "dynamics_loss_avg": 0.03798253908753395}
+{"step": 11940, "action_loss_avg": 0.004750874207820744}
+{"step": 11950, "loss": 0.0406, "learning_rate": 9.86856072615272e-05}
+{"step": 11950, "dynamics_loss_avg": 0.037539249565452334}
+{"step": 11950, "action_loss_avg": 0.005983372218906879}
+{"step": 11960, "dynamics_loss_avg": 0.03104363353922963}
+{"step": 11960, "action_loss_avg": 0.00451853375416249}
+{"step": 11970, "dynamics_loss_avg": 0.03561485894024372}
+{"step": 11970, "action_loss_avg": 0.007073565945029258}
+{"step": 11980, "dynamics_loss_avg": 0.03644880345091224}
+{"step": 11980, "action_loss_avg": 0.005198510538320988}
+{"step": 11990, "dynamics_loss_avg": 0.031037178169935942}
+{"step": 11990, "action_loss_avg": 0.005383953091222793}
+{"step": 12000, "loss": 0.041, "learning_rate": 9.86667091813171e-05}
+{"step": 12000, "dynamics_loss_avg": 0.03941595032811165}
+{"step": 12000, "action_loss_avg": 0.00628133713034913}
+{"step": 12010, "dynamics_loss_avg": 0.037116825487464665}
+{"step": 12010, "action_loss_avg": 0.007995961885899305}
+{"step": 12020, "dynamics_loss_avg": 0.03285839073359966}
+{"step": 12020, "action_loss_avg": 0.005281869205646217}
+{"step": 12030, "dynamics_loss_avg": 0.03659397554583847}
+{"step": 12030, "action_loss_avg": 0.006217921641655267}
+{"step": 12040, "dynamics_loss_avg": 0.03563314573839307}
+{"step": 12040, "action_loss_avg": 0.00702495250152424}
+{"step": 12050, "loss": 0.0397, "learning_rate": 9.864767804818243e-05}
+{"step": 12050, "dynamics_loss_avg": 0.030712514463812114}
+{"step": 12050, "action_loss_avg": 0.005767806572839618}
+{"step": 12060, "dynamics_loss_avg": 0.032657370902597904}
+{"step": 12060, "action_loss_avg": 0.006030991720035672}
+{"step": 12070, "dynamics_loss_avg": 0.04984313361346722}
+{"step": 12070, "action_loss_avg": 0.008543429034762084}
+{"step": 12080, "dynamics_loss_avg": 0.036704718321561816}
+{"step": 12080, "action_loss_avg": 0.006863441132009029}
+{"step": 12090, "dynamics_loss_avg": 0.03963741585612297}
+{"step": 12090, "action_loss_avg": 0.007289117341861129}
+{"step": 12100, "loss": 0.041, "learning_rate": 9.862851391415356e-05}
+{"step": 12100, "dynamics_loss_avg": 0.03639069339260459}
+{"step": 12100, "action_loss_avg": 0.007794528990052641}
+{"step": 12110, "dynamics_loss_avg": 0.029462145082652567}
+{"step": 12110, "action_loss_avg": 0.004501595511101186}
+{"step": 12120, "dynamics_loss_avg": 0.03219792284071445}
+{"step": 12120, "action_loss_avg": 0.005061122996266931}
+{"step": 12130, "dynamics_loss_avg": 0.02861421965062618}
+{"step": 12130, "action_loss_avg": 0.004263793420977891}
+{"step": 12140, "dynamics_loss_avg": 0.030228811828419567}
+{"step": 12140, "action_loss_avg": 0.006228611618280411}
+{"step": 12150, "loss": 0.0336, "learning_rate": 9.860921683162455e-05}
+{"step": 12150, "dynamics_loss_avg": 0.022189769381657242}
+{"step": 12150, "action_loss_avg": 0.003218895185273141}
+{"step": 12160, "dynamics_loss_avg": 0.043438490759581325}
+{"step": 12160, "action_loss_avg": 0.005316135031171143}
+{"step": 12170, "dynamics_loss_avg": 0.027094066515564917}
+{"step": 12170, "action_loss_avg": 0.003683683695271611}
+{"step": 12180, "dynamics_loss_avg": 0.038959909696131945}
+{"step": 12180, "action_loss_avg": 0.004803542618174106}
+{"step": 12190, "dynamics_loss_avg": 0.04526399187743664}
+{"step": 12190, "action_loss_avg": 0.007181918516289442}
+{"step": 12200, "loss": 0.0409, "learning_rate": 9.858978685335285e-05}
+{"step": 12200, "dynamics_loss_avg": 0.030398333352059125}
+{"step": 12200, "action_loss_avg": 0.004683637619018554}
+{"step": 12210, "dynamics_loss_avg": 0.0287120102904737}
+{"step": 12210, "action_loss_avg": 0.005378050764556974}
+{"step": 12220, "dynamics_loss_avg": 0.034094374533742665}
+{"step": 12220, "action_loss_avg": 0.005501081398688257}
+{"step": 12230, "dynamics_loss_avg": 0.03671246413141489}
+{"step": 12230, "action_loss_avg": 0.0060115944012068216}
+{"step": 12240, "dynamics_loss_avg": 0.04439051002264023}
+{"step": 12240, "action_loss_avg": 0.005730570876039565}
+{"step": 12250, "loss": 0.0417, "learning_rate": 9.857022403245928e-05}
+{"step": 12250, "dynamics_loss_avg": 0.04927428271621466}
+{"step": 12250, "action_loss_avg": 0.007812399743124842}
+{"step": 12260, "dynamics_loss_avg": 0.02740056151524186}
+{"step": 12260, "action_loss_avg": 0.005883000529138371}
+{"step": 12270, "dynamics_loss_avg": 0.03926918916404247}
+{"step": 12270, "action_loss_avg": 0.006237564666662365}
+{"step": 12280, "dynamics_loss_avg": 0.0389435950666666}
+{"step": 12280, "action_loss_avg": 0.006012904806993902}
+{"step": 12290, "dynamics_loss_avg": 0.03644901141524315}
+{"step": 12290, "action_loss_avg": 0.004548944457201287}
+{"step": 12300, "loss": 0.0383, "learning_rate": 9.855052842242787e-05}
+{"step": 12300, "dynamics_loss_avg": 0.033155158441513774}
+{"step": 12300, "action_loss_avg": 0.00646966490894556}
+{"step": 12310, "dynamics_loss_avg": 0.030718463473021984}
+{"step": 12310, "action_loss_avg": 0.005352123198099435}
+{"step": 12320, "dynamics_loss_avg": 0.02484493711963296}
+{"step": 12320, "action_loss_avg": 0.003428174345754087}
+{"step": 12330, "dynamics_loss_avg": 0.02964186780154705}
+{"step": 12330, "action_loss_avg": 0.0047481275512836875}
+{"step": 12340, "dynamics_loss_avg": 0.02638431917876005}
+{"step": 12340, "action_loss_avg": 0.004415368539048359}
+{"step": 12350, "loss": 0.0319, "learning_rate": 9.853070007710564e-05}
+{"step": 12350, "dynamics_loss_avg": 0.025878506433218717}
+{"step": 12350, "action_loss_avg": 0.0038029663846828043}
+{"step": 12360, "dynamics_loss_avg": 0.03384678289294243}
+{"step": 12360, "action_loss_avg": 0.004975223098881543}
+{"step": 12370, "dynamics_loss_avg": 0.03669204190373421}
+{"step": 12370, "action_loss_avg": 0.004759436915628612}
+{"step": 12380, "dynamics_loss_avg": 0.03277951292693615}
+{"step": 12380, "action_loss_avg": 0.004401317134033888}
+{"step": 12390, "dynamics_loss_avg": 0.03587852260097861}
+{"step": 12390, "action_loss_avg": 0.0052385394461452964}
+{"step": 12400, "loss": 0.0374, "learning_rate": 9.851073905070254e-05}
+{"step": 12400, "dynamics_loss_avg": 0.022826865781098604}
+{"step": 12400, "action_loss_avg": 0.0035115439328365027}
+{"step": 12410, "dynamics_loss_avg": 0.038765539228916165}
+{"step": 12410, "action_loss_avg": 0.0052779979771003125}
+{"step": 12420, "dynamics_loss_avg": 0.04502534531056881}
+{"step": 12420, "action_loss_avg": 0.0065947950235567985}
+{"step": 12430, "dynamics_loss_avg": 0.03418310061097145}
+{"step": 12430, "action_loss_avg": 0.00496601783670485}
+{"step": 12440, "dynamics_loss_avg": 0.05085400827229023}
+{"step": 12440, "action_loss_avg": 0.009500710060819983}
+{"step": 12450, "loss": 0.0391, "learning_rate": 9.849064539779127e-05}
+{"step": 12450, "dynamics_loss_avg": 0.035358587838709356}
+{"step": 12450, "action_loss_avg": 0.0053798351902514694}
+{"step": 12460, "dynamics_loss_avg": 0.04013006240129471}
+{"step": 12460, "action_loss_avg": 0.006180348875932396}
+{"step": 12470, "dynamics_loss_avg": 0.033854028396308425}
+{"step": 12470, "action_loss_avg": 0.005944158334750682}
+{"step": 12480, "dynamics_loss_avg": 0.04311768654733896}
+{"step": 12480, "action_loss_avg": 0.006310128793120384}
+{"step": 12490, "dynamics_loss_avg": 0.037731122225522995}
+{"step": 12490, "action_loss_avg": 0.006692670308984816}
+{"step": 12500, "loss": 0.0407, "learning_rate": 9.847041917330708e-05}
+{"step": 12500, "dynamics_loss_avg": 0.033333230018615725}
+{"step": 12500, "action_loss_avg": 0.004085490480065346}
+{"step": 12510, "dynamics_loss_avg": 0.03990177009254694}
+{"step": 12510, "action_loss_avg": 0.005823653750121593}
+{"step": 12520, "dynamics_loss_avg": 0.03539493680000305}
+{"step": 12520, "action_loss_avg": 0.0062411786057055}
+{"step": 12530, "dynamics_loss_avg": 0.042835728637874125}
+{"step": 12530, "action_loss_avg": 0.0074235790641978385}
+{"step": 12540, "dynamics_loss_avg": 0.04163725152611732}
+{"step": 12540, "action_loss_avg": 0.006340618594549596}
+{"step": 12550, "loss": 0.042, "learning_rate": 9.845006043254771e-05}
+{"step": 12550, "dynamics_loss_avg": 0.045553664676845074}
+{"step": 12550, "action_loss_avg": 0.005197587586008012}
+{"step": 12560, "dynamics_loss_avg": 0.036207035277038814}
+{"step": 12560, "action_loss_avg": 0.0044086698850151155}
+{"step": 12570, "dynamics_loss_avg": 0.027922070864588023}
+{"step": 12570, "action_loss_avg": 0.005119345593266189}
+{"step": 12580, "dynamics_loss_avg": 0.03286331370472908}
+{"step": 12580, "action_loss_avg": 0.004229448596015572}
+{"step": 12590, "dynamics_loss_avg": 0.033430803148075935}
+{"step": 12590, "action_loss_avg": 0.004701931797899306}
+{"step": 12600, "loss": 0.0389, "learning_rate": 9.842956923117317e-05}
+{"step": 12600, "dynamics_loss_avg": 0.03431917503476143}
+{"step": 12600, "action_loss_avg": 0.007394968764856458}
+{"step": 12610, "dynamics_loss_avg": 0.030647873831912874}
+{"step": 12610, "action_loss_avg": 0.006075019086711109}
+{"step": 12620, "dynamics_loss_avg": 0.028864493034780024}
+{"step": 12620, "action_loss_avg": 0.004795695631764829}
+{"step": 12630, "dynamics_loss_avg": 0.02732318677008152}
+{"step": 12630, "action_loss_avg": 0.004104788391850888}
+{"step": 12640, "dynamics_loss_avg": 0.03556957095861435}
+{"step": 12640, "action_loss_avg": 0.005330947693437338}
+{"step": 12650, "loss": 0.0354, "learning_rate": 9.840894562520565e-05}
+{"step": 12650, "dynamics_loss_avg": 0.03165896749123931}
+{"step": 12650, "action_loss_avg": 0.005011732026468962}
+{"step": 12660, "dynamics_loss_avg": 0.02653435356914997}
+{"step": 12660, "action_loss_avg": 0.0032807684619911015}
+{"step": 12670, "dynamics_loss_avg": 0.04100013989955187}
+{"step": 12670, "action_loss_avg": 0.005624682933557779}
+{"step": 12680, "dynamics_loss_avg": 0.03529616352170706}
+{"step": 12680, "action_loss_avg": 0.005182261206209659}
+{"step": 12690, "dynamics_loss_avg": 0.036455121077597144}
+{"step": 12690, "action_loss_avg": 0.0058691209414973855}
+{"step": 12700, "loss": 0.0365, "learning_rate": 9.838818967102926e-05}
+{"step": 12700, "dynamics_loss_avg": 0.02892579431645572}
+{"step": 12700, "action_loss_avg": 0.003951861837413162}
+{"step": 12710, "dynamics_loss_avg": 0.038263028394430874}
+{"step": 12710, "action_loss_avg": 0.006825318635674193}
+{"step": 12720, "dynamics_loss_avg": 0.037689057271927597}
+{"step": 12720, "action_loss_avg": 0.006589901348343119}
+{"step": 12730, "dynamics_loss_avg": 0.03316250247880816}
+{"step": 12730, "action_loss_avg": 0.005501294566784054}
+{"step": 12740, "dynamics_loss_avg": 0.027335084974765778}
+{"step": 12740, "action_loss_avg": 0.004740265849977732}
+{"step": 12750, "loss": 0.0384, "learning_rate": 9.836730142539001e-05}
+{"step": 12750, "dynamics_loss_avg": 0.037745285965502265}
+{"step": 12750, "action_loss_avg": 0.008102938905358315}
+{"step": 12760, "dynamics_loss_avg": 0.029254859872162343}
+{"step": 12760, "action_loss_avg": 0.004975337302312255}
+{"step": 12770, "dynamics_loss_avg": 0.03286251472309232}
+{"step": 12770, "action_loss_avg": 0.0048010290716774765}
+{"step": 12780, "dynamics_loss_avg": 0.04045389695093036}
+{"step": 12780, "action_loss_avg": 0.007938123284839093}
+{"step": 12790, "dynamics_loss_avg": 0.04207856114953756}
+{"step": 12790, "action_loss_avg": 0.0058030907297506925}
+{"step": 12800, "loss": 0.0379, "learning_rate": 9.834628094539558e-05}
+{"step": 12800, "dynamics_loss_avg": 0.03216870501637459}
+{"step": 12800, "action_loss_avg": 0.004503565921913833}
+{"step": 12810, "dynamics_loss_avg": 0.029674639785662295}
+{"step": 12810, "action_loss_avg": 0.003985867719165981}
+{"step": 12820, "dynamics_loss_avg": 0.02935003410093486}
+{"step": 12820, "action_loss_avg": 0.005150737264193595}
+{"step": 12830, "dynamics_loss_avg": 0.040362862311303614}
+{"step": 12830, "action_loss_avg": 0.0066235682577826084}
+{"step": 12840, "dynamics_loss_avg": 0.039101528190076354}
+{"step": 12840, "action_loss_avg": 0.0056522100698202845}
+{"step": 12850, "loss": 0.0394, "learning_rate": 9.832512828851515e-05}
+{"step": 12850, "dynamics_loss_avg": 0.04528200980275869}
+{"step": 12850, "action_loss_avg": 0.008562332740984857}
+{"step": 12860, "dynamics_loss_avg": 0.02989773442968726}
+{"step": 12860, "action_loss_avg": 0.004477302951272577}
+{"step": 12870, "dynamics_loss_avg": 0.03517071194946766}
+{"step": 12870, "action_loss_avg": 0.005378744169138372}
+{"step": 12880, "dynamics_loss_avg": 0.03201266583055258}
+{"step": 12880, "action_loss_avg": 0.00556783308275044}
+{"step": 12890, "dynamics_loss_avg": 0.04514129776507616}
+{"step": 12890, "action_loss_avg": 0.007431055209599436}
+{"step": 12900, "loss": 0.0402, "learning_rate": 9.830384351257924e-05}
+{"step": 12900, "dynamics_loss_avg": 0.04122246615588665}
+{"step": 12900, "action_loss_avg": 0.006374668935313821}
+{"step": 12910, "dynamics_loss_avg": 0.04462596271187067}
+{"step": 12910, "action_loss_avg": 0.007133987476117909}
+{"step": 12920, "dynamics_loss_avg": 0.03204866545274854}
+{"step": 12920, "action_loss_avg": 0.00552762298611924}
+{"step": 12930, "dynamics_loss_avg": 0.03816991411149502}
+{"step": 12930, "action_loss_avg": 0.006355316424742341}
+{"step": 12940, "dynamics_loss_avg": 0.04197316747158766}
+{"step": 12940, "action_loss_avg": 0.006611978099681437}
+{"step": 12950, "loss": 0.0396, "learning_rate": 9.828242667577966e-05}
+{"step": 12950, "dynamics_loss_avg": 0.05009630471467972}
+{"step": 12950, "action_loss_avg": 0.00883497167378664}
+{"step": 12960, "dynamics_loss_avg": 0.03764502853155136}
+{"step": 12960, "action_loss_avg": 0.00596979537513107}
+{"step": 12970, "dynamics_loss_avg": 0.0470490301027894}
+{"step": 12970, "action_loss_avg": 0.007631211099214852}
+{"step": 12980, "dynamics_loss_avg": 0.03319563576951623}
+{"step": 12980, "action_loss_avg": 0.0037156572216190398}
+{"step": 12990, "dynamics_loss_avg": 0.045242475159466264}
+{"step": 12990, "action_loss_avg": 0.005278283229563386}
+{"step": 13000, "loss": 0.0398, "learning_rate": 9.826087783666921e-05}
+{"step": 13000, "dynamics_loss_avg": 0.03774255532771349}
+{"step": 13000, "action_loss_avg": 0.006210807641036808}
+{"step": 13010, "dynamics_loss_avg": 0.03761772275902331}
+{"step": 13010, "action_loss_avg": 0.004641851497581229}
+{"step": 13020, "dynamics_loss_avg": 0.033998860884457825}
+{"step": 13020, "action_loss_avg": 0.005521625373512506}
+{"step": 13030, "dynamics_loss_avg": 0.033631449844688174}
+{"step": 13030, "action_loss_avg": 0.0053354126051999625}
+{"step": 13040, "dynamics_loss_avg": 0.030703026056289672}
+{"step": 13040, "action_loss_avg": 0.004736506054177881}
+{"step": 13050, "loss": 0.0376, "learning_rate": 9.823919705416158e-05}
+{"step": 13050, "dynamics_loss_avg": 0.03735877359285951}
+{"step": 13050, "action_loss_avg": 0.006222091405652464}
+{"step": 13060, "dynamics_loss_avg": 0.02920526685193181}
+{"step": 13060, "action_loss_avg": 0.0035622343304567037}
+{"step": 13070, "dynamics_loss_avg": 0.037340739741921425}
+{"step": 13070, "action_loss_avg": 0.006527119479142129}
+{"step": 13080, "dynamics_loss_avg": 0.03883154625073075}
+{"step": 13080, "action_loss_avg": 0.0071597081259824336}
+{"step": 13090, "dynamics_loss_avg": 0.044289767183363436}
+{"step": 13090, "action_loss_avg": 0.007550203753635287}
+{"step": 13100, "loss": 0.04, "learning_rate": 9.821738438753123e-05}
+{"step": 13100, "dynamics_loss_avg": 0.031695131491869685}
+{"step": 13100, "action_loss_avg": 0.0037940038717351856}
+{"step": 13110, "dynamics_loss_avg": 0.040602187439799306}
+{"step": 13110, "action_loss_avg": 0.006797695881687105}
+{"step": 13120, "dynamics_loss_avg": 0.03615541653707623}
+{"step": 13120, "action_loss_avg": 0.006768366519827396}
+{"step": 13130, "dynamics_loss_avg": 0.03827003370970487}
+{"step": 13130, "action_loss_avg": 0.00669978023506701}
+{"step": 13140, "dynamics_loss_avg": 0.03397114733234048}
+{"step": 13140, "action_loss_avg": 0.006511193118058145}
+{"step": 13150, "loss": 0.0368, "learning_rate": 9.819543989641314e-05}
+{"step": 13150, "dynamics_loss_avg": 0.029225677810609342}
+{"step": 13150, "action_loss_avg": 0.00459645725786686}
+{"step": 13160, "dynamics_loss_avg": 0.038056248985230925}
+{"step": 13160, "action_loss_avg": 0.004899259889498353}
+{"step": 13170, "dynamics_loss_avg": 0.03338529309257865}
+{"step": 13170, "action_loss_avg": 0.005559557001106441}
+{"step": 13180, "dynamics_loss_avg": 0.02767533529549837}
+{"step": 13180, "action_loss_avg": 0.004174375790171325}
+{"step": 13190, "dynamics_loss_avg": 0.03310908358544111}
+{"step": 13190, "action_loss_avg": 0.006280477927066386}
+{"step": 13200, "loss": 0.0352, "learning_rate": 9.81733636408027e-05}
+{"step": 13200, "dynamics_loss_avg": 0.032490179594606164}
+{"step": 13200, "action_loss_avg": 0.004881730512715876}
+{"step": 13210, "dynamics_loss_avg": 0.02655389830470085}
+{"step": 13210, "action_loss_avg": 0.004198506759712473}
+{"step": 13220, "dynamics_loss_avg": 0.031235984433442353}
+{"step": 13220, "action_loss_avg": 0.004044841893482953}
+{"step": 13230, "dynamics_loss_avg": 0.03209738656878471}
+{"step": 13230, "action_loss_avg": 0.0045513947145082055}
+{"step": 13240, "dynamics_loss_avg": 0.04698696937412024}
+{"step": 13240, "action_loss_avg": 0.007068275101482868}
+{"step": 13250, "loss": 0.0374, "learning_rate": 9.815115568105555e-05}
+{"step": 13250, "dynamics_loss_avg": 0.03479993655346334}
+{"step": 13250, "action_loss_avg": 0.00570291121257469}
+{"step": 13260, "dynamics_loss_avg": 0.02880863696336746}
+{"step": 13260, "action_loss_avg": 0.004621675139060244}
+{"step": 13270, "dynamics_loss_avg": 0.05032922886312008}
+{"step": 13270, "action_loss_avg": 0.0071571089792996645}
+{"step": 13280, "dynamics_loss_avg": 0.030956044048070907}
+{"step": 13280, "action_loss_avg": 0.0037816344760358334}
+{"step": 13290, "dynamics_loss_avg": 0.03347258549183607}
+{"step": 13290, "action_loss_avg": 0.004952497623162344}
+{"step": 13300, "loss": 0.0374, "learning_rate": 9.812881607788744e-05}
+{"step": 13300, "dynamics_loss_avg": 0.037277865875512364}
+{"step": 13300, "action_loss_avg": 0.005695337359793484}
+{"step": 13310, "dynamics_loss_avg": 0.03662647772580385}
+{"step": 13310, "action_loss_avg": 0.004910901887342334}
+{"step": 13320, "dynamics_loss_avg": 0.03190379636362195}
+{"step": 13320, "action_loss_avg": 0.004450708127114922}
+{"step": 13330, "dynamics_loss_avg": 0.030068162456154825}
+{"step": 13330, "action_loss_avg": 0.004840641189366579}
+{"step": 13340, "dynamics_loss_avg": 0.032983715366572144}
+{"step": 13340, "action_loss_avg": 0.006467124004848302}
+{"step": 13350, "loss": 0.0346, "learning_rate": 9.810634489237396e-05}
+{"step": 13350, "dynamics_loss_avg": 0.032432908285409214}
+{"step": 13350, "action_loss_avg": 0.0059096330078318715}
+{"step": 13360, "dynamics_loss_avg": 0.03141539106145501}
+{"step": 13360, "action_loss_avg": 0.004797314386814832}
+{"step": 13370, "dynamics_loss_avg": 0.03621052671223879}
+{"step": 13370, "action_loss_avg": 0.004464255250059068}
+{"step": 13380, "dynamics_loss_avg": 0.029820439778268336}
+{"step": 13380, "action_loss_avg": 0.005493228358682245}
+{"step": 13390, "dynamics_loss_avg": 0.03538095960393548}
+{"step": 13390, "action_loss_avg": 0.004245883622206748}
+{"step": 13400, "loss": 0.0374, "learning_rate": 9.808374218595046e-05}
+{"step": 13400, "dynamics_loss_avg": 0.03312634183093906}
+{"step": 13400, "action_loss_avg": 0.004273592785466462}
+{"step": 13410, "dynamics_loss_avg": 0.03282643277198076}
+{"step": 13410, "action_loss_avg": 0.0051804943941533566}
+{"step": 13420, "dynamics_loss_avg": 0.0411082511767745}
+{"step": 13420, "action_loss_avg": 0.005442834389396012}
+{"step": 13430, "dynamics_loss_avg": 0.03282289039343596}
+{"step": 13430, "action_loss_avg": 0.00499166150111705}
+{"step": 13440, "dynamics_loss_avg": 0.03296192386187613}
+{"step": 13440, "action_loss_avg": 0.004938512924127281}
+{"step": 13450, "loss": 0.0377, "learning_rate": 9.806100802041193e-05}
+{"step": 13450, "dynamics_loss_avg": 0.031582411099225285}
+{"step": 13450, "action_loss_avg": 0.0043934490415267645}
+{"step": 13460, "dynamics_loss_avg": 0.04588839514181018}
+{"step": 13460, "action_loss_avg": 0.007269001338863745}
+{"step": 13470, "dynamics_loss_avg": 0.03143586125224829}
+{"step": 13470, "action_loss_avg": 0.0037292514694854616}
+{"step": 13480, "dynamics_loss_avg": 0.03596693612635136}
+{"step": 13480, "action_loss_avg": 0.006279560242546722}
+{"step": 13490, "dynamics_loss_avg": 0.039717975072562695}
+{"step": 13490, "action_loss_avg": 0.005568609584588558}
+{"step": 13500, "loss": 0.0382, "learning_rate": 9.803814245791265e-05}
+{"step": 13500, "dynamics_loss_avg": 0.037111487798392774}
+{"step": 13500, "action_loss_avg": 0.006094636674970388}
+{"step": 13510, "dynamics_loss_avg": 0.026893809833563865}
+{"step": 13510, "action_loss_avg": 0.004290643520653248}
+{"step": 13520, "dynamics_loss_avg": 0.03024062532931566}
+{"step": 13520, "action_loss_avg": 0.004888758837478235}
+{"step": 13530, "dynamics_loss_avg": 0.0326689450070262}
+{"step": 13530, "action_loss_avg": 0.004579371667932719}
+{"step": 13540, "dynamics_loss_avg": 0.04279630435630679}
+{"step": 13540, "action_loss_avg": 0.0061715437099337574}
+{"step": 13550, "loss": 0.0356, "learning_rate": 9.801514556096625e-05}
+{"step": 13550, "dynamics_loss_avg": 0.042374733835458755}
+{"step": 13550, "action_loss_avg": 0.005849287053570152}
+{"step": 13560, "dynamics_loss_avg": 0.03207614552229643}
+{"step": 13560, "action_loss_avg": 0.0046642081928439435}
+{"step": 13570, "dynamics_loss_avg": 0.046872094925493005}
+{"step": 13570, "action_loss_avg": 0.005305042036343366}
+{"step": 13580, "dynamics_loss_avg": 0.03370549054816365}
+{"step": 13580, "action_loss_avg": 0.004553470632527023}
+{"step": 13590, "dynamics_loss_avg": 0.03622377309948206}
+{"step": 13590, "action_loss_avg": 0.005140110873617232}
+{"step": 13600, "loss": 0.0375, "learning_rate": 9.799201739244532e-05}
+{"step": 13600, "dynamics_loss_avg": 0.023816497111693025}
+{"step": 13600, "action_loss_avg": 0.004034666414372623}
+{"step": 13610, "dynamics_loss_avg": 0.02571533164009452}
+{"step": 13610, "action_loss_avg": 0.003914210293442011}
+{"step": 13620, "dynamics_loss_avg": 0.04590989081189036}
+{"step": 13620, "action_loss_avg": 0.006422012287657708}
+{"step": 13630, "dynamics_loss_avg": 0.03497856836766004}
+{"step": 13630, "action_loss_avg": 0.0045048975152894855}
+{"step": 13640, "dynamics_loss_avg": 0.03698562672361731}
+{"step": 13640, "action_loss_avg": 0.004698184016160667}
+{"step": 13650, "loss": 0.0375, "learning_rate": 9.796875801558141e-05}
+{"step": 13650, "dynamics_loss_avg": 0.04001258192583919}
+{"step": 13650, "action_loss_avg": 0.004955906991381198}
+{"step": 13660, "dynamics_loss_avg": 0.037115632090717554}
+{"step": 13660, "action_loss_avg": 0.005434741533827036}
+{"step": 13670, "dynamics_loss_avg": 0.029833209328353406}
+{"step": 13670, "action_loss_avg": 0.0042489473009482024}
+{"step": 13680, "dynamics_loss_avg": 0.027130670798942446}
+{"step": 13680, "action_loss_avg": 0.0036917828605510295}
+{"step": 13690, "dynamics_loss_avg": 0.02875535227358341}
+{"step": 13690, "action_loss_avg": 0.0037760258186608554}
+{"step": 13700, "loss": 0.0384, "learning_rate": 9.794536749396477e-05}
+{"step": 13700, "dynamics_loss_avg": 0.03143158908933401}
+{"step": 13700, "action_loss_avg": 0.0032402198994532228}
+{"step": 13710, "dynamics_loss_avg": 0.03656509853899479}
+{"step": 13710, "action_loss_avg": 0.004029157268814742}
+{"step": 13720, "dynamics_loss_avg": 0.03764121662825346}
+{"step": 13720, "action_loss_avg": 0.0059934996766969565}
+{"step": 13730, "dynamics_loss_avg": 0.03782629305496812}
+{"step": 13730, "action_loss_avg": 0.0056709385360591115}
+{"step": 13740, "dynamics_loss_avg": 0.028931243508122862}
+{"step": 13740, "action_loss_avg": 0.0037058502726722508}
+{"step": 13750, "loss": 0.0373, "learning_rate": 9.79218458915442e-05}
+{"step": 13750, "dynamics_loss_avg": 0.0391137070953846}
+{"step": 13750, "action_loss_avg": 0.004928267723880708}
+{"step": 13760, "dynamics_loss_avg": 0.03143796948716045}
+{"step": 13760, "action_loss_avg": 0.004034192196559161}
+{"step": 13770, "dynamics_loss_avg": 0.029109062813222408}
+{"step": 13770, "action_loss_avg": 0.0040484359138645235}
+{"step": 13780, "dynamics_loss_avg": 0.02884840564802289}
+{"step": 13780, "action_loss_avg": 0.004151427088072523}
+{"step": 13790, "dynamics_loss_avg": 0.03360795211046934}
+{"step": 13790, "action_loss_avg": 0.005018276814371348}
+{"step": 13800, "loss": 0.0352, "learning_rate": 9.789819327262684e-05}
+{"step": 13800, "dynamics_loss_avg": 0.027930036094039677}
+{"step": 13800, "action_loss_avg": 0.004013299325015396}
+{"step": 13810, "dynamics_loss_avg": 0.03393361046910286}
+{"step": 13810, "action_loss_avg": 0.004880277439951897}
+{"step": 13820, "dynamics_loss_avg": 0.024780479539185763}
+{"step": 13820, "action_loss_avg": 0.0030567369656637313}
+{"step": 13830, "dynamics_loss_avg": 0.030254791397601365}
+{"step": 13830, "action_loss_avg": 0.005194809101521969}
+{"step": 13840, "dynamics_loss_avg": 0.03681231588125229}
+{"step": 13840, "action_loss_avg": 0.005779716745018959}
+{"step": 13850, "loss": 0.0377, "learning_rate": 9.787440970187807e-05}
+{"step": 13850, "dynamics_loss_avg": 0.03437280571088195}
+{"step": 13850, "action_loss_avg": 0.005058410274796188}
+{"step": 13860, "dynamics_loss_avg": 0.029673479590564968}
+{"step": 13860, "action_loss_avg": 0.004211898427456617}
+{"step": 13870, "dynamics_loss_avg": 0.041749306954443455}
+{"step": 13870, "action_loss_avg": 0.00689630713313818}
+{"step": 13880, "dynamics_loss_avg": 0.032761598005890846}
+{"step": 13880, "action_loss_avg": 0.004622413555625826}
+{"step": 13890, "dynamics_loss_avg": 0.046108651999384166}
+{"step": 13890, "action_loss_avg": 0.006187796115409583}
+{"step": 13900, "loss": 0.0377, "learning_rate": 9.785049524432124e-05}
+{"step": 13900, "dynamics_loss_avg": 0.03697648411616683}
+{"step": 13900, "action_loss_avg": 0.00485020448686555}
+{"step": 13910, "dynamics_loss_avg": 0.04374756645411253}
+{"step": 13910, "action_loss_avg": 0.005951303383335471}
+{"step": 13920, "dynamics_loss_avg": 0.029059968888759613}
+{"step": 13920, "action_loss_avg": 0.004158052592538297}
+{"step": 13930, "dynamics_loss_avg": 0.025989691168069838}
+{"step": 13930, "action_loss_avg": 0.004036812880076468}
+{"step": 13940, "dynamics_loss_avg": 0.027700700052082538}
+{"step": 13940, "action_loss_avg": 0.003624559857416898}
+{"step": 13950, "loss": 0.0351, "learning_rate": 9.78264499653376e-05}
+{"step": 13950, "dynamics_loss_avg": 0.03610122138634324}
+{"step": 13950, "action_loss_avg": 0.0060126098804175855}
+{"step": 13960, "dynamics_loss_avg": 0.035392132215201856}
+{"step": 13960, "action_loss_avg": 0.004292215500026941}
+{"step": 13970, "dynamics_loss_avg": 0.030503530614078046}
+{"step": 13970, "action_loss_avg": 0.004266427364200354}
+{"step": 13980, "dynamics_loss_avg": 0.03294017529115081}
+{"step": 13980, "action_loss_avg": 0.003503062971867621}
+{"step": 13990, "dynamics_loss_avg": 0.037420705799013375}
+{"step": 13990, "action_loss_avg": 0.004342146823182702}
+{"step": 14000, "loss": 0.0364, "learning_rate": 9.780227393066599e-05}
+{"step": 14000, "dynamics_loss_avg": 0.027341690938919784}
+{"step": 14000, "action_loss_avg": 0.0030026243184693158}
+{"step": 14010, "dynamics_loss_avg": 0.04223355427384377}
+{"step": 14010, "action_loss_avg": 0.005704913148656487}
+{"step": 14020, "dynamics_loss_avg": 0.032236576359719035}
+{"step": 14020, "action_loss_avg": 0.003007630514912307}
+{"step": 14030, "dynamics_loss_avg": 0.036296904925256966}
+{"step": 14030, "action_loss_avg": 0.004153156653046608}
+{"step": 14040, "dynamics_loss_avg": 0.03291904516518116}
+{"step": 14040, "action_loss_avg": 0.003483116248389706}
+{"step": 14050, "loss": 0.0381, "learning_rate": 9.777796720640277e-05}
+{"step": 14050, "dynamics_loss_avg": 0.03913519885390997}
+{"step": 14050, "action_loss_avg": 0.005351167765911669}
+{"step": 14060, "dynamics_loss_avg": 0.02855334132909775}
+{"step": 14060, "action_loss_avg": 0.005381480057258159}
+{"step": 14070, "dynamics_loss_avg": 0.037696695886552334}
+{"step": 14070, "action_loss_avg": 0.006068194797262549}
+{"step": 14080, "dynamics_loss_avg": 0.03823622493073344}
+{"step": 14080, "action_loss_avg": 0.004891178128309548}
+{"step": 14090, "dynamics_loss_avg": 0.029821677878499032}
+{"step": 14090, "action_loss_avg": 0.0034003006061539055}
+{"step": 14100, "loss": 0.0377, "learning_rate": 9.775352985900163e-05}
+{"step": 14100, "dynamics_loss_avg": 0.03686424847692251}
+{"step": 14100, "action_loss_avg": 0.0057207475882023575}
+{"step": 14110, "dynamics_loss_avg": 0.03066384494304657}
+{"step": 14110, "action_loss_avg": 0.004300586506724357}
+{"step": 14120, "dynamics_loss_avg": 0.028223384730517866}
+{"step": 14120, "action_loss_avg": 0.003680972126312554}
+{"step": 14130, "dynamics_loss_avg": 0.041846674680709836}
+{"step": 14130, "action_loss_avg": 0.005175105575472116}
+{"step": 14140, "dynamics_loss_avg": 0.03468991992995143}
+{"step": 14140, "action_loss_avg": 0.00567951388657093}
+{"step": 14150, "loss": 0.0363, "learning_rate": 9.77289619552733e-05}
+{"step": 14150, "dynamics_loss_avg": 0.02858232082799077}
+{"step": 14150, "action_loss_avg": 0.004443985084071756}
+{"step": 14160, "dynamics_loss_avg": 0.037859623320400715}
+{"step": 14160, "action_loss_avg": 0.0041629636602010574}
+{"step": 14170, "dynamics_loss_avg": 0.027385866828262807}
+{"step": 14170, "action_loss_avg": 0.0037576458882540463}
+{"step": 14180, "dynamics_loss_avg": 0.03848568117246032}
+{"step": 14180, "action_loss_avg": 0.005826148082269356}
+{"step": 14190, "dynamics_loss_avg": 0.04387412499636412}
+{"step": 14190, "action_loss_avg": 0.0062658131355419755}
+{"step": 14200, "loss": 0.0375, "learning_rate": 9.770426356238551e-05}
+{"step": 14200, "dynamics_loss_avg": 0.03342337282374501}
+{"step": 14200, "action_loss_avg": 0.003843877906911075}
+{"step": 14210, "dynamics_loss_avg": 0.042399528156965974}
+{"step": 14210, "action_loss_avg": 0.007695808098651469}
+{"step": 14220, "dynamics_loss_avg": 0.036950991675257686}
+{"step": 14220, "action_loss_avg": 0.005315973446704448}
+{"step": 14230, "dynamics_loss_avg": 0.034702138230204585}
+{"step": 14230, "action_loss_avg": 0.005247254041023552}
+{"step": 14240, "dynamics_loss_avg": 0.029970007203519344}
+{"step": 14240, "action_loss_avg": 0.004496266099158675}
+{"step": 14250, "loss": 0.0379, "learning_rate": 9.767943474786275e-05}
+{"step": 14250, "dynamics_loss_avg": 0.03496443890035152}
+{"step": 14250, "action_loss_avg": 0.004623335145879537}
+{"step": 14260, "dynamics_loss_avg": 0.033652902208268644}
+{"step": 14260, "action_loss_avg": 0.004255929449573159}
+{"step": 14270, "dynamics_loss_avg": 0.04235471095889807}
+{"step": 14270, "action_loss_avg": 0.004842364089563489}
+{"step": 14280, "dynamics_loss_avg": 0.03660476980730891}
+{"step": 14280, "action_loss_avg": 0.003812996903434396}
+{"step": 14290, "dynamics_loss_avg": 0.02315992983058095}
+{"step": 14290, "action_loss_avg": 0.0036260235705412925}
+{"step": 14300, "loss": 0.0362, "learning_rate": 9.765447557958599e-05}
+{"step": 14300, "dynamics_loss_avg": 0.036114335805177686}
+{"step": 14300, "action_loss_avg": 0.005269054137170315}
+{"step": 14310, "dynamics_loss_avg": 0.034833685494959354}
+{"step": 14310, "action_loss_avg": 0.0035807785345241426}
+{"step": 14320, "dynamics_loss_avg": 0.03582093734294176}
+{"step": 14320, "action_loss_avg": 0.005833872850053013}
+{"step": 14330, "dynamics_loss_avg": 0.02599324081093073}
+{"step": 14330, "action_loss_avg": 0.003992400004062801}
+{"step": 14340, "dynamics_loss_avg": 0.04110740888863802}
+{"step": 14340, "action_loss_avg": 0.006015672406647354}
+{"step": 14350, "loss": 0.0384, "learning_rate": 9.762938612579269e-05}
+{"step": 14350, "dynamics_loss_avg": 0.03832197627052665}
+{"step": 14350, "action_loss_avg": 0.005192350316792727}
+{"step": 14360, "dynamics_loss_avg": 0.03275670111179352}
+{"step": 14360, "action_loss_avg": 0.004242479777894914}
+{"step": 14370, "dynamics_loss_avg": 0.04057352095842361}
+{"step": 14370, "action_loss_avg": 0.006258110469207168}
+{"step": 14380, "dynamics_loss_avg": 0.03165127970278263}
+{"step": 14380, "action_loss_avg": 0.00370505464670714}
+{"step": 14390, "dynamics_loss_avg": 0.036076178587973115}
+{"step": 14390, "action_loss_avg": 0.00381162294652313}
+{"step": 14400, "loss": 0.0355, "learning_rate": 9.760416645507644e-05}
+{"step": 14400, "dynamics_loss_avg": 0.023403752781450748}
+{"step": 14400, "action_loss_avg": 0.0031336165557149798}
+{"step": 14410, "dynamics_loss_avg": 0.045301400730386375}
+{"step": 14410, "action_loss_avg": 0.006117197763524018}
+{"step": 14420, "dynamics_loss_avg": 0.03331322642043233}
+{"step": 14420, "action_loss_avg": 0.004291771829593926}
+{"step": 14430, "dynamics_loss_avg": 0.028757483046501876}
+{"step": 14430, "action_loss_avg": 0.005809469881933182}
+{"step": 14440, "dynamics_loss_avg": 0.03263083910569549}
+{"step": 14440, "action_loss_avg": 0.005549067235551775}
+{"step": 14450, "loss": 0.0376, "learning_rate": 9.757881663638688e-05}
+{"step": 14450, "dynamics_loss_avg": 0.03363062581047416}
+{"step": 14450, "action_loss_avg": 0.003947511885780841}
+{"step": 14460, "dynamics_loss_avg": 0.031877079233527186}
+{"step": 14460, "action_loss_avg": 0.004209195077419281}
+{"step": 14470, "dynamics_loss_avg": 0.03418271988630295}
+{"step": 14470, "action_loss_avg": 0.004450076352804899}
+{"step": 14480, "dynamics_loss_avg": 0.0331689853221178}
+{"step": 14480, "action_loss_avg": 0.0049742273055017}
+{"step": 14490, "dynamics_loss_avg": 0.03972893310710788}
+{"step": 14490, "action_loss_avg": 0.007380619971081614}
+{"step": 14500, "loss": 0.0372, "learning_rate": 9.755333673902941e-05}
+{"step": 14500, "dynamics_loss_avg": 0.035242754593491556}
+{"step": 14500, "action_loss_avg": 0.005200596782378853}
+{"step": 14510, "dynamics_loss_avg": 0.04088138286024332}
+{"step": 14510, "action_loss_avg": 0.0069622481008991596}
+{"step": 14520, "dynamics_loss_avg": 0.03896422772668302}
+{"step": 14520, "action_loss_avg": 0.006367800396401435}
+{"step": 14530, "dynamics_loss_avg": 0.04280206607654691}
+{"step": 14530, "action_loss_avg": 0.005497469799593091}
+{"step": 14540, "dynamics_loss_avg": 0.031362781208008526}
+{"step": 14540, "action_loss_avg": 0.0036056185606867077}
+{"step": 14550, "loss": 0.0421, "learning_rate": 9.752772683266512e-05}
+{"step": 14550, "dynamics_loss_avg": 0.03209850080311298}
+{"step": 14550, "action_loss_avg": 0.005107390671037137}
+{"step": 14560, "dynamics_loss_avg": 0.03657142035663128}
+{"step": 14560, "action_loss_avg": 0.0049799852538853885}
+{"step": 14570, "dynamics_loss_avg": 0.02979564443230629}
+{"step": 14570, "action_loss_avg": 0.0042606957315001635}
+{"step": 14580, "dynamics_loss_avg": 0.040001969877630474}
+{"step": 14580, "action_loss_avg": 0.004814205085858702}
+{"step": 14590, "dynamics_loss_avg": 0.033700980618596076}
+{"step": 14590, "action_loss_avg": 0.0047565045766532425}
+{"step": 14600, "loss": 0.0375, "learning_rate": 9.750198698731053e-05}
+{"step": 14600, "dynamics_loss_avg": 0.030876264441758394}
+{"step": 14600, "action_loss_avg": 0.003292262274771929}
+{"step": 14610, "dynamics_loss_avg": 0.03194845374673605}
+{"step": 14610, "action_loss_avg": 0.004256520129274577}
+{"step": 14620, "dynamics_loss_avg": 0.03733065240085125}
+{"step": 14620, "action_loss_avg": 0.005107865238096565}
+{"step": 14630, "dynamics_loss_avg": 0.03372526247985661}
+{"step": 14630, "action_loss_avg": 0.004850813880329952}
+{"step": 14640, "dynamics_loss_avg": 0.05022033154964447}
+{"step": 14640, "action_loss_avg": 0.006764803268015385}
+{"step": 14650, "loss": 0.0394, "learning_rate": 9.747611727333734e-05}
+{"step": 14650, "dynamics_loss_avg": 0.04186561657115817}
+{"step": 14650, "action_loss_avg": 0.005328583018854261}
+{"step": 14660, "dynamics_loss_avg": 0.03294088840484619}
+{"step": 14660, "action_loss_avg": 0.0032854967983439566}
+{"step": 14670, "dynamics_loss_avg": 0.028943984676152466}
+{"step": 14670, "action_loss_avg": 0.004491460719145834}
+{"step": 14680, "dynamics_loss_avg": 0.030631486838683487}
+{"step": 14680, "action_loss_avg": 0.004024290613597259}
+{"step": 14690, "dynamics_loss_avg": 0.03579929461702704}
+{"step": 14690, "action_loss_avg": 0.004810730088502168}
+{"step": 14700, "loss": 0.0371, "learning_rate": 9.745011776147242e-05}
+{"step": 14700, "dynamics_loss_avg": 0.03870975645259023}
+{"step": 14700, "action_loss_avg": 0.004580096807330847}
+{"step": 14710, "dynamics_loss_avg": 0.04091593269258738}
+{"step": 14710, "action_loss_avg": 0.005783696111757308}
+{"step": 14720, "dynamics_loss_avg": 0.028353811893612146}
+{"step": 14720, "action_loss_avg": 0.003512433252763003}
+{"step": 14730, "dynamics_loss_avg": 0.04164166133850813}
+{"step": 14730, "action_loss_avg": 0.005665801023133099}
+{"step": 14740, "dynamics_loss_avg": 0.03802616973407567}
+{"step": 14740, "action_loss_avg": 0.005984812561655417}
+{"step": 14750, "loss": 0.0373, "learning_rate": 9.742398852279741e-05}
+{"step": 14750, "dynamics_loss_avg": 0.033509956952184436}
+{"step": 14750, "action_loss_avg": 0.00542090896051377}
+{"step": 14760, "dynamics_loss_avg": 0.04189440067857504}
+{"step": 14760, "action_loss_avg": 0.005374589655548334}
+{"step": 14770, "dynamics_loss_avg": 0.02518929596990347}
+{"step": 14770, "action_loss_avg": 0.002960364066530019}
+{"step": 14780, "dynamics_loss_avg": 0.03570221681147814}
+{"step": 14780, "action_loss_avg": 0.00537365039344877}
+{"step": 14790, "dynamics_loss_avg": 0.03613399798050523}
+{"step": 14790, "action_loss_avg": 0.005828231229679659}
+{"step": 14800, "loss": 0.0356, "learning_rate": 9.739772962874867e-05}
+{"step": 14800, "dynamics_loss_avg": 0.0350302591919899}
+{"step": 14800, "action_loss_avg": 0.004829426563810557}
+{"step": 14810, "dynamics_loss_avg": 0.025457193795591592}
+{"step": 14810, "action_loss_avg": 0.003178853238932788}
+{"step": 14820, "dynamics_loss_avg": 0.03349962318316102}
+{"step": 14820, "action_loss_avg": 0.0037184703280217944}
+{"step": 14830, "dynamics_loss_avg": 0.035672693885862826}
+{"step": 14830, "action_loss_avg": 0.003944253269582987}
+{"step": 14840, "dynamics_loss_avg": 0.03728302801027894}
+{"step": 14840, "action_loss_avg": 0.0046149125089868905}
+{"step": 14850, "loss": 0.0369, "learning_rate": 9.737134115111699e-05}
+{"step": 14850, "dynamics_loss_avg": 0.034742768947035076}
+{"step": 14850, "action_loss_avg": 0.004754625586792826}
+{"step": 14860, "dynamics_loss_avg": 0.03318012012168765}
+{"step": 14860, "action_loss_avg": 0.003375386301195249}
+{"step": 14870, "dynamics_loss_avg": 0.04015296939760447}
+{"step": 14870, "action_loss_avg": 0.006106985511723906}
+{"step": 14880, "dynamics_loss_avg": 0.033529809303581716}
+{"step": 14880, "action_loss_avg": 0.003878561337478459}
+{"step": 14890, "dynamics_loss_avg": 0.025254884921014308}
+{"step": 14890, "action_loss_avg": 0.0032766986754722894}
+{"step": 14900, "loss": 0.0351, "learning_rate": 9.734482316204747e-05}
+{"step": 14900, "dynamics_loss_avg": 0.0286707597784698}
+{"step": 14900, "action_loss_avg": 0.0039050075341947378}
+{"step": 14910, "dynamics_loss_avg": 0.03413341669365764}
+{"step": 14910, "action_loss_avg": 0.004601994412951171}
+{"step": 14920, "dynamics_loss_avg": 0.03859848696738481}
+{"step": 14920, "action_loss_avg": 0.005778776435181499}
+{"step": 14930, "dynamics_loss_avg": 0.03904609438031912}
+{"step": 14930, "action_loss_avg": 0.004646328487433493}
+{"step": 14940, "dynamics_loss_avg": 0.04722803588956594}
+{"step": 14940, "action_loss_avg": 0.00517613475676626}
+{"step": 14950, "loss": 0.0398, "learning_rate": 9.731817573403929e-05}
+{"step": 14950, "dynamics_loss_avg": 0.034516450855880974}
+{"step": 14950, "action_loss_avg": 0.003928524896036833}
+{"step": 14960, "dynamics_loss_avg": 0.035198590252548456}
+{"step": 14960, "action_loss_avg": 0.004661021591164172}
+{"step": 14970, "dynamics_loss_avg": 0.038246468640863895}
+{"step": 14970, "action_loss_avg": 0.004933976486790925}
+{"step": 14980, "dynamics_loss_avg": 0.036115489527583124}
+{"step": 14980, "action_loss_avg": 0.004457582603208721}
+{"step": 14990, "dynamics_loss_avg": 0.04234340060502291}
+{"step": 14990, "action_loss_avg": 0.005363197065889835}
+{"step": 15000, "loss": 0.0393, "learning_rate": 9.72913989399455e-05}
+{"step": 15000, "dynamics_loss_avg": 0.03436379497870803}
+{"step": 15000, "action_loss_avg": 0.004766017105430365}
+{"step": 15010, "dynamics_loss_avg": 0.030173102114349603}
+{"step": 15010, "action_loss_avg": 0.003650437144096941}
+{"step": 15020, "dynamics_loss_avg": 0.04302677158266306}
+{"step": 15020, "action_loss_avg": 0.005735334230121225}
+{"step": 15030, "dynamics_loss_avg": 0.03305801413953304}
+{"step": 15030, "action_loss_avg": 0.0041351490071974695}
+{"step": 15040, "dynamics_loss_avg": 0.03021344365552068}
+{"step": 15040, "action_loss_avg": 0.004164856276474893}
+{"step": 15050, "loss": 0.036, "learning_rate": 9.726449285297281e-05}
+{"step": 15050, "dynamics_loss_avg": 0.033627238729968666}
+{"step": 15050, "action_loss_avg": 0.0035833735310006887}
+{"step": 15060, "dynamics_loss_avg": 0.028602742683142425}
+{"step": 15060, "action_loss_avg": 0.003199885378126055}
+{"step": 15070, "dynamics_loss_avg": 0.02224083188921213}
+{"step": 15070, "action_loss_avg": 0.004201761574950069}
+{"step": 15080, "dynamics_loss_avg": 0.031242089252918957}
+{"step": 15080, "action_loss_avg": 0.005301171191968023}
+{"step": 15090, "dynamics_loss_avg": 0.03359739650040865}
+{"step": 15090, "action_loss_avg": 0.004421331547200679}
+{"step": 15100, "loss": 0.0325, "learning_rate": 9.723745754668147e-05}
+{"step": 15100, "dynamics_loss_avg": 0.03098901817575097}
+{"step": 15100, "action_loss_avg": 0.003545618453063071}
+{"step": 15110, "dynamics_loss_avg": 0.029968789685517548}
+{"step": 15110, "action_loss_avg": 0.004255804233253002}
+{"step": 15120, "dynamics_loss_avg": 0.0344080304261297}
+{"step": 15120, "action_loss_avg": 0.004699218212044798}
+{"step": 15130, "dynamics_loss_avg": 0.03492920305579901}
+{"step": 15130, "action_loss_avg": 0.004813673975877464}
+{"step": 15140, "dynamics_loss_avg": 0.03730620834976435}
+{"step": 15140, "action_loss_avg": 0.0047035094234161075}
+{"step": 15150, "loss": 0.0371, "learning_rate": 9.721029309498494e-05}
+{"step": 15150, "dynamics_loss_avg": 0.03081887811422348}
+{"step": 15150, "action_loss_avg": 0.0038013910641893746}
+{"step": 15160, "dynamics_loss_avg": 0.028581718634814023}
+{"step": 15160, "action_loss_avg": 0.003730502910912037}
+{"step": 15170, "dynamics_loss_avg": 0.042947563156485555}
+{"step": 15170, "action_loss_avg": 0.005717509717214853}
+{"step": 15180, "dynamics_loss_avg": 0.03568523600697517}
+{"step": 15180, "action_loss_avg": 0.003979606321081519}
+{"step": 15190, "dynamics_loss_avg": 0.03831081008538604}
+{"step": 15190, "action_loss_avg": 0.004675715696066618}
+{"step": 15200, "loss": 0.0347, "learning_rate": 9.718299957214982e-05}
+{"step": 15200, "dynamics_loss_avg": 0.03143490757793188}
+{"step": 15200, "action_loss_avg": 0.003866184363141656}
+{"step": 15210, "dynamics_loss_avg": 0.027586713340133427}
+{"step": 15210, "action_loss_avg": 0.004788048751652241}
+{"step": 15220, "dynamics_loss_avg": 0.03476726291701197}
+{"step": 15220, "action_loss_avg": 0.005529422359541058}
+{"step": 15230, "dynamics_loss_avg": 0.03208005102351308}
+{"step": 15230, "action_loss_avg": 0.004769302310887724}
+{"step": 15240, "dynamics_loss_avg": 0.031316626071929934}
+{"step": 15240, "action_loss_avg": 0.004445669869892299}
+{"step": 15250, "loss": 0.0354, "learning_rate": 9.715557705279555e-05}
+{"step": 15250, "dynamics_loss_avg": 0.033847618103027347}
+{"step": 15250, "action_loss_avg": 0.005663468805141747}
+{"step": 15260, "dynamics_loss_avg": 0.03530843909829855}
+{"step": 15260, "action_loss_avg": 0.003978712169919163}
+{"step": 15270, "dynamics_loss_avg": 0.039312949404120445}
+{"step": 15270, "action_loss_avg": 0.006233601435087621}
+{"step": 15280, "dynamics_loss_avg": 0.03477133954875171}
+{"step": 15280, "action_loss_avg": 0.004480262711877003}
+{"step": 15290, "dynamics_loss_avg": 0.03485710695385933}
+{"step": 15290, "action_loss_avg": 0.004678648873232305}
+{"step": 15300, "loss": 0.037, "learning_rate": 9.712802561189422e-05}
+{"step": 15300, "dynamics_loss_avg": 0.03326199166476727}
+{"step": 15300, "action_loss_avg": 0.003412028611637652}
+{"step": 15310, "dynamics_loss_avg": 0.03130198195576668}
+{"step": 15310, "action_loss_avg": 0.004160161811159924}
+{"step": 15320, "dynamics_loss_avg": 0.031938216835260394}
+{"step": 15320, "action_loss_avg": 0.004430908214999363}
+{"step": 15330, "dynamics_loss_avg": 0.032450398709625}
+{"step": 15330, "action_loss_avg": 0.004852707672398537}
+{"step": 15340, "dynamics_loss_avg": 0.02649425361305475}
+{"step": 15340, "action_loss_avg": 0.0028259511687792837}
+{"step": 15350, "loss": 0.0321, "learning_rate": 9.710034532477048e-05}
+{"step": 15350, "dynamics_loss_avg": 0.02779070781543851}
+{"step": 15350, "action_loss_avg": 0.004851542715914548}
+{"step": 15360, "dynamics_loss_avg": 0.030763224838301538}
+{"step": 15360, "action_loss_avg": 0.004544403834734112}
+{"step": 15370, "dynamics_loss_avg": 0.030141972191631793}
+{"step": 15370, "action_loss_avg": 0.003919900231994689}
+{"step": 15380, "dynamics_loss_avg": 0.03753236224874854}
+{"step": 15380, "action_loss_avg": 0.005142860126215965}
+{"step": 15390, "dynamics_loss_avg": 0.03690798496827483}
+{"step": 15390, "action_loss_avg": 0.005342959403060376}
+{"step": 15400, "loss": 0.0363, "learning_rate": 9.707253626710113e-05}
+{"step": 15400, "dynamics_loss_avg": 0.025830339826643466}
+{"step": 15400, "action_loss_avg": 0.0041096207918599244}
+{"step": 15410, "dynamics_loss_avg": 0.0307837488129735}
+{"step": 15410, "action_loss_avg": 0.004185339889954775}
+{"step": 15420, "dynamics_loss_avg": 0.046420044638216494}
+{"step": 15420, "action_loss_avg": 0.006025147705804557}
+{"step": 15430, "dynamics_loss_avg": 0.02887270334176719}
+{"step": 15430, "action_loss_avg": 0.003497642552247271}
+{"step": 15440, "dynamics_loss_avg": 0.03265869552269578}
+{"step": 15440, "action_loss_avg": 0.004379557655192911}
+{"step": 15450, "loss": 0.0377, "learning_rate": 9.704459851491508e-05}
+{"step": 15450, "dynamics_loss_avg": 0.03366679958999157}
+{"step": 15450, "action_loss_avg": 0.004606218030676246}
+{"step": 15460, "dynamics_loss_avg": 0.042012097872793676}
+{"step": 15460, "action_loss_avg": 0.005732963606715202}
+{"step": 15470, "dynamics_loss_avg": 0.02789494888857007}
+{"step": 15470, "action_loss_avg": 0.0037518557743169366}
+{"step": 15480, "dynamics_loss_avg": 0.029611847922205926}
+{"step": 15480, "action_loss_avg": 0.00394027897855267}
+{"step": 15490, "dynamics_loss_avg": 0.03622891865670681}
+{"step": 15490, "action_loss_avg": 0.004437408642843366}
+{"step": 15500, "loss": 0.0376, "learning_rate": 9.701653214459309e-05}
+{"step": 15500, "dynamics_loss_avg": 0.035120685771107676}
+{"step": 15500, "action_loss_avg": 0.004163906478788703}
+{"step": 15510, "dynamics_loss_avg": 0.0321755075827241}
+{"step": 15510, "action_loss_avg": 0.004537018982227891}
+{"step": 15520, "dynamics_loss_avg": 0.045351735688745974}
+{"step": 15520, "action_loss_avg": 0.006171673140488565}
+{"step": 15530, "dynamics_loss_avg": 0.035380068235099316}
+{"step": 15530, "action_loss_avg": 0.005400100396946073}
+{"step": 15540, "dynamics_loss_avg": 0.029709333879873158}
+{"step": 15540, "action_loss_avg": 0.004216810228535905}
+{"step": 15550, "loss": 0.0366, "learning_rate": 9.698833723286753e-05}
+{"step": 15550, "dynamics_loss_avg": 0.023986828979104757}
+{"step": 15550, "action_loss_avg": 0.003157524298876524}
+{"step": 15560, "dynamics_loss_avg": 0.034734612051397565}
+{"step": 15560, "action_loss_avg": 0.004253664740826934}
+{"step": 15570, "dynamics_loss_avg": 0.03803477715700865}
+{"step": 15570, "action_loss_avg": 0.004097137763164937}
+{"step": 15580, "dynamics_loss_avg": 0.028216728661209344}
+{"step": 15580, "action_loss_avg": 0.003645819122903049}
+{"step": 15590, "dynamics_loss_avg": 0.03063159454613924}
+{"step": 15590, "action_loss_avg": 0.0034407773229759185}
+{"step": 15600, "loss": 0.0366, "learning_rate": 9.696001385682223e-05}
+{"step": 15600, "dynamics_loss_avg": 0.02579979207366705}
+{"step": 15600, "action_loss_avg": 0.004042802745243534}
+{"step": 15610, "dynamics_loss_avg": 0.03539964705705643}
+{"step": 15610, "action_loss_avg": 0.004308499477338046}
+{"step": 15620, "dynamics_loss_avg": 0.0411580546759069}
+{"step": 15620, "action_loss_avg": 0.0054534444818273185}
+{"step": 15630, "dynamics_loss_avg": 0.03721490176394582}
+{"step": 15630, "action_loss_avg": 0.005813477316405624}
+{"step": 15640, "dynamics_loss_avg": 0.030722552631050348}
+{"step": 15640, "action_loss_avg": 0.0041091686929576095}
+{"step": 15650, "loss": 0.0373, "learning_rate": 9.693156209389221e-05}
+{"step": 15650, "dynamics_loss_avg": 0.03511948543600738}
+{"step": 15650, "action_loss_avg": 0.004389171011280268}
+{"step": 15660, "dynamics_loss_avg": 0.02288767360150814}
+{"step": 15660, "action_loss_avg": 0.003031716909026727}
+{"step": 15670, "dynamics_loss_avg": 0.043410996068269016}
+{"step": 15670, "action_loss_avg": 0.004790060326922685}
+{"step": 15680, "dynamics_loss_avg": 0.02706330893561244}
+{"step": 15680, "action_loss_avg": 0.002992127853212878}
+{"step": 15690, "dynamics_loss_avg": 0.04133646823465824}
+{"step": 15690, "action_loss_avg": 0.004807365906890482}
+{"step": 15700, "loss": 0.0358, "learning_rate": 9.69029820218635e-05}
+{"step": 15700, "dynamics_loss_avg": 0.029523919429630043}
+{"step": 15700, "action_loss_avg": 0.004489910177653655}
+{"step": 15710, "dynamics_loss_avg": 0.0355068601667881}
+{"step": 15710, "action_loss_avg": 0.004395273234695196}
+{"step": 15720, "dynamics_loss_avg": 0.03679166324436665}
+{"step": 15720, "action_loss_avg": 0.004869647696614266}
+{"step": 15730, "dynamics_loss_avg": 0.032604781724512574}
+{"step": 15730, "action_loss_avg": 0.003840847738320008}
+{"step": 15740, "dynamics_loss_avg": 0.02602613177150488}
+{"step": 15740, "action_loss_avg": 0.0043298779695760455}
+{"step": 15750, "loss": 0.0335, "learning_rate": 9.687427371887293e-05}
+{"step": 15750, "dynamics_loss_avg": 0.029212245857343076}
+{"step": 15750, "action_loss_avg": 0.004032132343854755}
+{"step": 15760, "dynamics_loss_avg": 0.038684130273759366}
+{"step": 15760, "action_loss_avg": 0.004514608543831855}
+{"step": 15770, "dynamics_loss_avg": 0.027062665298581125}
+{"step": 15770, "action_loss_avg": 0.003812852478586137}
+{"step": 15780, "dynamics_loss_avg": 0.03934922963380814}
+{"step": 15780, "action_loss_avg": 0.0033295419765636326}
+{"step": 15790, "dynamics_loss_avg": 0.038438393734395504}
+{"step": 15790, "action_loss_avg": 0.004989390447735787}
+{"step": 15800, "loss": 0.0363, "learning_rate": 9.684543726340791e-05}
+{"step": 15800, "dynamics_loss_avg": 0.036514440458267926}
+{"step": 15800, "action_loss_avg": 0.005359360994771123}
+{"step": 15810, "dynamics_loss_avg": 0.04159977789968252}
+{"step": 15810, "action_loss_avg": 0.0044080766499973835}
+{"step": 15820, "dynamics_loss_avg": 0.030919601488858462}
+{"step": 15820, "action_loss_avg": 0.0042767611797899}
+{"step": 15830, "dynamics_loss_avg": 0.032151123508811}
+{"step": 15830, "action_loss_avg": 0.004167978069745004}
+{"step": 15840, "dynamics_loss_avg": 0.0401014163158834}
+{"step": 15840, "action_loss_avg": 0.004344502079766244}
+{"step": 15850, "loss": 0.0353, "learning_rate": 9.681647273430618e-05}
+{"step": 15850, "dynamics_loss_avg": 0.0335140623152256}
+{"step": 15850, "action_loss_avg": 0.0042038984596729275}
+{"step": 15860, "dynamics_loss_avg": 0.030633509811013936}
+{"step": 15860, "action_loss_avg": 0.004417951975483447}
+{"step": 15870, "dynamics_loss_avg": 0.03570272978395224}
+{"step": 15870, "action_loss_avg": 0.004766518203541637}
+{"step": 15880, "dynamics_loss_avg": 0.026700234320014716}
+{"step": 15880, "action_loss_avg": 0.0035539073986001314}
+{"step": 15890, "dynamics_loss_avg": 0.03914800891652703}
+{"step": 15890, "action_loss_avg": 0.005073586793150753}
+{"step": 15900, "loss": 0.0366, "learning_rate": 9.67873802107557e-05}
+{"step": 15900, "dynamics_loss_avg": 0.028504143003374338}
+{"step": 15900, "action_loss_avg": 0.004682767414487898}
+{"step": 15910, "dynamics_loss_avg": 0.028624470345675945}
+{"step": 15910, "action_loss_avg": 0.004405791306635365}
+{"step": 15920, "dynamics_loss_avg": 0.03541062083095312}
+{"step": 15920, "action_loss_avg": 0.003978491178713739}
+{"step": 15930, "dynamics_loss_avg": 0.030608739983290435}
+{"step": 15930, "action_loss_avg": 0.0037369216326624153}
+{"step": 15940, "dynamics_loss_avg": 0.03744756784290075}
+{"step": 15940, "action_loss_avg": 0.0047156497952528294}
+{"step": 15950, "loss": 0.0386, "learning_rate": 9.675815977229428e-05}
+{"step": 15950, "dynamics_loss_avg": 0.04333013743162155}
+{"step": 15950, "action_loss_avg": 0.00475337200332433}
+{"step": 15960, "dynamics_loss_avg": 0.033992264326661824}
+{"step": 15960, "action_loss_avg": 0.004396585741778836}
+{"step": 15970, "dynamics_loss_avg": 0.030096640903502704}
+{"step": 15970, "action_loss_avg": 0.00450835432857275}
+{"step": 15980, "dynamics_loss_avg": 0.028472135961055755}
+{"step": 15980, "action_loss_avg": 0.004500157118309289}
+{"step": 15990, "dynamics_loss_avg": 0.03191729299724102}
+{"step": 15990, "action_loss_avg": 0.0042330964643042535}
+{"step": 16000, "loss": 0.0313, "learning_rate": 9.67288114988095e-05}
+{"step": 16000, "dynamics_loss_avg": 0.033419133722782136}
+{"step": 16000, "action_loss_avg": 0.0048628138960339126}
+{"step": 16010, "dynamics_loss_avg": 0.03985829334706068}
+{"step": 16010, "action_loss_avg": 0.005583540280349552}
+{"step": 16020, "dynamics_loss_avg": 0.035209689475595954}
+{"step": 16020, "action_loss_avg": 0.00455159650882706}
+{"step": 16030, "dynamics_loss_avg": 0.03557337028905749}
+{"step": 16030, "action_loss_avg": 0.004412569594569505}
+{"step": 16040, "dynamics_loss_avg": 0.033344331104308365}
+{"step": 16040, "action_loss_avg": 0.0044180733850225805}
+{"step": 16050, "loss": 0.0392, "learning_rate": 9.669933547053842e-05}
+{"step": 16050, "dynamics_loss_avg": 0.032325828541070224}
+{"step": 16050, "action_loss_avg": 0.003692854556720704}
+{"step": 16060, "dynamics_loss_avg": 0.036713172867894175}
+{"step": 16060, "action_loss_avg": 0.0035879645613022147}
+{"step": 16070, "dynamics_loss_avg": 0.03149562906473875}
+{"step": 16070, "action_loss_avg": 0.004188787005841732}
+{"step": 16080, "dynamics_loss_avg": 0.03896331302821636}
+{"step": 16080, "action_loss_avg": 0.00521829801145941}
+{"step": 16090, "dynamics_loss_avg": 0.030817566439509392}
+{"step": 16090, "action_loss_avg": 0.003566255257464945}
+{"step": 16100, "loss": 0.0355, "learning_rate": 9.666973176806737e-05}
+{"step": 16100, "dynamics_loss_avg": 0.0255312561057508}
+{"step": 16100, "action_loss_avg": 0.003756167780375108}
+{"step": 16110, "dynamics_loss_avg": 0.026084317825734615}
+{"step": 16110, "action_loss_avg": 0.00347259413683787}
+{"step": 16120, "dynamics_loss_avg": 0.03621761631220579}
+{"step": 16120, "action_loss_avg": 0.0051158963236957785}
+{"step": 16130, "dynamics_loss_avg": 0.039985375665128234}
+{"step": 16130, "action_loss_avg": 0.004889450804330409}
+{"step": 16140, "dynamics_loss_avg": 0.03130345516838133}
+{"step": 16140, "action_loss_avg": 0.004417429340537638}
+{"step": 16150, "loss": 0.0355, "learning_rate": 9.664000047233175e-05}
+{"step": 16150, "dynamics_loss_avg": 0.030249025393277406}
+{"step": 16150, "action_loss_avg": 0.004557379719335586}
+{"step": 16160, "dynamics_loss_avg": 0.024825412034988403}
+{"step": 16160, "action_loss_avg": 0.0036414187867194413}
+{"step": 16170, "dynamics_loss_avg": 0.03646038565784693}
+{"step": 16170, "action_loss_avg": 0.004531711910385638}
+{"step": 16180, "dynamics_loss_avg": 0.034318009950220586}
+{"step": 16180, "action_loss_avg": 0.004494209925178438}
+{"step": 16190, "dynamics_loss_avg": 0.03633828582242131}
+{"step": 16190, "action_loss_avg": 0.0058983589056879285}
+{"step": 16200, "loss": 0.0358, "learning_rate": 9.661014166461579e-05}
+{"step": 16200, "dynamics_loss_avg": 0.02755392426624894}
+{"step": 16200, "action_loss_avg": 0.004295567271765321}
+{"step": 16210, "dynamics_loss_avg": 0.035331463906913996}
+{"step": 16210, "action_loss_avg": 0.005213667138013989}
+{"step": 16220, "dynamics_loss_avg": 0.036249918211251494}
+{"step": 16220, "action_loss_avg": 0.005016646557487547}
+{"step": 16230, "dynamics_loss_avg": 0.04150620130822062}
+{"step": 16230, "action_loss_avg": 0.004837025643792003}
+{"step": 16240, "dynamics_loss_avg": 0.02999339010566473}
+{"step": 16240, "action_loss_avg": 0.0029794157133437695}
+{"step": 16250, "loss": 0.0361, "learning_rate": 9.65801554265523e-05}
+{"step": 16250, "dynamics_loss_avg": 0.025842866580933332}
+{"step": 16250, "action_loss_avg": 0.0030044114799238743}
+{"step": 16260, "dynamics_loss_avg": 0.03615312911570072}
+{"step": 16260, "action_loss_avg": 0.004391211585607379}
+{"step": 16270, "dynamics_loss_avg": 0.031978354696184395}
+{"step": 16270, "action_loss_avg": 0.003276017343159765}
+{"step": 16280, "dynamics_loss_avg": 0.040224809944629666}
+{"step": 16280, "action_loss_avg": 0.00511045241728425}
+{"step": 16290, "dynamics_loss_avg": 0.0352611381560564}
+{"step": 16290, "action_loss_avg": 0.004033984581474215}
+{"step": 16300, "loss": 0.0371, "learning_rate": 9.655004184012256e-05}
+{"step": 16300, "dynamics_loss_avg": 0.032097651110962036}
+{"step": 16300, "action_loss_avg": 0.004121904680505395}
+{"step": 16310, "dynamics_loss_avg": 0.035806198976933955}
+{"step": 16310, "action_loss_avg": 0.0050675553153269}
+{"step": 16320, "dynamics_loss_avg": 0.0335924525745213}
+{"step": 16320, "action_loss_avg": 0.003749097470426932}
+{"step": 16330, "dynamics_loss_avg": 0.04156769635155797}
+{"step": 16330, "action_loss_avg": 0.005606241943314672}
+{"step": 16340, "dynamics_loss_avg": 0.03807919416576624}
+{"step": 16340, "action_loss_avg": 0.005268633924424648}
+{"step": 16350, "loss": 0.0387, "learning_rate": 9.651980098765591e-05}
+{"step": 16350, "dynamics_loss_avg": 0.029665537318214773}
+{"step": 16350, "action_loss_avg": 0.004673253043438308}
+{"step": 16360, "dynamics_loss_avg": 0.027403287356719375}
+{"step": 16360, "action_loss_avg": 0.0036452173022553324}
+{"step": 16370, "dynamics_loss_avg": 0.03385364287532866}
+{"step": 16370, "action_loss_avg": 0.004357027355581522}
+{"step": 16380, "dynamics_loss_avg": 0.029235827177762984}
+{"step": 16380, "action_loss_avg": 0.003351198532618582}
+{"step": 16390, "dynamics_loss_avg": 0.032798868231475355}
+{"step": 16390, "action_loss_avg": 0.003747315215878189}
+{"step": 16400, "loss": 0.035, "learning_rate": 9.648943295182973e-05}
+{"step": 16400, "dynamics_loss_avg": 0.02871994082815945}
+{"step": 16400, "action_loss_avg": 0.004370694444514811}
+{"step": 16410, "dynamics_loss_avg": 0.03674743659794331}
+{"step": 16410, "action_loss_avg": 0.004281880031339824}
+{"step": 16420, "dynamics_loss_avg": 0.029849438462406397}
+{"step": 16420, "action_loss_avg": 0.004024095612112433}
+{"step": 16430, "dynamics_loss_avg": 0.030676854914054273}
+{"step": 16430, "action_loss_avg": 0.0044219414878170936}
+{"step": 16440, "dynamics_loss_avg": 0.041102593671530484}
+{"step": 16440, "action_loss_avg": 0.005622584943193942}
+{"step": 16450, "loss": 0.0375, "learning_rate": 9.645893781566907e-05}
+{"step": 16450, "dynamics_loss_avg": 0.041480194218456744}
+{"step": 16450, "action_loss_avg": 0.0055402737809345124}
+{"step": 16460, "dynamics_loss_avg": 0.02497711256146431}
+{"step": 16460, "action_loss_avg": 0.0026509677525609733}
+{"step": 16470, "dynamics_loss_avg": 0.035998709872364996}
+{"step": 16470, "action_loss_avg": 0.00529723062645644}
+{"step": 16480, "dynamics_loss_avg": 0.04117559976875782}
+{"step": 16480, "action_loss_avg": 0.0050563301192596555}
+{"step": 16490, "dynamics_loss_avg": 0.03932575099170208}
+{"step": 16490, "action_loss_avg": 0.005916879163123667}
+{"step": 16500, "loss": 0.0378, "learning_rate": 9.642831566254641e-05}
+{"step": 16500, "dynamics_loss_avg": 0.035921369772404434}
+{"step": 16500, "action_loss_avg": 0.004287866503000259}
+{"step": 16510, "dynamics_loss_avg": 0.02655516527593136}
+{"step": 16510, "action_loss_avg": 0.0034579844679683445}
+{"step": 16520, "dynamics_loss_avg": 0.03081397609785199}
+{"step": 16520, "action_loss_avg": 0.003996176784858108}
+{"step": 16530, "dynamics_loss_avg": 0.028000471368432044}
+{"step": 16530, "action_loss_avg": 0.002959096111590043}
+{"step": 16540, "dynamics_loss_avg": 0.03051546439528465}
+{"step": 16540, "action_loss_avg": 0.0032520733773708345}
+{"step": 16550, "loss": 0.0331, "learning_rate": 9.639756657618162e-05}
+{"step": 16550, "dynamics_loss_avg": 0.032843503076583146}
+{"step": 16550, "action_loss_avg": 0.003928262647241354}
+{"step": 16560, "dynamics_loss_avg": 0.03592627784237266}
+{"step": 16560, "action_loss_avg": 0.0048644644557498395}
+{"step": 16570, "dynamics_loss_avg": 0.034083899669349195}
+{"step": 16570, "action_loss_avg": 0.004968166374601424}
+{"step": 16580, "dynamics_loss_avg": 0.027710394095629455}
+{"step": 16580, "action_loss_avg": 0.004081078612944111}
+{"step": 16590, "dynamics_loss_avg": 0.031172771751880646}
+{"step": 16590, "action_loss_avg": 0.005636746541131288}
+{"step": 16600, "loss": 0.0328, "learning_rate": 9.63666906406415e-05}
+{"step": 16600, "dynamics_loss_avg": 0.031170352082699537}
+{"step": 16600, "action_loss_avg": 0.003665776422712952}
+{"step": 16610, "dynamics_loss_avg": 0.03499247608706355}
+{"step": 16610, "action_loss_avg": 0.0045730031910352405}
+{"step": 16620, "dynamics_loss_avg": 0.02972412873059511}
+{"step": 16620, "action_loss_avg": 0.004196647758362815}
+{"step": 16630, "dynamics_loss_avg": 0.045307276956737044}
+{"step": 16630, "action_loss_avg": 0.006081011076457798}
+{"step": 16640, "dynamics_loss_avg": 0.02329785469919443}
+{"step": 16640, "action_loss_avg": 0.0025420990656130015}
+{"step": 16650, "loss": 0.0368, "learning_rate": 9.633568794033967e-05}
+{"step": 16650, "dynamics_loss_avg": 0.04125182125717401}
+{"step": 16650, "action_loss_avg": 0.006249363697133958}
+{"step": 16660, "dynamics_loss_avg": 0.03140751738101244}
+{"step": 16660, "action_loss_avg": 0.004268089646939188}
+{"step": 16670, "dynamics_loss_avg": 0.028196881618350746}
+{"step": 16670, "action_loss_avg": 0.002523967664455995}
+{"step": 16680, "dynamics_loss_avg": 0.03326290287077427}
+{"step": 16680, "action_loss_avg": 0.004151747119612992}
+{"step": 16690, "dynamics_loss_avg": 0.035345795936882494}
+{"step": 16690, "action_loss_avg": 0.0053719218587502835}
+{"step": 16700, "loss": 0.0354, "learning_rate": 9.630455856003632e-05}
+{"step": 16700, "dynamics_loss_avg": 0.022341008856892587}
+{"step": 16700, "action_loss_avg": 0.002420858043478802}
+{"step": 16710, "dynamics_loss_avg": 0.041393944155424835}
+{"step": 16710, "action_loss_avg": 0.007061217114096507}
+{"step": 16720, "dynamics_loss_avg": 0.028006640356034042}
+{"step": 16720, "action_loss_avg": 0.0047683525830507275}
+{"step": 16730, "dynamics_loss_avg": 0.03477255385369062}
+{"step": 16730, "action_loss_avg": 0.004428167530568317}
+{"step": 16740, "dynamics_loss_avg": 0.04173089042305946}
+{"step": 16740, "action_loss_avg": 0.004723396839108318}
+{"step": 16750, "loss": 0.0346, "learning_rate": 9.627330258483802e-05}
+{"step": 16750, "dynamics_loss_avg": 0.033611226547509435}
+{"step": 16750, "action_loss_avg": 0.0052893809275701646}
+{"step": 16760, "dynamics_loss_avg": 0.03532201964408159}
+{"step": 16760, "action_loss_avg": 0.004232311272062361}
+{"step": 16770, "dynamics_loss_avg": 0.029826111067086457}
+{"step": 16770, "action_loss_avg": 0.004586470872163772}
+{"step": 16780, "dynamics_loss_avg": 0.034959566034376624}
+{"step": 16780, "action_loss_avg": 0.003725108411163092}
+{"step": 16790, "dynamics_loss_avg": 0.03455255515873432}
+{"step": 16790, "action_loss_avg": 0.004134328709915281}
+{"step": 16800, "loss": 0.0351, "learning_rate": 9.62419201001974e-05}
+{"step": 16800, "dynamics_loss_avg": 0.03291602414101362}
+{"step": 16800, "action_loss_avg": 0.0037643967429175974}
+{"step": 16810, "dynamics_loss_avg": 0.028822576999664305}
+{"step": 16810, "action_loss_avg": 0.0037180125364102423}
+{"step": 16820, "dynamics_loss_avg": 0.030638551525771617}
+{"step": 16820, "action_loss_avg": 0.004423194006085396}
+{"step": 16830, "dynamics_loss_avg": 0.03611736372113228}
+{"step": 16830, "action_loss_avg": 0.003633000061381608}
+{"step": 16840, "dynamics_loss_avg": 0.036659447383135556}
+{"step": 16840, "action_loss_avg": 0.004948282649274915}
+{"step": 16850, "loss": 0.0331, "learning_rate": 9.621041119191295e-05}
+{"step": 16850, "dynamics_loss_avg": 0.029259461350739}
+{"step": 16850, "action_loss_avg": 0.0037023267243057488}
+{"step": 16860, "dynamics_loss_avg": 0.03960475279018283}
+{"step": 16860, "action_loss_avg": 0.004932035808451474}
+{"step": 16870, "dynamics_loss_avg": 0.029519539093598723}
+{"step": 16870, "action_loss_avg": 0.004681768454611301}
+{"step": 16880, "dynamics_loss_avg": 0.04465881809592247}
+{"step": 16880, "action_loss_avg": 0.005018181208288297}
+{"step": 16890, "dynamics_loss_avg": 0.022898032609373332}
+{"step": 16890, "action_loss_avg": 0.0028430865553673358}
+{"step": 16900, "loss": 0.0371, "learning_rate": 9.617877594612886e-05}
+{"step": 16900, "dynamics_loss_avg": 0.03132194969803095}
+{"step": 16900, "action_loss_avg": 0.0034343623090535404}
+{"step": 16910, "dynamics_loss_avg": 0.03206081762909889}
+{"step": 16910, "action_loss_avg": 0.0037105473573319616}
+{"step": 16920, "dynamics_loss_avg": 0.02844685735180974}
+{"step": 16920, "action_loss_avg": 0.003374786232598126}
+{"step": 16930, "dynamics_loss_avg": 0.022319648414850235}
+{"step": 16930, "action_loss_avg": 0.0026149179378990085}
+{"step": 16940, "dynamics_loss_avg": 0.03938511945307255}
+{"step": 16940, "action_loss_avg": 0.0050549997016787526}
+{"step": 16950, "loss": 0.0356, "learning_rate": 9.614701444933465e-05}
+{"step": 16950, "dynamics_loss_avg": 0.03283222857862711}
+{"step": 16950, "action_loss_avg": 0.003604806069051847}
+{"step": 16960, "dynamics_loss_avg": 0.029817962553352118}
+{"step": 16960, "action_loss_avg": 0.0031119275197852405}
+{"step": 16970, "dynamics_loss_avg": 0.03431296609342098}
+{"step": 16970, "action_loss_avg": 0.0028931517619639633}
+{"step": 16980, "dynamics_loss_avg": 0.025080721452832223}
+{"step": 16980, "action_loss_avg": 0.0029234951827675102}
+{"step": 16990, "dynamics_loss_avg": 0.036704063229262826}
+{"step": 16990, "action_loss_avg": 0.005256066468427889}
+{"step": 17000, "loss": 0.0364, "learning_rate": 9.611512678836506e-05}
+{"step": 17000, "dynamics_loss_avg": 0.03311821417883039}
+{"step": 17000, "action_loss_avg": 0.005194591276813298}
+{"step": 17010, "dynamics_loss_avg": 0.042784284241497515}
+{"step": 17010, "action_loss_avg": 0.0064199819229543206}
+{"step": 17020, "dynamics_loss_avg": 0.03769415058195591}
+{"step": 17020, "action_loss_avg": 0.003669935406651348}
+{"step": 17030, "dynamics_loss_avg": 0.04149464555084705}
+{"step": 17030, "action_loss_avg": 0.004342917224857956}
+{"step": 17040, "dynamics_loss_avg": 0.03634637091308832}
+{"step": 17040, "action_loss_avg": 0.004419602616690099}
+{"step": 17050, "loss": 0.0389, "learning_rate": 9.608311305039972e-05}
+{"step": 17050, "dynamics_loss_avg": 0.031876984424889086}
+{"step": 17050, "action_loss_avg": 0.00531456401804462}
+{"step": 17060, "dynamics_loss_avg": 0.030018717236816882}
+{"step": 17060, "action_loss_avg": 0.0034349966794252396}
+{"step": 17070, "dynamics_loss_avg": 0.024753881525248288}
+{"step": 17070, "action_loss_avg": 0.0029632018879055975}
+{"step": 17080, "dynamics_loss_avg": 0.032143148221075536}
+{"step": 17080, "action_loss_avg": 0.004147750558331609}
+{"step": 17090, "dynamics_loss_avg": 0.03344875955954194}
+{"step": 17090, "action_loss_avg": 0.004463539062999189}
+{"step": 17100, "loss": 0.034, "learning_rate": 9.6050973322963e-05}
+{"step": 17100, "dynamics_loss_avg": 0.034065869823098185}
+{"step": 17100, "action_loss_avg": 0.004177398001775146}
+{"step": 17110, "dynamics_loss_avg": 0.03321194760501385}
+{"step": 17110, "action_loss_avg": 0.004410774330608547}
+{"step": 17120, "dynamics_loss_avg": 0.041217761021107434}
+{"step": 17120, "action_loss_avg": 0.005439706798642874}
+{"step": 17130, "dynamics_loss_avg": 0.040840372908860445}
+{"step": 17130, "action_loss_avg": 0.005553485848940909}
+{"step": 17140, "dynamics_loss_avg": 0.03177817333489656}
+{"step": 17140, "action_loss_avg": 0.00430489236023277}
+{"step": 17150, "loss": 0.0348, "learning_rate": 9.601870769392365e-05}
+{"step": 17150, "dynamics_loss_avg": 0.027107437327504157}
+{"step": 17150, "action_loss_avg": 0.0028370282729156316}
+{"step": 17160, "dynamics_loss_avg": 0.03773077940568328}
+{"step": 17160, "action_loss_avg": 0.0033950881916098297}
+{"step": 17170, "dynamics_loss_avg": 0.03346297135576606}
+{"step": 17170, "action_loss_avg": 0.004274064197670668}
+{"step": 17180, "dynamics_loss_avg": 0.022904421482235194}
+{"step": 17180, "action_loss_avg": 0.00214399240212515}
+{"step": 17190, "dynamics_loss_avg": 0.03722661081701517}
+{"step": 17190, "action_loss_avg": 0.00329050807049498}
+{"step": 17200, "loss": 0.0349, "learning_rate": 9.59863162514947e-05}
+{"step": 17200, "dynamics_loss_avg": 0.03469563769176602}
+{"step": 17200, "action_loss_avg": 0.004345055413432419}
+{"step": 17210, "dynamics_loss_avg": 0.031462274678051474}
+{"step": 17210, "action_loss_avg": 0.004122769215609878}
+{"step": 17220, "dynamics_loss_avg": 0.04229261726140976}
+{"step": 17220, "action_loss_avg": 0.0055100250872783365}
+{"step": 17230, "dynamics_loss_avg": 0.0337923489511013}
+{"step": 17230, "action_loss_avg": 0.0034283997491002085}
+{"step": 17240, "dynamics_loss_avg": 0.03421582356095314}
+{"step": 17240, "action_loss_avg": 0.0037404325092211367}
+{"step": 17250, "loss": 0.0356, "learning_rate": 9.59537990842331e-05}
+{"step": 17250, "dynamics_loss_avg": 0.032072912389412525}
+{"step": 17250, "action_loss_avg": 0.004202829778660089}
+{"step": 17260, "dynamics_loss_avg": 0.037332261353731154}
+{"step": 17260, "action_loss_avg": 0.004738416930194944}
+{"step": 17270, "dynamics_loss_avg": 0.034755208622664215}
+{"step": 17270, "action_loss_avg": 0.004439557367004454}
+{"step": 17280, "dynamics_loss_avg": 0.03974260687828064}
+{"step": 17280, "action_loss_avg": 0.0050708269816823305}
+{"step": 17290, "dynamics_loss_avg": 0.03266670778393745}
+{"step": 17290, "action_loss_avg": 0.0037342038238421084}
+{"step": 17300, "loss": 0.0357, "learning_rate": 9.592115628103952e-05}
+{"step": 17300, "dynamics_loss_avg": 0.03012009020894766}
+{"step": 17300, "action_loss_avg": 0.0035358844557777046}
+{"step": 17310, "dynamics_loss_avg": 0.03437055423855782}
+{"step": 17310, "action_loss_avg": 0.004346270021051169}
+{"step": 17320, "dynamics_loss_avg": 0.03790170112624765}
+{"step": 17320, "action_loss_avg": 0.004168150259647519}
+{"step": 17330, "dynamics_loss_avg": 0.025673521496355534}
+{"step": 17330, "action_loss_avg": 0.0031728051602840424}
+{"step": 17340, "dynamics_loss_avg": 0.03842011746019125}
+{"step": 17340, "action_loss_avg": 0.00478528953390196}
+{"step": 17350, "loss": 0.035, "learning_rate": 9.58883879311582e-05}
+{"step": 17350, "dynamics_loss_avg": 0.03371373545378446}
+{"step": 17350, "action_loss_avg": 0.003265053906943649}
+{"step": 17360, "dynamics_loss_avg": 0.03496458064764738}
+{"step": 17360, "action_loss_avg": 0.0038956107280682774}
+{"step": 17370, "dynamics_loss_avg": 0.0318573166616261}
+{"step": 17370, "action_loss_avg": 0.003087395243346691}
+{"step": 17380, "dynamics_loss_avg": 0.035544184222817424}
+{"step": 17380, "action_loss_avg": 0.0030808590410742907}
+{"step": 17390, "dynamics_loss_avg": 0.03733578007668257}
+{"step": 17390, "action_loss_avg": 0.004603358439635485}
+{"step": 17400, "loss": 0.0357, "learning_rate": 9.58554941241765e-05}
+{"step": 17400, "dynamics_loss_avg": 0.029098252952098846}
+{"step": 17400, "action_loss_avg": 0.002665075333788991}
+{"step": 17410, "dynamics_loss_avg": 0.03540384797379374}
+{"step": 17410, "action_loss_avg": 0.003789866017177701}
+{"step": 17420, "dynamics_loss_avg": 0.027198830619454384}
+{"step": 17420, "action_loss_avg": 0.0027144070016220214}
+{"step": 17430, "dynamics_loss_avg": 0.02627336010336876}
+{"step": 17430, "action_loss_avg": 0.00283159795217216}
+{"step": 17440, "dynamics_loss_avg": 0.030045950971543788}
+{"step": 17440, "action_loss_avg": 0.0036146338563412426}
+{"step": 17450, "loss": 0.0331, "learning_rate": 9.582247495002486e-05}
+{"step": 17450, "dynamics_loss_avg": 0.03114383053034544}
+{"step": 17450, "action_loss_avg": 0.0044349375297315415}
+{"step": 17460, "dynamics_loss_avg": 0.024062099028378726}
+{"step": 17460, "action_loss_avg": 0.002288559032604098}
+{"step": 17470, "dynamics_loss_avg": 0.04000264164060354}
+{"step": 17470, "action_loss_avg": 0.005207917897496373}
+{"step": 17480, "dynamics_loss_avg": 0.028516705706715585}
+{"step": 17480, "action_loss_avg": 0.003740295418538153}
+{"step": 17490, "dynamics_loss_avg": 0.039760027546435595}
+{"step": 17490, "action_loss_avg": 0.005200373905245215}
+{"step": 17500, "loss": 0.0378, "learning_rate": 9.578933049897643e-05}
+{"step": 17500, "dynamics_loss_avg": 0.04198305727913976}
+{"step": 17500, "action_loss_avg": 0.005473871040157974}
+{"step": 17510, "dynamics_loss_avg": 0.0503799244761467}
+{"step": 17510, "action_loss_avg": 0.005520241800695658}
+{"step": 17520, "dynamics_loss_avg": 0.03829627837985754}
+{"step": 17520, "action_loss_avg": 0.005675428640097379}
+{"step": 17530, "dynamics_loss_avg": 0.035736190434545276}
+{"step": 17530, "action_loss_avg": 0.003964023664593697}
+{"step": 17540, "dynamics_loss_avg": 0.03347113160416484}
+{"step": 17540, "action_loss_avg": 0.004199739918112755}
+{"step": 17550, "loss": 0.0402, "learning_rate": 9.575606086164687e-05}
+{"step": 17550, "dynamics_loss_avg": 0.037967896973714235}
+{"step": 17550, "action_loss_avg": 0.004675953998230398}
+{"step": 17560, "dynamics_loss_avg": 0.020093094976618885}
+{"step": 17560, "action_loss_avg": 0.003032375208567828}
+{"step": 17570, "dynamics_loss_avg": 0.02665521642193198}
+{"step": 17570, "action_loss_avg": 0.0035049648024141787}
+{"step": 17580, "dynamics_loss_avg": 0.03217617003247142}
+{"step": 17580, "action_loss_avg": 0.0027087520458735524}
+{"step": 17590, "dynamics_loss_avg": 0.037776506319642064}
+{"step": 17590, "action_loss_avg": 0.004964961437508464}
+{"step": 17600, "loss": 0.0356, "learning_rate": 9.57226661289941e-05}
+{"step": 17600, "dynamics_loss_avg": 0.031126955756917596}
+{"step": 17600, "action_loss_avg": 0.004034540324937552}
+{"step": 17610, "dynamics_loss_avg": 0.02639066632837057}
+{"step": 17610, "action_loss_avg": 0.004164062824565917}
+{"step": 17620, "dynamics_loss_avg": 0.02694990234449506}
+{"step": 17620, "action_loss_avg": 0.003712835715850815}
+{"step": 17630, "dynamics_loss_avg": 0.04044585414230824}
+{"step": 17630, "action_loss_avg": 0.005858861294109374}
+{"step": 17640, "dynamics_loss_avg": 0.03217392787337303}
+{"step": 17640, "action_loss_avg": 0.003401001391466707}
+{"step": 17650, "loss": 0.0334, "learning_rate": 9.568914639231807e-05}
+{"step": 17650, "dynamics_loss_avg": 0.03276601983234286}
+{"step": 17650, "action_loss_avg": 0.004136248689610511}
+{"step": 17660, "dynamics_loss_avg": 0.03183925040066242}
+{"step": 17660, "action_loss_avg": 0.003870138106867671}
+{"step": 17670, "dynamics_loss_avg": 0.0337056877091527}
+{"step": 17670, "action_loss_avg": 0.004067180713173002}
+{"step": 17680, "dynamics_loss_avg": 0.03908360674977303}
+{"step": 17680, "action_loss_avg": 0.004040045302826911}
+{"step": 17690, "dynamics_loss_avg": 0.036856308672577144}
+{"step": 17690, "action_loss_avg": 0.003961623611394316}
+{"step": 17700, "loss": 0.0363, "learning_rate": 9.565550174326043e-05}
+{"step": 17700, "dynamics_loss_avg": 0.03621268887072802}
+{"step": 17700, "action_loss_avg": 0.004281548433937132}
+{"step": 17710, "dynamics_loss_avg": 0.02485385797917843}
+{"step": 17710, "action_loss_avg": 0.0030900815152563156}
+{"step": 17720, "dynamics_loss_avg": 0.03110645255073905}
+{"step": 17720, "action_loss_avg": 0.0025621445092838258}
+{"step": 17730, "dynamics_loss_avg": 0.04433850236237049}
+{"step": 17730, "action_loss_avg": 0.0048339884029701356}
+{"step": 17740, "dynamics_loss_avg": 0.035772351548075676}
+{"step": 17740, "action_loss_avg": 0.003718370373826474}
+{"step": 17750, "loss": 0.0354, "learning_rate": 9.562173227380436e-05}
+{"step": 17750, "dynamics_loss_avg": 0.034743554424494505}
+{"step": 17750, "action_loss_avg": 0.0040421419544145465}
+{"step": 17760, "dynamics_loss_avg": 0.043572887871414424}
+{"step": 17760, "action_loss_avg": 0.004542593588121235}
+{"step": 17770, "dynamics_loss_avg": 0.026571615925058724}
+{"step": 17770, "action_loss_avg": 0.003322677139658481}
+{"step": 17780, "dynamics_loss_avg": 0.03165597338229418}
+{"step": 17780, "action_loss_avg": 0.003254033322446048}
+{"step": 17790, "dynamics_loss_avg": 0.03318336857482791}
+{"step": 17790, "action_loss_avg": 0.003913329419447109}
+{"step": 17800, "loss": 0.0349, "learning_rate": 9.558783807627434e-05}
+{"step": 17800, "dynamics_loss_avg": 0.028781396429985763}
+{"step": 17800, "action_loss_avg": 0.003192470991052687}
+{"step": 17810, "dynamics_loss_avg": 0.03215541746467352}
+{"step": 17810, "action_loss_avg": 0.003036820923443884}
+{"step": 17820, "dynamics_loss_avg": 0.030311078671365975}
+{"step": 17820, "action_loss_avg": 0.0036909781163558366}
+{"step": 17830, "dynamics_loss_avg": 0.0370510159060359}
+{"step": 17830, "action_loss_avg": 0.0035833129892125725}
+{"step": 17840, "dynamics_loss_avg": 0.035024567414075135}
+{"step": 17840, "action_loss_avg": 0.0033671079785563053}
+{"step": 17850, "loss": 0.0382, "learning_rate": 9.555381924333578e-05}
+{"step": 17850, "dynamics_loss_avg": 0.04053631294518709}
+{"step": 17850, "action_loss_avg": 0.005723725352436304}
+{"step": 17860, "dynamics_loss_avg": 0.036807629838585855}
+{"step": 17860, "action_loss_avg": 0.005406415730249137}
+{"step": 17870, "dynamics_loss_avg": 0.026894913427531718}
+{"step": 17870, "action_loss_avg": 0.0041352452244609594}
+{"step": 17880, "dynamics_loss_avg": 0.03277353225275874}
+{"step": 17880, "action_loss_avg": 0.003958845708984882}
+{"step": 17890, "dynamics_loss_avg": 0.03281893106177449}
+{"step": 17890, "action_loss_avg": 0.00464034341275692}
+{"step": 17900, "loss": 0.0361, "learning_rate": 9.551967586799486e-05}
+{"step": 17900, "dynamics_loss_avg": 0.032812264701351526}
+{"step": 17900, "action_loss_avg": 0.004252477351110428}
+{"step": 17910, "dynamics_loss_avg": 0.033678865619003774}
+{"step": 17910, "action_loss_avg": 0.005366591224446893}
+{"step": 17920, "dynamics_loss_avg": 0.034285802766680716}
+{"step": 17920, "action_loss_avg": 0.0048007865902036425}
+{"step": 17930, "dynamics_loss_avg": 0.0281757827848196}
+{"step": 17930, "action_loss_avg": 0.0033166240784339605}
+{"step": 17940, "dynamics_loss_avg": 0.043669586163014175}
+{"step": 17940, "action_loss_avg": 0.006113621487747878}
+{"step": 17950, "loss": 0.0364, "learning_rate": 9.548540804359828e-05}
+{"step": 17950, "dynamics_loss_avg": 0.039831965882331136}
+{"step": 17950, "action_loss_avg": 0.005371815687976777}
+{"step": 17960, "dynamics_loss_avg": 0.035064546205103395}
+{"step": 17960, "action_loss_avg": 0.004668318014591932}
+{"step": 17970, "dynamics_loss_avg": 0.03027108060196042}
+{"step": 17970, "action_loss_avg": 0.0031818923947867007}
+{"step": 17980, "dynamics_loss_avg": 0.03883012067526579}
+{"step": 17980, "action_loss_avg": 0.0047142004361376165}
+{"step": 17990, "dynamics_loss_avg": 0.03101997757330537}
+{"step": 17990, "action_loss_avg": 0.004281652893405407}
+{"step": 18000, "loss": 0.0353, "learning_rate": 9.5451015863833e-05}
+{"step": 18000, "dynamics_loss_avg": 0.03677073251456022}
+{"step": 18000, "action_loss_avg": 0.004841586819384247}
+{"step": 18010, "dynamics_loss_avg": 0.039834357984364036}
+{"step": 18010, "action_loss_avg": 0.00466356027754955}
+{"step": 18020, "dynamics_loss_avg": 0.02734196772798896}
+{"step": 18020, "action_loss_avg": 0.0032529877847991885}
+{"step": 18030, "dynamics_loss_avg": 0.04092010036110878}
+{"step": 18030, "action_loss_avg": 0.004734042496420443}
+{"step": 18040, "dynamics_loss_avg": 0.037056080903857945}
+{"step": 18040, "action_loss_avg": 0.0035456459503620864}
+{"step": 18050, "loss": 0.0378, "learning_rate": 9.541649942272585e-05}
+{"step": 18050, "dynamics_loss_avg": 0.05025638490915298}
+{"step": 18050, "action_loss_avg": 0.005264775996329263}
+{"step": 18060, "dynamics_loss_avg": 0.03002281514927745}
+{"step": 18060, "action_loss_avg": 0.004674026422435418}
+{"step": 18070, "dynamics_loss_avg": 0.029446499329060315}
+{"step": 18070, "action_loss_avg": 0.003631054947618395}
+{"step": 18080, "dynamics_loss_avg": 0.02402787362225354}
+{"step": 18080, "action_loss_avg": 0.0029503193334676327}
+{"step": 18090, "dynamics_loss_avg": 0.03579585487022996}
+{"step": 18090, "action_loss_avg": 0.0039637679932639}
+{"step": 18100, "loss": 0.0348, "learning_rate": 9.538185881464353e-05}
+{"step": 18100, "dynamics_loss_avg": 0.035469018016010524}
+{"step": 18100, "action_loss_avg": 0.004252234997693449}
+{"step": 18110, "dynamics_loss_avg": 0.03264663713052869}
+{"step": 18110, "action_loss_avg": 0.002722096157958731}
+{"step": 18120, "dynamics_loss_avg": 0.03531229924410582}
+{"step": 18120, "action_loss_avg": 0.004036279127467424}
+{"step": 18130, "dynamics_loss_avg": 0.03022666140459478}
+{"step": 18130, "action_loss_avg": 0.0034118727140594273}
+{"step": 18140, "dynamics_loss_avg": 0.029289275780320166}
+{"step": 18140, "action_loss_avg": 0.003184242709539831}
+{"step": 18150, "loss": 0.0346, "learning_rate": 9.53470941342921e-05}
+{"step": 18150, "dynamics_loss_avg": 0.03089740676805377}
+{"step": 18150, "action_loss_avg": 0.004613370861625299}
+{"step": 18160, "dynamics_loss_avg": 0.03351150518283248}
+{"step": 18160, "action_loss_avg": 0.004870600893627852}
+{"step": 18170, "dynamics_loss_avg": 0.025091869104653598}
+{"step": 18170, "action_loss_avg": 0.002492016868200153}
+{"step": 18180, "dynamics_loss_avg": 0.031694271974265574}
+{"step": 18180, "action_loss_avg": 0.0033080601191613824}
+{"step": 18190, "dynamics_loss_avg": 0.032474505808204414}
+{"step": 18190, "action_loss_avg": 0.0030247886199504135}
+{"step": 18200, "loss": 0.0357, "learning_rate": 9.531220547671688e-05}
+{"step": 18200, "dynamics_loss_avg": 0.042063324339687826}
+{"step": 18200, "action_loss_avg": 0.0041345776291564105}
+{"step": 18210, "dynamics_loss_avg": 0.04083832371979952}
+{"step": 18210, "action_loss_avg": 0.004318785551004112}
+{"step": 18220, "dynamics_loss_avg": 0.03816191125661135}
+{"step": 18220, "action_loss_avg": 0.005033555324189365}
+{"step": 18230, "dynamics_loss_avg": 0.02838987801223993}
+{"step": 18230, "action_loss_avg": 0.003560106741497293}
+{"step": 18240, "dynamics_loss_avg": 0.027597406692802907}
+{"step": 18240, "action_loss_avg": 0.0034576780162751675}
+{"step": 18250, "loss": 0.0334, "learning_rate": 9.527719293730215e-05}
+{"step": 18250, "dynamics_loss_avg": 0.027160842996090652}
+{"step": 18250, "action_loss_avg": 0.0035075690015219153}
+{"step": 18260, "dynamics_loss_avg": 0.044227705150842664}
+{"step": 18260, "action_loss_avg": 0.0055708953063003715}
+{"step": 18270, "dynamics_loss_avg": 0.028648648969829084}
+{"step": 18270, "action_loss_avg": 0.003276619070675224}
+{"step": 18280, "dynamics_loss_avg": 0.029673829209059477}
+{"step": 18280, "action_loss_avg": 0.0033467561064753682}
+{"step": 18290, "dynamics_loss_avg": 0.03862398881465197}
+{"step": 18290, "action_loss_avg": 0.004816526576178148}
+{"step": 18300, "loss": 0.0363, "learning_rate": 9.524205661177081e-05}
+{"step": 18300, "dynamics_loss_avg": 0.03426370751112699}
+{"step": 18300, "action_loss_avg": 0.004815625393530354}
+{"step": 18310, "dynamics_loss_avg": 0.03708139015361667}
+{"step": 18310, "action_loss_avg": 0.00520547175547108}
+{"step": 18320, "dynamics_loss_avg": 0.03007510993629694}
+{"step": 18320, "action_loss_avg": 0.0035095861647278072}
+{"step": 18330, "dynamics_loss_avg": 0.0336055220104754}
+{"step": 18330, "action_loss_avg": 0.0032277483609505}
+{"step": 18340, "dynamics_loss_avg": 0.028917566873133183}
+{"step": 18340, "action_loss_avg": 0.002746905852109194}
+{"step": 18350, "loss": 0.0344, "learning_rate": 9.520679659618428e-05}
+{"step": 18350, "dynamics_loss_avg": 0.03281802264973521}
+{"step": 18350, "action_loss_avg": 0.004886364424601197}
+{"step": 18360, "dynamics_loss_avg": 0.0343447788618505}
+{"step": 18360, "action_loss_avg": 0.0046257334179244936}
+{"step": 18370, "dynamics_loss_avg": 0.034690342657268045}
+{"step": 18370, "action_loss_avg": 0.004319656209554523}
+{"step": 18380, "dynamics_loss_avg": 0.0366352679207921}
+{"step": 18380, "action_loss_avg": 0.004335290938615799}
+{"step": 18390, "dynamics_loss_avg": 0.029048695508390666}
+{"step": 18390, "action_loss_avg": 0.003372283623320982}
+{"step": 18400, "loss": 0.0375, "learning_rate": 9.517141298694205e-05}
+{"step": 18400, "dynamics_loss_avg": 0.03323267949745059}
+{"step": 18400, "action_loss_avg": 0.003132285794708878}
+{"step": 18410, "dynamics_loss_avg": 0.03268633410334587}
+{"step": 18410, "action_loss_avg": 0.004161265434231609}
+{"step": 18420, "dynamics_loss_avg": 0.032980353198945524}
+{"step": 18420, "action_loss_avg": 0.0035308246966451406}
+{"step": 18430, "dynamics_loss_avg": 0.03352142358198762}
+{"step": 18430, "action_loss_avg": 0.003953125653788447}
+{"step": 18440, "dynamics_loss_avg": 0.026959840767085554}
+{"step": 18440, "action_loss_avg": 0.0022336603025905786}
+{"step": 18450, "loss": 0.0345, "learning_rate": 9.513590588078159e-05}
+{"step": 18450, "dynamics_loss_avg": 0.03694887096062303}
+{"step": 18450, "action_loss_avg": 0.004193018982186913}
+{"step": 18460, "dynamics_loss_avg": 0.030289470474235712}
+{"step": 18460, "action_loss_avg": 0.0029220912416349164}
+{"step": 18470, "dynamics_loss_avg": 0.031041423324495554}
+{"step": 18470, "action_loss_avg": 0.0033838062663562596}
+{"step": 18480, "dynamics_loss_avg": 0.028564608097076415}
+{"step": 18480, "action_loss_avg": 0.0031181891448795796}
+{"step": 18490, "dynamics_loss_avg": 0.03396295579150319}
+{"step": 18490, "action_loss_avg": 0.003933404386043548}
+{"step": 18500, "loss": 0.0372, "learning_rate": 9.510027537477797e-05}
+{"step": 18500, "dynamics_loss_avg": 0.04192297193221748}
+{"step": 18500, "action_loss_avg": 0.005872891342733055}
+{"step": 18510, "dynamics_loss_avg": 0.028239334747195245}
+{"step": 18510, "action_loss_avg": 0.003034697734983638}
+{"step": 18520, "dynamics_loss_avg": 0.031924440246075395}
+{"step": 18520, "action_loss_avg": 0.003740338294301182}
+{"step": 18530, "dynamics_loss_avg": 0.038166138157248494}
+{"step": 18530, "action_loss_avg": 0.005549975682515651}
+{"step": 18540, "dynamics_loss_avg": 0.03281295914202929}
+{"step": 18540, "action_loss_avg": 0.0034322979277931153}
+{"step": 18550, "loss": 0.0361, "learning_rate": 9.506452156634362e-05}
+{"step": 18550, "dynamics_loss_avg": 0.03462095223367214}
+{"step": 18550, "action_loss_avg": 0.004412592865992338}
+{"step": 18560, "dynamics_loss_avg": 0.03466638242825866}
+{"step": 18560, "action_loss_avg": 0.004334080137778073}
+{"step": 18570, "dynamics_loss_avg": 0.039535784255713226}
+{"step": 18570, "action_loss_avg": 0.005303562362678349}
+{"step": 18580, "dynamics_loss_avg": 0.027705541346222162}
+{"step": 18580, "action_loss_avg": 0.0020736577920615674}
+{"step": 18590, "dynamics_loss_avg": 0.02466196343302727}
+{"step": 18590, "action_loss_avg": 0.0026188550633378326}
+{"step": 18600, "loss": 0.0333, "learning_rate": 9.502864455322809e-05}
+{"step": 18600, "dynamics_loss_avg": 0.02746110549196601}
+{"step": 18600, "action_loss_avg": 0.0032412307453341784}
+{"step": 18610, "dynamics_loss_avg": 0.03837883779779076}
+{"step": 18610, "action_loss_avg": 0.003859412483870983}
+{"step": 18620, "dynamics_loss_avg": 0.030017895624041557}
+{"step": 18620, "action_loss_avg": 0.0033054561587050556}
+{"step": 18630, "dynamics_loss_avg": 0.02985058194026351}
+{"step": 18630, "action_loss_avg": 0.002844276395626366}
+{"step": 18640, "dynamics_loss_avg": 0.044150740699842574}
+{"step": 18640, "action_loss_avg": 0.005251871462678537}
+{"step": 18650, "loss": 0.0345, "learning_rate": 9.499264443351775e-05}
+{"step": 18650, "dynamics_loss_avg": 0.030919107142835855}
+{"step": 18650, "action_loss_avg": 0.003979839564999565}
+{"step": 18660, "dynamics_loss_avg": 0.03491206057369709}
+{"step": 18660, "action_loss_avg": 0.0057752187480218705}
+{"step": 18670, "dynamics_loss_avg": 0.029848690889775754}
+{"step": 18670, "action_loss_avg": 0.0046814276720397174}
+{"step": 18680, "dynamics_loss_avg": 0.03887923005968332}
+{"step": 18680, "action_loss_avg": 0.004344521241728216}
+{"step": 18690, "dynamics_loss_avg": 0.033646519854664804}
+{"step": 18690, "action_loss_avg": 0.004571495368145407}
+{"step": 18700, "loss": 0.0369, "learning_rate": 9.49565213056356e-05}
+{"step": 18700, "dynamics_loss_avg": 0.03632225412875414}
+{"step": 18700, "action_loss_avg": 0.004237226163968444}
+{"step": 18710, "dynamics_loss_avg": 0.025933178886771203}
+{"step": 18710, "action_loss_avg": 0.002606767066754401}
+{"step": 18720, "dynamics_loss_avg": 0.03235620176419616}
+{"step": 18720, "action_loss_avg": 0.004044867563061416}
+{"step": 18730, "dynamics_loss_avg": 0.0344378711655736}
+{"step": 18730, "action_loss_avg": 0.004324029735289514}
+{"step": 18740, "dynamics_loss_avg": 0.03989512054249644}
+{"step": 18740, "action_loss_avg": 0.005489039537496865}
+{"step": 18750, "loss": 0.036, "learning_rate": 9.492027526834083e-05}
+{"step": 18750, "dynamics_loss_avg": 0.03709928318858147}
+{"step": 18750, "action_loss_avg": 0.004271674971096218}
+{"step": 18760, "dynamics_loss_avg": 0.03245461417827755}
+{"step": 18760, "action_loss_avg": 0.004283345516887494}
+{"step": 18770, "dynamics_loss_avg": 0.0381838534027338}
+{"step": 18770, "action_loss_avg": 0.004226654733065516}
+{"step": 18780, "dynamics_loss_avg": 0.03505158154293895}
+{"step": 18780, "action_loss_avg": 0.003235560702160001}
+{"step": 18790, "dynamics_loss_avg": 0.03301483364775777}
+{"step": 18790, "action_loss_avg": 0.004508720018202439}
+{"step": 18800, "loss": 0.0366, "learning_rate": 9.488390642072878e-05}
+{"step": 18800, "dynamics_loss_avg": 0.038479998521506784}
+{"step": 18800, "action_loss_avg": 0.003952947538346052}
+{"step": 18810, "dynamics_loss_avg": 0.0300355332903564}
+{"step": 18810, "action_loss_avg": 0.0028791781864129008}
+{"step": 18820, "dynamics_loss_avg": 0.02778008859604597}
+{"step": 18820, "action_loss_avg": 0.003901928255800158}
+{"step": 18830, "dynamics_loss_avg": 0.03864014502614736}
+{"step": 18830, "action_loss_avg": 0.0036717792274430392}
+{"step": 18840, "dynamics_loss_avg": 0.03545676097273827}
+{"step": 18840, "action_loss_avg": 0.0033945848001167176}
+{"step": 18850, "loss": 0.0341, "learning_rate": 9.484741486223043e-05}
+{"step": 18850, "dynamics_loss_avg": 0.028188807424157858}
+{"step": 18850, "action_loss_avg": 0.00270250589819625}
+{"step": 18860, "dynamics_loss_avg": 0.04239969523623586}
+{"step": 18860, "action_loss_avg": 0.0042724032187834386}
+{"step": 18870, "dynamics_loss_avg": 0.026818258129060267}
+{"step": 18870, "action_loss_avg": 0.002755053446162492}
+{"step": 18880, "dynamics_loss_avg": 0.04682843508198857}
+{"step": 18880, "action_loss_avg": 0.005042420834070071}
+{"step": 18890, "dynamics_loss_avg": 0.029046729067340495}
+{"step": 18890, "action_loss_avg": 0.0028512504592072218}
+{"step": 18900, "loss": 0.0383, "learning_rate": 9.481080069261237e-05}
+{"step": 18900, "dynamics_loss_avg": 0.03836116846650839}
+{"step": 18900, "action_loss_avg": 0.0036708608502522113}
+{"step": 18910, "dynamics_loss_avg": 0.02816849444061518}
+{"step": 18910, "action_loss_avg": 0.0039008809020742775}
+{"step": 18920, "dynamics_loss_avg": 0.027929234970360994}
+{"step": 18920, "action_loss_avg": 0.0030950823449529706}
+{"step": 18930, "dynamics_loss_avg": 0.045356778986752035}
+{"step": 18930, "action_loss_avg": 0.005945483571849763}
+{"step": 18940, "dynamics_loss_avg": 0.02327731093391776}
+{"step": 18940, "action_loss_avg": 0.00280239632120356}
+{"step": 18950, "loss": 0.033, "learning_rate": 9.47740640119763e-05}
+{"step": 18950, "dynamics_loss_avg": 0.02248606402426958}
+{"step": 18950, "action_loss_avg": 0.0031853770953603087}
+{"step": 18960, "dynamics_loss_avg": 0.03444523587822914}
+{"step": 18960, "action_loss_avg": 0.0038986614905297755}
+{"step": 18970, "dynamics_loss_avg": 0.03519229236990214}
+{"step": 18970, "action_loss_avg": 0.00406939503736794}
+{"step": 18980, "dynamics_loss_avg": 0.03338389173150062}
+{"step": 18980, "action_loss_avg": 0.0038274220132734627}
+{"step": 18990, "dynamics_loss_avg": 0.033070096652954815}
+{"step": 18990, "action_loss_avg": 0.00334796030074358}
+{"step": 19000, "loss": 0.0364, "learning_rate": 9.473720492075892e-05}
+{"step": 19000, "dynamics_loss_avg": 0.042988195829093453}
+{"step": 19000, "action_loss_avg": 0.004162962175905704}
+{"step": 19010, "dynamics_loss_avg": 0.030309570673853158}
+{"step": 19010, "action_loss_avg": 0.0038459192670416086}
+{"step": 19020, "dynamics_loss_avg": 0.03213924937881529}
+{"step": 19020, "action_loss_avg": 0.004056264949031174}
+{"step": 19030, "dynamics_loss_avg": 0.03295284542255104}
+{"step": 19030, "action_loss_avg": 0.0036872657423373313}
+{"step": 19040, "dynamics_loss_avg": 0.04661351041868329}
+{"step": 19040, "action_loss_avg": 0.0050326421798672525}
+{"step": 19050, "loss": 0.0368, "learning_rate": 9.470022351973158e-05}
+{"step": 19050, "dynamics_loss_avg": 0.041971211414784194}
+{"step": 19050, "action_loss_avg": 0.00641502202488482}
+{"step": 19060, "dynamics_loss_avg": 0.028425369644537568}
+{"step": 19060, "action_loss_avg": 0.003217123361537233}
+{"step": 19070, "dynamics_loss_avg": 0.03377505857497454}
+{"step": 19070, "action_loss_avg": 0.0037582994438707827}
+{"step": 19080, "dynamics_loss_avg": 0.030235787248238923}
+{"step": 19080, "action_loss_avg": 0.003453364613233134}
+{"step": 19090, "dynamics_loss_avg": 0.024698871280997993}
+{"step": 19090, "action_loss_avg": 0.002781222463818267}
+{"step": 19100, "loss": 0.0335, "learning_rate": 9.466311990999999e-05}
+{"step": 19100, "dynamics_loss_avg": 0.029973355121910572}
+{"step": 19100, "action_loss_avg": 0.0039619639865122736}
+{"step": 19110, "dynamics_loss_avg": 0.031472528167068956}
+{"step": 19110, "action_loss_avg": 0.003042043466120958}
+{"step": 19120, "dynamics_loss_avg": 0.04357706420123577}
+{"step": 19120, "action_loss_avg": 0.006152872869279236}
+{"step": 19130, "dynamics_loss_avg": 0.0393985259346664}
+{"step": 19130, "action_loss_avg": 0.003989929077215492}
+{"step": 19140, "dynamics_loss_avg": 0.025739858346059918}
+{"step": 19140, "action_loss_avg": 0.004121499671600759}
+{"step": 19150, "loss": 0.036, "learning_rate": 9.462589419300403e-05}
+{"step": 19150, "dynamics_loss_avg": 0.036158821638673545}
+{"step": 19150, "action_loss_avg": 0.004922588588669896}
+{"step": 19160, "dynamics_loss_avg": 0.03592765787616372}
+{"step": 19160, "action_loss_avg": 0.004670248826732859}
+{"step": 19170, "dynamics_loss_avg": 0.021652379911392926}
+{"step": 19170, "action_loss_avg": 0.003042074339464307}
+{"step": 19180, "dynamics_loss_avg": 0.04590694243088365}
+{"step": 19180, "action_loss_avg": 0.004230015992652625}
+{"step": 19190, "dynamics_loss_avg": 0.029207271337509156}
+{"step": 19190, "action_loss_avg": 0.003694166912464425}
+{"step": 19200, "loss": 0.0388, "learning_rate": 9.45885464705174e-05}
+{"step": 19200, "dynamics_loss_avg": 0.03634005347266793}
+{"step": 19200, "action_loss_avg": 0.005408809817163273}
+{"step": 19210, "dynamics_loss_avg": 0.02728891298174858}
+{"step": 19210, "action_loss_avg": 0.0042108014575205745}
+{"step": 19220, "dynamics_loss_avg": 0.03065110696479678}
+{"step": 19220, "action_loss_avg": 0.004329703142866492}
+{"step": 19230, "dynamics_loss_avg": 0.030284816306084393}
+{"step": 19230, "action_loss_avg": 0.004092058958485722}
+{"step": 19240, "dynamics_loss_avg": 0.03588118134066463}
+{"step": 19240, "action_loss_avg": 0.005277875228784978}
+{"step": 19250, "loss": 0.034, "learning_rate": 9.45510768446473e-05}
+{"step": 19250, "dynamics_loss_avg": 0.033916397113353015}
+{"step": 19250, "action_loss_avg": 0.004153522144770249}
+{"step": 19260, "dynamics_loss_avg": 0.03273393409326673}
+{"step": 19260, "action_loss_avg": 0.004684664512751624}
+{"step": 19270, "dynamics_loss_avg": 0.03718648198992014}
+{"step": 19270, "action_loss_avg": 0.004000842175446451}
+{"step": 19280, "dynamics_loss_avg": 0.035179533250629905}
+{"step": 19280, "action_loss_avg": 0.00408491421258077}
+{"step": 19290, "dynamics_loss_avg": 0.03099482087418437}
+{"step": 19290, "action_loss_avg": 0.002875256061088294}
+{"step": 19300, "loss": 0.0352, "learning_rate": 9.451348541783431e-05}
+{"step": 19300, "dynamics_loss_avg": 0.033888679929077625}
+{"step": 19300, "action_loss_avg": 0.003513170394580811}
+{"step": 19310, "dynamics_loss_avg": 0.031067894771695137}
+{"step": 19310, "action_loss_avg": 0.0033514359267428516}
+{"step": 19320, "dynamics_loss_avg": 0.03223660252988338}
+{"step": 19320, "action_loss_avg": 0.00480733901495114}
+{"step": 19330, "dynamics_loss_avg": 0.04127527493983507}
+{"step": 19330, "action_loss_avg": 0.003912237158510834}
+{"step": 19340, "dynamics_loss_avg": 0.030815957766026258}
+{"step": 19340, "action_loss_avg": 0.004660714592318982}
+{"step": 19350, "loss": 0.0359, "learning_rate": 9.447577229285192e-05}
+{"step": 19350, "dynamics_loss_avg": 0.03742480371147394}
+{"step": 19350, "action_loss_avg": 0.004214409028645605}
+{"step": 19360, "dynamics_loss_avg": 0.033662411384284496}
+{"step": 19360, "action_loss_avg": 0.003524923883378506}
+{"step": 19370, "dynamics_loss_avg": 0.03473147582262755}
+{"step": 19370, "action_loss_avg": 0.004717719287145883}
+{"step": 19380, "dynamics_loss_avg": 0.03181040473282337}
+{"step": 19380, "action_loss_avg": 0.0033823028206825256}
+{"step": 19390, "dynamics_loss_avg": 0.035402873530983925}
+{"step": 19390, "action_loss_avg": 0.005516267765779048}
+{"step": 19400, "loss": 0.0326, "learning_rate": 9.443793757280638e-05}
+{"step": 19400, "dynamics_loss_avg": 0.02617495795711875}
+{"step": 19400, "action_loss_avg": 0.003986307245213538}
+{"step": 19410, "dynamics_loss_avg": 0.03959472747519612}
+{"step": 19410, "action_loss_avg": 0.005355786741711199}
+{"step": 19420, "dynamics_loss_avg": 0.029959924146533014}
+{"step": 19420, "action_loss_avg": 0.0031139640719629823}
+{"step": 19430, "dynamics_loss_avg": 0.032674364559352395}
+{"step": 19430, "action_loss_avg": 0.003961586765944958}
+{"step": 19440, "dynamics_loss_avg": 0.02206938583403826}
+{"step": 19440, "action_loss_avg": 0.002156567573547363}
+{"step": 19450, "loss": 0.0325, "learning_rate": 9.439998136113639e-05}
+{"step": 19450, "dynamics_loss_avg": 0.03777428464964032}
+{"step": 19450, "action_loss_avg": 0.0044548663834575565}
+{"step": 19460, "dynamics_loss_avg": 0.030246877297759055}
+{"step": 19460, "action_loss_avg": 0.0031374754616990685}
+{"step": 19470, "dynamics_loss_avg": 0.04145518578588962}
+{"step": 19470, "action_loss_avg": 0.004836316732689738}
+{"step": 19480, "dynamics_loss_avg": 0.0366637883707881}
+{"step": 19480, "action_loss_avg": 0.0032474630745127795}
+{"step": 19490, "dynamics_loss_avg": 0.039116645231842995}
+{"step": 19490, "action_loss_avg": 0.0038844105554744603}
+{"step": 19500, "loss": 0.0374, "learning_rate": 9.436190376161276e-05}
+{"step": 19500, "dynamics_loss_avg": 0.03212603125721216}
+{"step": 19500, "action_loss_avg": 0.002871968725230545}
+{"step": 19510, "dynamics_loss_avg": 0.04130548005923629}
+{"step": 19510, "action_loss_avg": 0.006220698822289705}
+{"step": 19520, "dynamics_loss_avg": 0.030650406796485185}
+{"step": 19520, "action_loss_avg": 0.0028127362485975025}
+{"step": 19530, "dynamics_loss_avg": 0.036033134534955026}
+{"step": 19530, "action_loss_avg": 0.004550781566649675}
+{"step": 19540, "dynamics_loss_avg": 0.020266110170632602}
+{"step": 19540, "action_loss_avg": 0.0021713907131925224}
+{"step": 19550, "loss": 0.0342, "learning_rate": 9.432370487833819e-05}
+{"step": 19550, "dynamics_loss_avg": 0.032016110979020594}
+{"step": 19550, "action_loss_avg": 0.0027028561395127325}
+{"step": 19560, "dynamics_loss_avg": 0.034109787456691264}
+{"step": 19560, "action_loss_avg": 0.0033417273545637725}
+{"step": 19570, "dynamics_loss_avg": 0.0296009024605155}
+{"step": 19570, "action_loss_avg": 0.0035796175012364983}
+{"step": 19580, "dynamics_loss_avg": 0.030489308713003992}
+{"step": 19580, "action_loss_avg": 0.0039018968003802002}
+{"step": 19590, "dynamics_loss_avg": 0.04231468550860882}
+{"step": 19590, "action_loss_avg": 0.0036686949082650245}
+{"step": 19600, "loss": 0.0333, "learning_rate": 9.428538481574699e-05}
+{"step": 19600, "dynamics_loss_avg": 0.028351505659520625}
+{"step": 19600, "action_loss_avg": 0.0029411384894046932}
+{"step": 19610, "dynamics_loss_avg": 0.03696638476103544}
+{"step": 19610, "action_loss_avg": 0.0035396865336224438}
+{"step": 19620, "dynamics_loss_avg": 0.028995237406343223}
+{"step": 19620, "action_loss_avg": 0.003835184429772198}
+{"step": 19630, "dynamics_loss_avg": 0.030089198052883147}
+{"step": 19630, "action_loss_avg": 0.0024073515087366104}
+{"step": 19640, "dynamics_loss_avg": 0.02822176106274128}
+{"step": 19640, "action_loss_avg": 0.003993221244309097}
+{"step": 19650, "loss": 0.0329, "learning_rate": 9.424694367860473e-05}
+{"step": 19650, "dynamics_loss_avg": 0.030733801145106553}
+{"step": 19650, "action_loss_avg": 0.0038570525473915042}
+{"step": 19660, "dynamics_loss_avg": 0.021781859640032052}
+{"step": 19660, "action_loss_avg": 0.002491557109169662}
+{"step": 19670, "dynamics_loss_avg": 0.028459781454876064}
+{"step": 19670, "action_loss_avg": 0.00494518486520974}
+{"step": 19680, "dynamics_loss_avg": 0.035721973516047}
+{"step": 19680, "action_loss_avg": 0.00454374905093573}
+{"step": 19690, "dynamics_loss_avg": 0.027135897893458605}
+{"step": 19690, "action_loss_avg": 0.0032984343357384204}
+{"step": 19700, "loss": 0.0313, "learning_rate": 9.420838157200803e-05}
+{"step": 19700, "dynamics_loss_avg": 0.03519725473597646}
+{"step": 19700, "action_loss_avg": 0.005154105753172189}
+{"step": 19710, "dynamics_loss_avg": 0.04013448413461447}
+{"step": 19710, "action_loss_avg": 0.004516508162487299}
+{"step": 19720, "dynamics_loss_avg": 0.035170750226825476}
+{"step": 19720, "action_loss_avg": 0.0035693150013685225}
+{"step": 19730, "dynamics_loss_avg": 0.030350299272686242}
+{"step": 19730, "action_loss_avg": 0.003969948377925902}
+{"step": 19740, "dynamics_loss_avg": 0.03415897861123085}
+{"step": 19740, "action_loss_avg": 0.004510178288910538}
+{"step": 19750, "loss": 0.0368, "learning_rate": 9.41696986013842e-05}
+{"step": 19750, "dynamics_loss_avg": 0.03051335848867893}
+{"step": 19750, "action_loss_avg": 0.0039526592707261445}
+{"step": 19760, "dynamics_loss_avg": 0.030476194713264702}
+{"step": 19760, "action_loss_avg": 0.003967983275651931}
+{"step": 19770, "dynamics_loss_avg": 0.029282549303025006}
+{"step": 19770, "action_loss_avg": 0.003533590119332075}
+{"step": 19780, "dynamics_loss_avg": 0.030492790043354034}
+{"step": 19780, "action_loss_avg": 0.0029051220160909}
+{"step": 19790, "dynamics_loss_avg": 0.036467420682311055}
+{"step": 19790, "action_loss_avg": 0.004213862249162048}
+{"step": 19800, "loss": 0.032, "learning_rate": 9.4130894872491e-05}
+{"step": 19800, "dynamics_loss_avg": 0.039394534286111595}
+{"step": 19800, "action_loss_avg": 0.0038329896342474967}
+{"step": 19810, "dynamics_loss_avg": 0.03221821221522987}
+{"step": 19810, "action_loss_avg": 0.0036464003700530157}
+{"step": 19820, "dynamics_loss_avg": 0.029494157806038857}
+{"step": 19820, "action_loss_avg": 0.00352294368785806}
+{"step": 19830, "dynamics_loss_avg": 0.026746342424303293}
+{"step": 19830, "action_loss_avg": 0.0026273054070770742}
+{"step": 19840, "dynamics_loss_avg": 0.03608057200908661}
+{"step": 19840, "action_loss_avg": 0.0036585118621587755}
+{"step": 19850, "loss": 0.0362, "learning_rate": 9.409197049141637e-05}
+{"step": 19850, "dynamics_loss_avg": 0.0362100001424551}
+{"step": 19850, "action_loss_avg": 0.0040957765653729435}
+{"step": 19860, "dynamics_loss_avg": 0.031843940168619154}
+{"step": 19860, "action_loss_avg": 0.0037862508848775177}
+{"step": 19870, "dynamics_loss_avg": 0.03268654644489288}
+{"step": 19870, "action_loss_avg": 0.003727649082429707}
+{"step": 19880, "dynamics_loss_avg": 0.03954752665013075}
+{"step": 19880, "action_loss_avg": 0.004736308625433594}
+{"step": 19890, "dynamics_loss_avg": 0.03323723031207919}
+{"step": 19890, "action_loss_avg": 0.003504405089188367}
+{"step": 19900, "loss": 0.0337, "learning_rate": 9.405292556457805e-05}
+{"step": 19900, "dynamics_loss_avg": 0.031630749069154265}
+{"step": 19900, "action_loss_avg": 0.00334440590813756}
+{"step": 19910, "dynamics_loss_avg": 0.033290321566164495}
+{"step": 19910, "action_loss_avg": 0.004205344640649855}
+{"step": 19920, "dynamics_loss_avg": 0.031660873675718904}
+{"step": 19920, "action_loss_avg": 0.003573038149625063}
+{"step": 19930, "dynamics_loss_avg": 0.03263698080554604}
+{"step": 19930, "action_loss_avg": 0.004228187503758818}
+{"step": 19940, "dynamics_loss_avg": 0.034047032706439495}
+{"step": 19940, "action_loss_avg": 0.003791685914620757}
+{"step": 19950, "loss": 0.0353, "learning_rate": 9.401376019872338e-05}
+{"step": 19950, "dynamics_loss_avg": 0.0268885082565248}
+{"step": 19950, "action_loss_avg": 0.0031144373351708055}
+{"step": 19960, "dynamics_loss_avg": 0.034496540762484075}
+{"step": 19960, "action_loss_avg": 0.003812537912745029}
+{"step": 19970, "dynamics_loss_avg": 0.03750097742304206}
+{"step": 19970, "action_loss_avg": 0.005477745202369988}
+{"step": 19980, "dynamics_loss_avg": 0.034347439929842946}
+{"step": 19980, "action_loss_avg": 0.004436678963247687}
+{"step": 19990, "dynamics_loss_avg": 0.03224763944745064}
+{"step": 19990, "action_loss_avg": 0.00351446884451434}
+{"step": 20000, "loss": 0.0364, "learning_rate": 9.397447450092902e-05}
+{"step": 20000, "dynamics_loss_avg": 0.03647715002298355}
+{"step": 20000, "action_loss_avg": 0.00391030126484111}
+{"step": 20010, "dynamics_loss_avg": 0.029330427572131158}
+{"step": 20010, "action_loss_avg": 0.0032042320439359174}
+{"step": 20020, "dynamics_loss_avg": 0.033773138746619226}
+{"step": 20020, "action_loss_avg": 0.004265322664286942}
+{"step": 20030, "dynamics_loss_avg": 0.024951803032308817}
+{"step": 20030, "action_loss_avg": 0.003230916883330792}
+{"step": 20040, "dynamics_loss_avg": 0.027205851254984738}
+{"step": 20040, "action_loss_avg": 0.0030361024546436965}
+{"step": 20050, "loss": 0.0325, "learning_rate": 9.393506857860052e-05}
+{"step": 20050, "dynamics_loss_avg": 0.027215636614710093}
+{"step": 20050, "action_loss_avg": 0.0036047515168320388}
+{"step": 20060, "dynamics_loss_avg": 0.028657976351678372}
+{"step": 20060, "action_loss_avg": 0.00375073003815487}
+{"step": 20070, "dynamics_loss_avg": 0.038968770578503606}
+{"step": 20070, "action_loss_avg": 0.0047048060456290845}
+{"step": 20080, "dynamics_loss_avg": 0.041732806153595446}
+{"step": 20080, "action_loss_avg": 0.004527718317694962}
+{"step": 20090, "dynamics_loss_avg": 0.028560567274689676}
+{"step": 20090, "action_loss_avg": 0.0034744753735139965}
+{"step": 20100, "loss": 0.0361, "learning_rate": 9.389554253947219e-05}
+{"step": 20100, "dynamics_loss_avg": 0.0352034536190331}
+{"step": 20100, "action_loss_avg": 0.0030118669965304434}
+{"step": 20110, "dynamics_loss_avg": 0.0337705297395587}
+{"step": 20110, "action_loss_avg": 0.004427589057013392}
+{"step": 20120, "dynamics_loss_avg": 0.03208163222298026}
+{"step": 20120, "action_loss_avg": 0.004025729314889759}
+{"step": 20130, "dynamics_loss_avg": 0.03564019706100226}
+{"step": 20130, "action_loss_avg": 0.004360964545048774}
+{"step": 20140, "dynamics_loss_avg": 0.026434651110321283}
+{"step": 20140, "action_loss_avg": 0.0029664420668268575}
+{"step": 20150, "loss": 0.0347, "learning_rate": 9.385589649160669e-05}
+{"step": 20150, "dynamics_loss_avg": 0.03531237207353115}
+{"step": 20150, "action_loss_avg": 0.004408587724901736}
+{"step": 20160, "dynamics_loss_avg": 0.021917233150452374}
+{"step": 20160, "action_loss_avg": 0.002505908033344895}
+{"step": 20170, "dynamics_loss_avg": 0.030619498528540134}
+{"step": 20170, "action_loss_avg": 0.005337795370724052}
+{"step": 20180, "dynamics_loss_avg": 0.034315197914838794}
+{"step": 20180, "action_loss_avg": 0.003884341719094664}
+{"step": 20190, "dynamics_loss_avg": 0.031124909315258263}
+{"step": 20190, "action_loss_avg": 0.0044330939883366225}
+{"step": 20200, "loss": 0.0314, "learning_rate": 9.381613054339482e-05}
+{"step": 20200, "dynamics_loss_avg": 0.030535085406154395}
+{"step": 20200, "action_loss_avg": 0.0021614925470203163}
+{"step": 20210, "dynamics_loss_avg": 0.022703070752322675}
+{"step": 20210, "action_loss_avg": 0.001949844672344625}
+{"step": 20220, "dynamics_loss_avg": 0.0364909409545362}
+{"step": 20220, "action_loss_avg": 0.003823903843294829}
+{"step": 20230, "dynamics_loss_avg": 0.0268094084225595}
+{"step": 20230, "action_loss_avg": 0.002548422140534967}
+{"step": 20240, "dynamics_loss_avg": 0.031363616790622474}
+{"step": 20240, "action_loss_avg": 0.0030196472187526526}
+{"step": 20250, "loss": 0.0344, "learning_rate": 9.377624480355517e-05}
+{"step": 20250, "dynamics_loss_avg": 0.03855058485642075}
+{"step": 20250, "action_loss_avg": 0.004096995783038437}
+{"step": 20260, "dynamics_loss_avg": 0.030780014488846062}
+{"step": 20260, "action_loss_avg": 0.003179955715313554}
+{"step": 20270, "dynamics_loss_avg": 0.030348426848649978}
+{"step": 20270, "action_loss_avg": 0.003637112386059016}
+{"step": 20280, "dynamics_loss_avg": 0.028484941087663175}
+{"step": 20280, "action_loss_avg": 0.0029444671235978603}
+{"step": 20290, "dynamics_loss_avg": 0.03632962545379996}
+{"step": 20290, "action_loss_avg": 0.004375989839900285}
+{"step": 20300, "loss": 0.0347, "learning_rate": 9.373623938113381e-05}
+{"step": 20300, "dynamics_loss_avg": 0.038519976660609245}
+{"step": 20300, "action_loss_avg": 0.0047694117180071775}
+{"step": 20310, "dynamics_loss_avg": 0.030311894416809083}
+{"step": 20310, "action_loss_avg": 0.0035735258599743245}
+{"step": 20320, "dynamics_loss_avg": 0.03473742511123419}
+{"step": 20320, "action_loss_avg": 0.0034893118077889084}
+{"step": 20330, "dynamics_loss_avg": 0.033503223303705455}
+{"step": 20330, "action_loss_avg": 0.003813466272549704}
+{"step": 20340, "dynamics_loss_avg": 0.03540509194135666}
+{"step": 20340, "action_loss_avg": 0.00465176971629262}
+{"step": 20350, "loss": 0.035, "learning_rate": 9.369611438550406e-05}
+{"step": 20350, "dynamics_loss_avg": 0.039393319841474296}
+{"step": 20350, "action_loss_avg": 0.003136573126539588}
+{"step": 20360, "dynamics_loss_avg": 0.029746889136731625}
+{"step": 20360, "action_loss_avg": 0.00274280589655973}
+{"step": 20370, "dynamics_loss_avg": 0.03984561404213309}
+{"step": 20370, "action_loss_avg": 0.004867679323069751}
+{"step": 20380, "dynamics_loss_avg": 0.03678207695484161}
+{"step": 20380, "action_loss_avg": 0.005153544107452035}
+{"step": 20390, "dynamics_loss_avg": 0.030952082481235266}
+{"step": 20390, "action_loss_avg": 0.003955885430332273}
+{"step": 20400, "loss": 0.0387, "learning_rate": 9.365586992636607e-05}
+{"step": 20400, "dynamics_loss_avg": 0.04474776592105627}
+{"step": 20400, "action_loss_avg": 0.005874100816436112}
+{"step": 20410, "dynamics_loss_avg": 0.03139796354807913}
+{"step": 20410, "action_loss_avg": 0.005231999381794594}
+{"step": 20420, "dynamics_loss_avg": 0.025213391333818436}
+{"step": 20420, "action_loss_avg": 0.003861685225274414}
+{"step": 20430, "dynamics_loss_avg": 0.03127491567283869}
+{"step": 20430, "action_loss_avg": 0.004431342298630625}
+{"step": 20440, "dynamics_loss_avg": 0.0331668390892446}
+{"step": 20440, "action_loss_avg": 0.004438992100767791}
+{"step": 20450, "loss": 0.0348, "learning_rate": 9.361550611374674e-05}
+{"step": 20450, "dynamics_loss_avg": 0.032155401166528465}
+{"step": 20450, "action_loss_avg": 0.003704101650509983}
+{"step": 20460, "dynamics_loss_avg": 0.04300290159881115}
+{"step": 20460, "action_loss_avg": 0.00475309801986441}
+{"step": 20470, "dynamics_loss_avg": 0.036706832516938445}
+{"step": 20470, "action_loss_avg": 0.003904040460474789}
+{"step": 20480, "dynamics_loss_avg": 0.028805005457252265}
+{"step": 20480, "action_loss_avg": 0.003576393274124712}
+{"step": 20490, "dynamics_loss_avg": 0.03691822178661823}
+{"step": 20490, "action_loss_avg": 0.0054381215712055566}
+{"step": 20500, "loss": 0.0375, "learning_rate": 9.357502305799914e-05}
+{"step": 20500, "dynamics_loss_avg": 0.03438241211697459}
+{"step": 20500, "action_loss_avg": 0.0037564791506156324}
+{"step": 20510, "dynamics_loss_avg": 0.03263692818582058}
+{"step": 20510, "action_loss_avg": 0.004208332143025473}
+{"step": 20520, "dynamics_loss_avg": 0.029601682908833027}
+{"step": 20520, "action_loss_avg": 0.003931080317124724}
+{"step": 20530, "dynamics_loss_avg": 0.033796982187777755}
+{"step": 20530, "action_loss_avg": 0.003999552800087259}
+{"step": 20540, "dynamics_loss_avg": 0.04483408462256193}
+{"step": 20540, "action_loss_avg": 0.004407623992301523}
+{"step": 20550, "loss": 0.0339, "learning_rate": 9.353442086980239e-05}
+{"step": 20550, "dynamics_loss_avg": 0.03203849634155631}
+{"step": 20550, "action_loss_avg": 0.0037869136314839123}
+{"step": 20560, "dynamics_loss_avg": 0.030968455784022807}
+{"step": 20560, "action_loss_avg": 0.004068866255693138}
+{"step": 20570, "dynamics_loss_avg": 0.03440741682425141}
+{"step": 20570, "action_loss_avg": 0.0034525916213169693}
+{"step": 20580, "dynamics_loss_avg": 0.03216201644390822}
+{"step": 20580, "action_loss_avg": 0.003954035404603928}
+{"step": 20590, "dynamics_loss_avg": 0.03537150751799345}
+{"step": 20590, "action_loss_avg": 0.004306228412315249}
+{"step": 20600, "loss": 0.0344, "learning_rate": 9.349369966016134e-05}
+{"step": 20600, "dynamics_loss_avg": 0.036008306220173834}
+{"step": 20600, "action_loss_avg": 0.0031093777739442884}
+{"step": 20610, "dynamics_loss_avg": 0.037333871237933636}
+{"step": 20610, "action_loss_avg": 0.003888622159138322}
+{"step": 20620, "dynamics_loss_avg": 0.029287556931376458}
+{"step": 20620, "action_loss_avg": 0.0034045547188725324}
+{"step": 20630, "dynamics_loss_avg": 0.028408444952219725}
+{"step": 20630, "action_loss_avg": 0.002871699328534305}
+{"step": 20640, "dynamics_loss_avg": 0.025371826998889447}
+{"step": 20640, "action_loss_avg": 0.001969253004062921}
+{"step": 20650, "loss": 0.0326, "learning_rate": 9.345285954040626e-05}
+{"step": 20650, "dynamics_loss_avg": 0.026337641570717097}
+{"step": 20650, "action_loss_avg": 0.0030993221909739075}
+{"step": 20660, "dynamics_loss_avg": 0.03807076020166278}
+{"step": 20660, "action_loss_avg": 0.004248279030434787}
+{"step": 20670, "dynamics_loss_avg": 0.03798417821526527}
+{"step": 20670, "action_loss_avg": 0.004097324830945581}
+{"step": 20680, "dynamics_loss_avg": 0.032977907080203296}
+{"step": 20680, "action_loss_avg": 0.004205802315846085}
+{"step": 20690, "dynamics_loss_avg": 0.040684057679027316}
+{"step": 20690, "action_loss_avg": 0.0043959305272437636}
+{"step": 20700, "loss": 0.037, "learning_rate": 9.34119006221924e-05}
+{"step": 20700, "dynamics_loss_avg": 0.03241456914693117}
+{"step": 20700, "action_loss_avg": 0.003977987088728696}
+{"step": 20710, "dynamics_loss_avg": 0.03944372236728668}
+{"step": 20710, "action_loss_avg": 0.004858808382414282}
+{"step": 20720, "dynamics_loss_avg": 0.04987036492675543}
+{"step": 20720, "action_loss_avg": 0.005447740841191262}
+{"step": 20730, "dynamics_loss_avg": 0.03589744623750448}
+{"step": 20730, "action_loss_avg": 0.003588010766543448}
+{"step": 20740, "dynamics_loss_avg": 0.03009708086028695}
+{"step": 20740, "action_loss_avg": 0.0032465452328324317}
+{"step": 20750, "loss": 0.0372, "learning_rate": 9.337082301749993e-05}
+{"step": 20750, "dynamics_loss_avg": 0.025823293812572957}
+{"step": 20750, "action_loss_avg": 0.0027534774970263244}
+{"step": 20760, "dynamics_loss_avg": 0.027278297301381826}
+{"step": 20760, "action_loss_avg": 0.002971786819398403}
+{"step": 20770, "dynamics_loss_avg": 0.04065690152347088}
+{"step": 20770, "action_loss_avg": 0.005401441175490618}
+{"step": 20780, "dynamics_loss_avg": 0.028085622657090425}
+{"step": 20780, "action_loss_avg": 0.0032506752759218216}
+{"step": 20790, "dynamics_loss_avg": 0.03814282091334462}
+{"step": 20790, "action_loss_avg": 0.004324634396471083}
+{"step": 20800, "loss": 0.0331, "learning_rate": 9.332962683863345e-05}
+{"step": 20800, "dynamics_loss_avg": 0.02751388242468238}
+{"step": 20800, "action_loss_avg": 0.003654276777524501}
+{"step": 20810, "dynamics_loss_avg": 0.03693157564848661}
+{"step": 20810, "action_loss_avg": 0.004710990161402151}
+{"step": 20820, "dynamics_loss_avg": 0.025861504999920727}
+{"step": 20820, "action_loss_avg": 0.0030520775879267605}
+{"step": 20830, "dynamics_loss_avg": 0.04681598786264658}
+{"step": 20830, "action_loss_avg": 0.006329102953895926}
+{"step": 20840, "dynamics_loss_avg": 0.0302885502576828}
+{"step": 20840, "action_loss_avg": 0.0038042865809984503}
+{"step": 20850, "loss": 0.0351, "learning_rate": 9.328831219822172e-05}
+{"step": 20850, "dynamics_loss_avg": 0.032336215302348134}
+{"step": 20850, "action_loss_avg": 0.004212921520229429}
+{"step": 20860, "dynamics_loss_avg": 0.03069389285519719}
+{"step": 20860, "action_loss_avg": 0.0031024150433950127}
+{"step": 20870, "dynamics_loss_avg": 0.03942097388207912}
+{"step": 20870, "action_loss_avg": 0.003445067908614874}
+{"step": 20880, "dynamics_loss_avg": 0.041288741305470465}
+{"step": 20880, "action_loss_avg": 0.003969518013764173}
+{"step": 20890, "dynamics_loss_avg": 0.03988002277910709}
+{"step": 20890, "action_loss_avg": 0.004535065032541752}
+{"step": 20900, "loss": 0.0362, "learning_rate": 9.32468792092174e-05}
+{"step": 20900, "dynamics_loss_avg": 0.03173918444663286}
+{"step": 20900, "action_loss_avg": 0.0036507123964838683}
+{"step": 20910, "dynamics_loss_avg": 0.028508714493364097}
+{"step": 20910, "action_loss_avg": 0.002627220714930445}
+{"step": 20920, "dynamics_loss_avg": 0.033572951517999175}
+{"step": 20920, "action_loss_avg": 0.0033643274335190656}
+{"step": 20930, "dynamics_loss_avg": 0.04040247369557619}
+{"step": 20930, "action_loss_avg": 0.003362496674526483}
+{"step": 20940, "dynamics_loss_avg": 0.03524815887212753}
+{"step": 20940, "action_loss_avg": 0.004087636363692582}
+{"step": 20950, "loss": 0.0349, "learning_rate": 9.32053279848967e-05}
+{"step": 20950, "dynamics_loss_avg": 0.029093139711767434}
+{"step": 20950, "action_loss_avg": 0.003216497728135437}
+{"step": 20960, "dynamics_loss_avg": 0.03382926881313324}
+{"step": 20960, "action_loss_avg": 0.0032268090697471054}
+{"step": 20970, "dynamics_loss_avg": 0.03635786138474941}
+{"step": 20970, "action_loss_avg": 0.003399542940314859}
+{"step": 20980, "dynamics_loss_avg": 0.03066838178783655}
+{"step": 20980, "action_loss_avg": 0.003570665733423084}
+{"step": 20990, "dynamics_loss_avg": 0.03665169747546315}
+{"step": 20990, "action_loss_avg": 0.0028912173816934227}
+{"step": 21000, "loss": 0.0339, "learning_rate": 9.316365863885909e-05}
+{"step": 21000, "dynamics_loss_avg": 0.039573057740926745}
+{"step": 21000, "action_loss_avg": 0.0043931188061833385}
+{"step": 21010, "dynamics_loss_avg": 0.03919472265988588}
+{"step": 21010, "action_loss_avg": 0.0034427751321345567}
+{"step": 21020, "dynamics_loss_avg": 0.027048716228455304}
+{"step": 21020, "action_loss_avg": 0.0027229009428992867}
+{"step": 21030, "dynamics_loss_avg": 0.027888880018144845}
+{"step": 21030, "action_loss_avg": 0.0026377547939773647}
+{"step": 21040, "dynamics_loss_avg": 0.035338603891432285}
+{"step": 21040, "action_loss_avg": 0.004199439907097258}
+{"step": 21050, "loss": 0.0346, "learning_rate": 9.312187128502695e-05}
+{"step": 21050, "dynamics_loss_avg": 0.032554034143686295}
+{"step": 21050, "action_loss_avg": 0.005316120176576078}
+{"step": 21060, "dynamics_loss_avg": 0.03194562289863825}
+{"step": 21060, "action_loss_avg": 0.0029979537473991515}
+{"step": 21070, "dynamics_loss_avg": 0.02946962248533964}
+{"step": 21070, "action_loss_avg": 0.00368833759566769}
+{"step": 21080, "dynamics_loss_avg": 0.04022963279858231}
+{"step": 21080, "action_loss_avg": 0.004142118006711826}
+{"step": 21090, "dynamics_loss_avg": 0.02996945260092616}
+{"step": 21090, "action_loss_avg": 0.0026704823481850325}
+{"step": 21100, "loss": 0.0345, "learning_rate": 9.307996603764533e-05}
+{"step": 21100, "dynamics_loss_avg": 0.027261324878782033}
+{"step": 21100, "action_loss_avg": 0.003184753889217973}
+{"step": 21110, "dynamics_loss_avg": 0.028185166697949172}
+{"step": 21110, "action_loss_avg": 0.0045869828027207404}
+{"step": 21120, "dynamics_loss_avg": 0.03808300085365772}
+{"step": 21120, "action_loss_avg": 0.0043195552658289674}
+{"step": 21130, "dynamics_loss_avg": 0.02333739008754492}
+{"step": 21130, "action_loss_avg": 0.0032965973485261204}
+{"step": 21140, "dynamics_loss_avg": 0.026947239600121974}
+{"step": 21140, "action_loss_avg": 0.003079738322412595}
+{"step": 21150, "loss": 0.0345, "learning_rate": 9.303794301128157e-05}
+{"step": 21150, "dynamics_loss_avg": 0.037202317733317614}
+{"step": 21150, "action_loss_avg": 0.003870722930878401}
+{"step": 21160, "dynamics_loss_avg": 0.02687625475227833}
+{"step": 21160, "action_loss_avg": 0.0030021408980246632}
+{"step": 21170, "dynamics_loss_avg": 0.02525141052901745}
+{"step": 21170, "action_loss_avg": 0.002584949368610978}
+{"step": 21180, "dynamics_loss_avg": 0.0395753750577569}
+{"step": 21180, "action_loss_avg": 0.005050921952351928}
+{"step": 21190, "dynamics_loss_avg": 0.03989140260964632}
+{"step": 21190, "action_loss_avg": 0.004763113358058036}
+{"step": 21200, "loss": 0.0358, "learning_rate": 9.299580232082501e-05}
+{"step": 21200, "dynamics_loss_avg": 0.03397406658623368}
+{"step": 21200, "action_loss_avg": 0.003276475542224944}
+{"step": 21210, "dynamics_loss_avg": 0.031290050595998764}
+{"step": 21210, "action_loss_avg": 0.0030143516254611314}
+{"step": 21220, "dynamics_loss_avg": 0.0419432532042265}
+{"step": 21220, "action_loss_avg": 0.005492675676941871}
+{"step": 21230, "dynamics_loss_avg": 0.03793794894590974}
+{"step": 21230, "action_loss_avg": 0.004911669390276074}
+{"step": 21240, "dynamics_loss_avg": 0.0380430749617517}
+{"step": 21240, "action_loss_avg": 0.004695565043948591}
+{"step": 21250, "loss": 0.0372, "learning_rate": 9.295354408148668e-05}
+{"step": 21250, "dynamics_loss_avg": 0.034498894959688185}
+{"step": 21250, "action_loss_avg": 0.00410794576164335}
+{"step": 21260, "dynamics_loss_avg": 0.028186861146241426}
+{"step": 21260, "action_loss_avg": 0.003539314866065979}
+{"step": 21270, "dynamics_loss_avg": 0.034646394103765486}
+{"step": 21270, "action_loss_avg": 0.0029775159433484077}
+{"step": 21280, "dynamics_loss_avg": 0.03173407018184662}
+{"step": 21280, "action_loss_avg": 0.0034788350574672224}
+{"step": 21290, "dynamics_loss_avg": 0.030608637956902385}
+{"step": 21290, "action_loss_avg": 0.0028632438858039676}
+{"step": 21300, "loss": 0.0352, "learning_rate": 9.291116840879904e-05}
+{"step": 21300, "dynamics_loss_avg": 0.041316602285951375}
+{"step": 21300, "action_loss_avg": 0.005672045610845089}
+{"step": 21310, "dynamics_loss_avg": 0.03428497835993767}
+{"step": 21310, "action_loss_avg": 0.00461561445845291}
+{"step": 21320, "dynamics_loss_avg": 0.02651329981163144}
+{"step": 21320, "action_loss_avg": 0.0025156600517220796}
+{"step": 21330, "dynamics_loss_avg": 0.03712091697379947}
+{"step": 21330, "action_loss_avg": 0.004699406155850738}
+{"step": 21340, "dynamics_loss_avg": 0.029066858254373072}
+{"step": 21340, "action_loss_avg": 0.002587418066104874}
+{"step": 21350, "loss": 0.0348, "learning_rate": 9.28686754186155e-05}
+{"step": 21350, "dynamics_loss_avg": 0.03676069490611553}
+{"step": 21350, "action_loss_avg": 0.0037248441949486732}
+{"step": 21360, "dynamics_loss_avg": 0.024217696394771338}
+{"step": 21360, "action_loss_avg": 0.002655722462804988}
+{"step": 21370, "dynamics_loss_avg": 0.039693175721913575}
+{"step": 21370, "action_loss_avg": 0.003581487713381648}
+{"step": 21380, "dynamics_loss_avg": 0.03455727770924568}
+{"step": 21380, "action_loss_avg": 0.00444086124189198}
+{"step": 21390, "dynamics_loss_avg": 0.03655142728239298}
+{"step": 21390, "action_loss_avg": 0.003914414619794115}
+{"step": 21400, "loss": 0.0344, "learning_rate": 9.282606522711033e-05}
+{"step": 21400, "dynamics_loss_avg": 0.03625415079295635}
+{"step": 21400, "action_loss_avg": 0.003749200631864369}
+{"step": 21410, "dynamics_loss_avg": 0.039052085112780334}
+{"step": 21410, "action_loss_avg": 0.004021177015965804}
+{"step": 21420, "dynamics_loss_avg": 0.03405179856345057}
+{"step": 21420, "action_loss_avg": 0.004547963425284252}
+{"step": 21430, "dynamics_loss_avg": 0.0322481126524508}
+{"step": 21430, "action_loss_avg": 0.00399554556934163}
+{"step": 21440, "dynamics_loss_avg": 0.03970581833273172}
+{"step": 21440, "action_loss_avg": 0.004608309624018148}
+{"step": 21450, "loss": 0.0376, "learning_rate": 9.278333795077812e-05}
+{"step": 21450, "dynamics_loss_avg": 0.0285098098218441}
+{"step": 21450, "action_loss_avg": 0.0027738010161556304}
+{"step": 21460, "dynamics_loss_avg": 0.03676458951085806}
+{"step": 21460, "action_loss_avg": 0.005800862621981651}
+{"step": 21470, "dynamics_loss_avg": 0.032559415232390164}
+{"step": 21470, "action_loss_avg": 0.005390982376411557}
+{"step": 21480, "dynamics_loss_avg": 0.03513406906276941}
+{"step": 21480, "action_loss_avg": 0.004319332027807832}
+{"step": 21490, "dynamics_loss_avg": 0.04645466785877943}
+{"step": 21490, "action_loss_avg": 0.005043594527523965}
+{"step": 21500, "loss": 0.0357, "learning_rate": 9.274049370643363e-05}
+{"step": 21500, "dynamics_loss_avg": 0.037603871710598466}
+{"step": 21500, "action_loss_avg": 0.0044671417446807025}
+{"step": 21510, "dynamics_loss_avg": 0.03669079765677452}
+{"step": 21510, "action_loss_avg": 0.004805307136848569}
+{"step": 21520, "dynamics_loss_avg": 0.03488879939541221}
+{"step": 21520, "action_loss_avg": 0.005566887161694467}
+{"step": 21530, "dynamics_loss_avg": 0.03947615260258317}
+{"step": 21530, "action_loss_avg": 0.004940283874748275}
+{"step": 21540, "dynamics_loss_avg": 0.027525841491296887}
+{"step": 21540, "action_loss_avg": 0.0028806435875594616}
+{"step": 21550, "loss": 0.0369, "learning_rate": 9.269753261121138e-05}
+{"step": 21550, "dynamics_loss_avg": 0.0351802634075284}
+{"step": 21550, "action_loss_avg": 0.004174218920525163}
+{"step": 21560, "dynamics_loss_avg": 0.023043327126652004}
+{"step": 21560, "action_loss_avg": 0.0034013788215816023}
+{"step": 21570, "dynamics_loss_avg": 0.037990132719278334}
+{"step": 21570, "action_loss_avg": 0.003927473328076303}
+{"step": 21580, "dynamics_loss_avg": 0.02598769422620535}
+{"step": 21580, "action_loss_avg": 0.0030405794619582593}
+{"step": 21590, "dynamics_loss_avg": 0.0291866990737617}
+{"step": 21590, "action_loss_avg": 0.0027194193098694086}
+{"step": 21600, "loss": 0.0344, "learning_rate": 9.26544547825654e-05}
+{"step": 21600, "dynamics_loss_avg": 0.03963523358106613}
+{"step": 21600, "action_loss_avg": 0.0035378302738536148}
+{"step": 21610, "dynamics_loss_avg": 0.03761973492801189}
+{"step": 21610, "action_loss_avg": 0.0038147131213918327}
+{"step": 21620, "dynamics_loss_avg": 0.038887844420969486}
+{"step": 21620, "action_loss_avg": 0.005077699339017272}
+{"step": 21630, "dynamics_loss_avg": 0.036516040563583374}
+{"step": 21630, "action_loss_avg": 0.004221240128390491}
+{"step": 21640, "dynamics_loss_avg": 0.029691678844392298}
+{"step": 21640, "action_loss_avg": 0.0031392071628943085}
+{"step": 21650, "loss": 0.0363, "learning_rate": 9.261126033826878e-05}
+{"step": 21650, "dynamics_loss_avg": 0.03561290670186281}
+{"step": 21650, "action_loss_avg": 0.004455032816622406}
+{"step": 21660, "dynamics_loss_avg": 0.0377725712954998}
+{"step": 21660, "action_loss_avg": 0.0035832950496114792}
+{"step": 21670, "dynamics_loss_avg": 0.0403579662553966}
+{"step": 21670, "action_loss_avg": 0.004029387841001153}
+{"step": 21680, "dynamics_loss_avg": 0.03602925315499306}
+{"step": 21680, "action_loss_avg": 0.003204981645103544}
+{"step": 21690, "dynamics_loss_avg": 0.03045941162854433}
+{"step": 21690, "action_loss_avg": 0.002953482139855623}
+{"step": 21700, "loss": 0.0358, "learning_rate": 9.25679493964135e-05}
+{"step": 21700, "dynamics_loss_avg": 0.02535742283798754}
+{"step": 21700, "action_loss_avg": 0.002729768882272765}
+{"step": 21710, "dynamics_loss_avg": 0.03411249537020922}
+{"step": 21710, "action_loss_avg": 0.0035614621941931547}
+{"step": 21720, "dynamics_loss_avg": 0.031370050739496946}
+{"step": 21720, "action_loss_avg": 0.0028311938338447364}
+{"step": 21730, "dynamics_loss_avg": 0.03228568285703659}
+{"step": 21730, "action_loss_avg": 0.0025507808779366313}
+{"step": 21740, "dynamics_loss_avg": 0.030890109576284887}
+{"step": 21740, "action_loss_avg": 0.002612390602007508}
+{"step": 21750, "loss": 0.035, "learning_rate": 9.252452207541004e-05}
+{"step": 21750, "dynamics_loss_avg": 0.020439006574451923}
+{"step": 21750, "action_loss_avg": 0.0021072128671221434}
+{"step": 21760, "dynamics_loss_avg": 0.024891915265470743}
+{"step": 21760, "action_loss_avg": 0.0032644722086843103}
+{"step": 21770, "dynamics_loss_avg": 0.031100309640169143}
+{"step": 21770, "action_loss_avg": 0.002966932428535074}
+{"step": 21780, "dynamics_loss_avg": 0.03253281228244305}
+{"step": 21780, "action_loss_avg": 0.003663314669393003}
+{"step": 21790, "dynamics_loss_avg": 0.029897972568869592}
+{"step": 21790, "action_loss_avg": 0.003110615024343133}
+{"step": 21800, "loss": 0.0342, "learning_rate": 9.2480978493987e-05}
+{"step": 21800, "dynamics_loss_avg": 0.02448902577161789}
+{"step": 21800, "action_loss_avg": 0.003260482510086149}
+{"step": 21810, "dynamics_loss_avg": 0.029078207165002822}
+{"step": 21810, "action_loss_avg": 0.0038599056657403707}
+{"step": 21820, "dynamics_loss_avg": 0.03838403355330229}
+{"step": 21820, "action_loss_avg": 0.0032549686846323313}
+{"step": 21830, "dynamics_loss_avg": 0.029639293253421784}
+{"step": 21830, "action_loss_avg": 0.003114203957375139}
+{"step": 21840, "dynamics_loss_avg": 0.029226574674248697}
+{"step": 21840, "action_loss_avg": 0.0033466146618593485}
+{"step": 21850, "loss": 0.0356, "learning_rate": 9.24373187711909e-05}
+{"step": 21850, "dynamics_loss_avg": 0.028642617352306842}
+{"step": 21850, "action_loss_avg": 0.004045305505860597}
+{"step": 21860, "dynamics_loss_avg": 0.045522636454552415}
+{"step": 21860, "action_loss_avg": 0.004835759324487298}
+{"step": 21870, "dynamics_loss_avg": 0.03365168608725071}
+{"step": 21870, "action_loss_avg": 0.004327420226763934}
+{"step": 21880, "dynamics_loss_avg": 0.032989584095776084}
+{"step": 21880, "action_loss_avg": 0.005121228040661663}
+{"step": 21890, "dynamics_loss_avg": 0.03954697605222464}
+{"step": 21890, "action_loss_avg": 0.00441454192623496}
+{"step": 21900, "loss": 0.0394, "learning_rate": 9.239354302638575e-05}
+{"step": 21900, "dynamics_loss_avg": 0.029803286679089068}
+{"step": 21900, "action_loss_avg": 0.0029101471416652204}
+{"step": 21910, "dynamics_loss_avg": 0.03579032802954316}
+{"step": 21910, "action_loss_avg": 0.004584559157956391}
+{"step": 21920, "dynamics_loss_avg": 0.027572548016905785}
+{"step": 21920, "action_loss_avg": 0.0024818130244966597}
+{"step": 21930, "dynamics_loss_avg": 0.03253845577128232}
+{"step": 21930, "action_loss_avg": 0.002832127513829619}
+{"step": 21940, "dynamics_loss_avg": 0.038820124324411155}
+{"step": 21940, "action_loss_avg": 0.003723749506752938}
+{"step": 21950, "loss": 0.0373, "learning_rate": 9.234965137925276e-05}
+{"step": 21950, "dynamics_loss_avg": 0.02872317312285304}
+{"step": 21950, "action_loss_avg": 0.0025465752463787795}
+{"step": 21960, "dynamics_loss_avg": 0.028306233696639538}
+{"step": 21960, "action_loss_avg": 0.0022868358035339044}
+{"step": 21970, "dynamics_loss_avg": 0.04190140552818775}
+{"step": 21970, "action_loss_avg": 0.0034371939342236145}
+{"step": 21980, "dynamics_loss_avg": 0.04195603467524052}
+{"step": 21980, "action_loss_avg": 0.0037959498702548446}
+{"step": 21990, "dynamics_loss_avg": 0.038478631619364025}
+{"step": 21990, "action_loss_avg": 0.004030188231263309}
+{"step": 22000, "loss": 0.0358, "learning_rate": 9.230564394979e-05}
+{"step": 22000, "dynamics_loss_avg": 0.037206010846421125}
+{"step": 22000, "action_loss_avg": 0.0033432199968956413}
+{"step": 22010, "dynamics_loss_avg": 0.04135760739445686}
+{"step": 22010, "action_loss_avg": 0.00462152196560055}
+{"step": 22020, "dynamics_loss_avg": 0.030784550961107014}
+{"step": 22020, "action_loss_avg": 0.0021898630366194993}
+{"step": 22030, "dynamics_loss_avg": 0.03519781893119216}
+{"step": 22030, "action_loss_avg": 0.003930134430993349}
+{"step": 22040, "dynamics_loss_avg": 0.03714001588523388}
+{"step": 22040, "action_loss_avg": 0.004418334120418877}
+{"step": 22050, "loss": 0.0349, "learning_rate": 9.226152085831213e-05}
+{"step": 22050, "dynamics_loss_avg": 0.033426524698734285}
+{"step": 22050, "action_loss_avg": 0.0037982966867275538}
+{"step": 22060, "dynamics_loss_avg": 0.03922803280875087}
+{"step": 22060, "action_loss_avg": 0.004628844477701932}
+{"step": 22070, "dynamics_loss_avg": 0.034664497897028926}
+{"step": 22070, "action_loss_avg": 0.004307358001824468}
+{"step": 22080, "dynamics_loss_avg": 0.03306812597438693}
+{"step": 22080, "action_loss_avg": 0.0032429922372102737}
+{"step": 22090, "dynamics_loss_avg": 0.031148426234722137}
+{"step": 22090, "action_loss_avg": 0.003183662344235927}
+{"step": 22100, "loss": 0.034, "learning_rate": 9.221728222544999e-05}
+{"step": 22100, "dynamics_loss_avg": 0.035688907653093335}
+{"step": 22100, "action_loss_avg": 0.00330673890421167}
+{"step": 22110, "dynamics_loss_avg": 0.03184650940820575}
+{"step": 22110, "action_loss_avg": 0.0034588190028443933}
+{"step": 22120, "dynamics_loss_avg": 0.029834113363176585}
+{"step": 22120, "action_loss_avg": 0.003961535438429564}
+{"step": 22130, "dynamics_loss_avg": 0.032441561575978994}
+{"step": 22130, "action_loss_avg": 0.003632678429130465}
+{"step": 22140, "dynamics_loss_avg": 0.038868930842727425}
+{"step": 22140, "action_loss_avg": 0.004361624433659017}
+{"step": 22150, "loss": 0.034, "learning_rate": 9.21729281721503e-05}
+{"step": 22150, "dynamics_loss_avg": 0.025338347442448138}
+{"step": 22150, "action_loss_avg": 0.0023543810879345984}
+{"step": 22160, "dynamics_loss_avg": 0.04342014333233237}
+{"step": 22160, "action_loss_avg": 0.003971228562295437}
+{"step": 22170, "dynamics_loss_avg": 0.02765272120013833}
+{"step": 22170, "action_loss_avg": 0.002892593154683709}
+{"step": 22180, "dynamics_loss_avg": 0.03454245515167713}
+{"step": 22180, "action_loss_avg": 0.0028217357117682695}
+{"step": 22190, "dynamics_loss_avg": 0.02766768550500274}
+{"step": 22190, "action_loss_avg": 0.002930394449504092}
+{"step": 22200, "loss": 0.0331, "learning_rate": 9.212845881967535e-05}
+{"step": 22200, "dynamics_loss_avg": 0.033960931655019524}
+{"step": 22200, "action_loss_avg": 0.003575889125932008}
+{"step": 22210, "dynamics_loss_avg": 0.04627310633659363}
+{"step": 22210, "action_loss_avg": 0.004708726506214589}
+{"step": 22220, "dynamics_loss_avg": 0.026979896798729898}
+{"step": 22220, "action_loss_avg": 0.0030155287589877845}
+{"step": 22230, "dynamics_loss_avg": 0.03807115387171507}
+{"step": 22230, "action_loss_avg": 0.0046484530437737705}
+{"step": 22240, "dynamics_loss_avg": 0.02877139514312148}
+{"step": 22240, "action_loss_avg": 0.0029604394221678376}
+{"step": 22250, "loss": 0.0337, "learning_rate": 9.208387428960268e-05}
+{"step": 22250, "dynamics_loss_avg": 0.03504972280934453}
+{"step": 22250, "action_loss_avg": 0.004268053238047287}
+{"step": 22260, "dynamics_loss_avg": 0.027896776981651782}
+{"step": 22260, "action_loss_avg": 0.002711707935668528}
+{"step": 22270, "dynamics_loss_avg": 0.033025735151022674}
+{"step": 22270, "action_loss_avg": 0.003303789027268067}
+{"step": 22280, "dynamics_loss_avg": 0.028023201692849397}
+{"step": 22280, "action_loss_avg": 0.003154217393603176}
+{"step": 22290, "dynamics_loss_avg": 0.03432030268013477}
+{"step": 22290, "action_loss_avg": 0.0034337064251303675}
+{"step": 22300, "loss": 0.0348, "learning_rate": 9.203917470382465e-05}
+{"step": 22300, "dynamics_loss_avg": 0.02911481065675616}
+{"step": 22300, "action_loss_avg": 0.0029028451652266087}
+{"step": 22310, "dynamics_loss_avg": 0.03210270330309868}
+{"step": 22310, "action_loss_avg": 0.004329428600613028}
+{"step": 22320, "dynamics_loss_avg": 0.029629389732144774}
+{"step": 22320, "action_loss_avg": 0.0028747095551807434}
+{"step": 22330, "dynamics_loss_avg": 0.03096731221303344}
+{"step": 22330, "action_loss_avg": 0.002889741922263056}
+{"step": 22340, "dynamics_loss_avg": 0.03628141731023789}
+{"step": 22340, "action_loss_avg": 0.0035409148666076364}
+{"step": 22350, "loss": 0.0345, "learning_rate": 9.199436018454826e-05}
+{"step": 22350, "dynamics_loss_avg": 0.03053272203542292}
+{"step": 22350, "action_loss_avg": 0.003227456856984645}
+{"step": 22360, "dynamics_loss_avg": 0.03197959363460541}
+{"step": 22360, "action_loss_avg": 0.0033369683427736164}
+{"step": 22370, "dynamics_loss_avg": 0.02893503587692976}
+{"step": 22370, "action_loss_avg": 0.003643701184773818}
+{"step": 22380, "dynamics_loss_avg": 0.03827382642775774}
+{"step": 22380, "action_loss_avg": 0.003143570572137833}
+{"step": 22390, "dynamics_loss_avg": 0.036506358347833154}
+{"step": 22390, "action_loss_avg": 0.0032582532614469526}
+{"step": 22400, "loss": 0.0337, "learning_rate": 9.194943085429466e-05}
+{"step": 22400, "dynamics_loss_avg": 0.02490037865936756}
+{"step": 22400, "action_loss_avg": 0.0023791685584001244}
+{"step": 22410, "dynamics_loss_avg": 0.032056206930428745}
+{"step": 22410, "action_loss_avg": 0.0028500355663709344}
+{"step": 22420, "dynamics_loss_avg": 0.03836447689682245}
+{"step": 22420, "action_loss_avg": 0.004558089713100344}
+{"step": 22430, "dynamics_loss_avg": 0.023715492337942123}
+{"step": 22430, "action_loss_avg": 0.0029188087733928113}
+{"step": 22440, "dynamics_loss_avg": 0.0337314922362566}
+{"step": 22440, "action_loss_avg": 0.0030080801574513317}
+{"step": 22450, "loss": 0.035, "learning_rate": 9.190438683589895e-05}
+{"step": 22450, "dynamics_loss_avg": 0.031164372991770505}
+{"step": 22450, "action_loss_avg": 0.0031084967718925326}
+{"step": 22460, "dynamics_loss_avg": 0.028898614877834915}
+{"step": 22460, "action_loss_avg": 0.0023893653298728166}
+{"step": 22470, "dynamics_loss_avg": 0.032929451670497656}
+{"step": 22470, "action_loss_avg": 0.0034081016143318265}
+{"step": 22480, "dynamics_loss_avg": 0.02956971023231745}
+{"step": 22480, "action_loss_avg": 0.0023180861957371236}
+{"step": 22490, "dynamics_loss_avg": 0.03692586869001389}
+{"step": 22490, "action_loss_avg": 0.004096878552809357}
+{"step": 22500, "loss": 0.0324, "learning_rate": 9.185922825250974e-05}
+{"step": 22500, "dynamics_loss_avg": 0.037223796267062424}
+{"step": 22500, "action_loss_avg": 0.0038105889107100666}
+{"step": 22510, "dynamics_loss_avg": 0.025173754524439575}
+{"step": 22510, "action_loss_avg": 0.0024050906649790704}
+{"step": 22520, "dynamics_loss_avg": 0.032769713271409276}
+{"step": 22520, "action_loss_avg": 0.0039794534270185975}
+{"step": 22530, "dynamics_loss_avg": 0.03130688790697604}
+{"step": 22530, "action_loss_avg": 0.002279309916775674}
+{"step": 22540, "dynamics_loss_avg": 0.0419799143448472}
+{"step": 22540, "action_loss_avg": 0.0046245517209172245}
+{"step": 22550, "loss": 0.0345, "learning_rate": 9.181395522758889e-05}
+{"step": 22550, "dynamics_loss_avg": 0.026358743477612735}
+{"step": 22550, "action_loss_avg": 0.0029196669231168924}
+{"step": 22560, "dynamics_loss_avg": 0.029589891200885177}
+{"step": 22560, "action_loss_avg": 0.003266822249861434}
+{"step": 22570, "dynamics_loss_avg": 0.03393928436562419}
+{"step": 22570, "action_loss_avg": 0.0035453679622150956}
+{"step": 22580, "dynamics_loss_avg": 0.026540046371519566}
+{"step": 22580, "action_loss_avg": 0.002197524666553363}
+{"step": 22590, "dynamics_loss_avg": 0.028397776046767832}
+{"step": 22590, "action_loss_avg": 0.00200942960800603}
+{"step": 22600, "loss": 0.034, "learning_rate": 9.176856788491109e-05}
+{"step": 22600, "dynamics_loss_avg": 0.04006740301847458}
+{"step": 22600, "action_loss_avg": 0.003416037815622985}
+{"step": 22610, "dynamics_loss_avg": 0.031814472004771235}
+{"step": 22610, "action_loss_avg": 0.002703078102786094}
+{"step": 22620, "dynamics_loss_avg": 0.027360132802277802}
+{"step": 22620, "action_loss_avg": 0.0024199716746807097}
+{"step": 22630, "dynamics_loss_avg": 0.03196517955511809}
+{"step": 22630, "action_loss_avg": 0.003098660398973152}
+{"step": 22640, "dynamics_loss_avg": 0.027137688966467975}
+{"step": 22640, "action_loss_avg": 0.0019957823387812823}
+{"step": 22650, "loss": 0.0311, "learning_rate": 9.172306634856362e-05}
+{"step": 22650, "dynamics_loss_avg": 0.039083386026322844}
+{"step": 22650, "action_loss_avg": 0.0030827766284346582}
+{"step": 22660, "dynamics_loss_avg": 0.027990800514817237}
+{"step": 22660, "action_loss_avg": 0.0029480994795449077}
+{"step": 22670, "dynamics_loss_avg": 0.04075593538582325}
+{"step": 22670, "action_loss_avg": 0.003094595787115395}
+{"step": 22680, "dynamics_loss_avg": 0.02926615308970213}
+{"step": 22680, "action_loss_avg": 0.002565313538070768}
+{"step": 22690, "dynamics_loss_avg": 0.030221683671697974}
+{"step": 22690, "action_loss_avg": 0.002533564573968761}
+{"step": 22700, "loss": 0.0332, "learning_rate": 9.167745074294598e-05}
+{"step": 22700, "dynamics_loss_avg": 0.03446968523785472}
+{"step": 22700, "action_loss_avg": 0.004243770381435752}
+{"step": 22710, "dynamics_loss_avg": 0.035416758991777895}
+{"step": 22710, "action_loss_avg": 0.0033070193603634834}
+{"step": 22720, "dynamics_loss_avg": 0.026355175580829383}
+{"step": 22720, "action_loss_avg": 0.0024712758720852436}
+{"step": 22730, "dynamics_loss_avg": 0.03767761313356459}
+{"step": 22730, "action_loss_avg": 0.0034833902260288595}
+{"step": 22740, "dynamics_loss_avg": 0.023399589769542217}
+{"step": 22740, "action_loss_avg": 0.0028027167310938237}
+{"step": 22750, "loss": 0.0331, "learning_rate": 9.163172119276942e-05}
+{"step": 22750, "dynamics_loss_avg": 0.029893708880990744}
+{"step": 22750, "action_loss_avg": 0.0035321612958796322}
+{"step": 22760, "dynamics_loss_avg": 0.02326078722253442}
+{"step": 22760, "action_loss_avg": 0.0019115082919597625}
+{"step": 22770, "dynamics_loss_avg": 0.033794113481417296}
+{"step": 22770, "action_loss_avg": 0.002982619125396013}
+{"step": 22780, "dynamics_loss_avg": 0.029710760712623595}
+{"step": 22780, "action_loss_avg": 0.0029054692131467164}
+{"step": 22790, "dynamics_loss_avg": 0.027933984249830245}
+{"step": 22790, "action_loss_avg": 0.0033515786984935404}
+{"step": 22800, "loss": 0.0324, "learning_rate": 9.158587782305684e-05}
+{"step": 22800, "dynamics_loss_avg": 0.041162443719804286}
+{"step": 22800, "action_loss_avg": 0.002782836486585438}
+{"step": 22810, "dynamics_loss_avg": 0.027791966591030358}
+{"step": 22810, "action_loss_avg": 0.0024905424914322795}
+{"step": 22820, "dynamics_loss_avg": 0.0414312363602221}
+{"step": 22820, "action_loss_avg": 0.005812827497720718}
+{"step": 22830, "dynamics_loss_avg": 0.04014187473803758}
+{"step": 22830, "action_loss_avg": 0.003567256685346365}
+{"step": 22840, "dynamics_loss_avg": 0.03288347087800503}
+{"step": 22840, "action_loss_avg": 0.003078125580213964}
+{"step": 22850, "loss": 0.0366, "learning_rate": 9.153992075914224e-05}
+{"step": 22850, "dynamics_loss_avg": 0.03657228844240308}
+{"step": 22850, "action_loss_avg": 0.0030073614499997346}
+{"step": 22860, "dynamics_loss_avg": 0.03573363032191992}
+{"step": 22860, "action_loss_avg": 0.003912260022480041}
+{"step": 22870, "dynamics_loss_avg": 0.03496250919997692}
+{"step": 22870, "action_loss_avg": 0.003084001480601728}
+{"step": 22880, "dynamics_loss_avg": 0.028032348304986954}
+{"step": 22880, "action_loss_avg": 0.002802130824420601}
+{"step": 22890, "dynamics_loss_avg": 0.028504295274615288}
+{"step": 22890, "action_loss_avg": 0.0026231413474306466}
+{"step": 22900, "loss": 0.0359, "learning_rate": 9.149385012667048e-05}
+{"step": 22900, "dynamics_loss_avg": 0.0426869623363018}
+{"step": 22900, "action_loss_avg": 0.0056272302812431}
+{"step": 22910, "dynamics_loss_avg": 0.028266533836722375}
+{"step": 22910, "action_loss_avg": 0.002993043151218444}
+{"step": 22920, "dynamics_loss_avg": 0.02647641645744443}
+{"step": 22920, "action_loss_avg": 0.002764363627647981}
+{"step": 22930, "dynamics_loss_avg": 0.03312731408514082}
+{"step": 22930, "action_loss_avg": 0.004822667932603508}
+{"step": 22940, "dynamics_loss_avg": 0.03530171988531947}
+{"step": 22940, "action_loss_avg": 0.005191868712427094}
+{"step": 22950, "loss": 0.0328, "learning_rate": 9.144766605159691e-05}
+{"step": 22950, "dynamics_loss_avg": 0.03547544274479151}
+{"step": 22950, "action_loss_avg": 0.004133019817527383}
+{"step": 22960, "dynamics_loss_avg": 0.03391031278297305}
+{"step": 22960, "action_loss_avg": 0.004320283274864778}
+{"step": 22970, "dynamics_loss_avg": 0.03698928691446781}
+{"step": 22970, "action_loss_avg": 0.0042462416575290264}
+{"step": 22980, "dynamics_loss_avg": 0.030271165911108254}
+{"step": 22980, "action_loss_avg": 0.004140077659394592}
+{"step": 22990, "dynamics_loss_avg": 0.031324876565486194}
+{"step": 22990, "action_loss_avg": 0.0027662807086016985}
+{"step": 23000, "loss": 0.0335, "learning_rate": 9.140136866018704e-05}
+{"step": 23000, "dynamics_loss_avg": 0.02794238906353712}
+{"step": 23000, "action_loss_avg": 0.00283349392702803}
+{"step": 23010, "dynamics_loss_avg": 0.03946527857333422}
+{"step": 23010, "action_loss_avg": 0.0039002719800919293}
+{"step": 23020, "dynamics_loss_avg": 0.030390716902911664}
+{"step": 23020, "action_loss_avg": 0.005117071012500673}
+{"step": 23030, "dynamics_loss_avg": 0.024144184635952116}
+{"step": 23030, "action_loss_avg": 0.0037041242117993533}
+{"step": 23040, "dynamics_loss_avg": 0.02621443858370185}
+{"step": 23040, "action_loss_avg": 0.0029540345713030547}
+{"step": 23050, "loss": 0.0337, "learning_rate": 9.135495807901615e-05}
+{"step": 23050, "dynamics_loss_avg": 0.03486132891848683}
+{"step": 23050, "action_loss_avg": 0.0038140124175697564}
+{"step": 23060, "dynamics_loss_avg": 0.02591165788471699}
+{"step": 23060, "action_loss_avg": 0.0029810993699356915}
+{"step": 23070, "dynamics_loss_avg": 0.03331028809770942}
+{"step": 23070, "action_loss_avg": 0.004207202460383997}
+{"step": 23080, "dynamics_loss_avg": 0.03078016620129347}
+{"step": 23080, "action_loss_avg": 0.0027974657772574575}
+{"step": 23090, "dynamics_loss_avg": 0.026637157518416645}
+{"step": 23090, "action_loss_avg": 0.0023576326610054823}
+{"step": 23100, "loss": 0.0323, "learning_rate": 9.130843443496901e-05}
+{"step": 23100, "dynamics_loss_avg": 0.031065830448642372}
+{"step": 23100, "action_loss_avg": 0.0030212527723051607}
+{"step": 23110, "dynamics_loss_avg": 0.027005905844271184}
+{"step": 23110, "action_loss_avg": 0.0025221552001312374}
+{"step": 23120, "dynamics_loss_avg": 0.026253752782940863}
+{"step": 23120, "action_loss_avg": 0.002779923810157925}
+{"step": 23130, "dynamics_loss_avg": 0.027556841727346182}
+{"step": 23130, "action_loss_avg": 0.002719141368288547}
+{"step": 23140, "dynamics_loss_avg": 0.032656535226851705}
+{"step": 23140, "action_loss_avg": 0.003335577150573954}
+{"step": 23150, "loss": 0.0303, "learning_rate": 9.12617978552395e-05}
+{"step": 23150, "dynamics_loss_avg": 0.03497147038578987}
+{"step": 23150, "action_loss_avg": 0.0037428263982292264}
+{"step": 23160, "dynamics_loss_avg": 0.04147119652479887}
+{"step": 23160, "action_loss_avg": 0.003588703670538962}
+{"step": 23170, "dynamics_loss_avg": 0.031507433485239746}
+{"step": 23170, "action_loss_avg": 0.003028084128163755}
+{"step": 23180, "dynamics_loss_avg": 0.025154187344014645}
+{"step": 23180, "action_loss_avg": 0.0027949275448918343}
+{"step": 23190, "dynamics_loss_avg": 0.036955642607063056}
+{"step": 23190, "action_loss_avg": 0.004141491238260642}
+{"step": 23200, "loss": 0.0341, "learning_rate": 9.12150484673302e-05}
+{"step": 23200, "dynamics_loss_avg": 0.0334549049846828}
+{"step": 23200, "action_loss_avg": 0.0032377014285884798}
+{"step": 23210, "dynamics_loss_avg": 0.029820429533720015}
+{"step": 23210, "action_loss_avg": 0.0031417685211636128}
+{"step": 23220, "dynamics_loss_avg": 0.03297597882337868}
+{"step": 23220, "action_loss_avg": 0.0031330713303759695}
+{"step": 23230, "dynamics_loss_avg": 0.02631046585738659}
+{"step": 23230, "action_loss_avg": 0.002035013592103496}
+{"step": 23240, "dynamics_loss_avg": 0.028190711792558432}
+{"step": 23240, "action_loss_avg": 0.003394127974752337}
+{"step": 23250, "loss": 0.0312, "learning_rate": 9.11681863990522e-05}
+{"step": 23250, "dynamics_loss_avg": 0.033120027557015416}
+{"step": 23250, "action_loss_avg": 0.004041575512383133}
+{"step": 23260, "dynamics_loss_avg": 0.035723811481148005}
+{"step": 23260, "action_loss_avg": 0.003356536920182407}
+{"step": 23270, "dynamics_loss_avg": 0.02674521217122674}
+{"step": 23270, "action_loss_avg": 0.002243430039379746}
+{"step": 23280, "dynamics_loss_avg": 0.03352100476622581}
+{"step": 23280, "action_loss_avg": 0.0036458742106333375}
+{"step": 23290, "dynamics_loss_avg": 0.04033178528770805}
+{"step": 23290, "action_loss_avg": 0.004233045352157206}
+{"step": 23300, "loss": 0.0331, "learning_rate": 9.112121177852459e-05}
+{"step": 23300, "dynamics_loss_avg": 0.028313900530338287}
+{"step": 23300, "action_loss_avg": 0.003412481863051653}
+{"step": 23310, "dynamics_loss_avg": 0.03335492461919785}
+{"step": 23310, "action_loss_avg": 0.004188372567296028}
+{"step": 23320, "dynamics_loss_avg": 0.03276301808655262}
+{"step": 23320, "action_loss_avg": 0.0035147854418028147}
+{"step": 23330, "dynamics_loss_avg": 0.035294465720653534}
+{"step": 23330, "action_loss_avg": 0.003092596592614427}
+{"step": 23340, "dynamics_loss_avg": 0.029647050146013498}
+{"step": 23340, "action_loss_avg": 0.0029452498187310995}
+{"step": 23350, "loss": 0.0346, "learning_rate": 9.107412473417419e-05}
+{"step": 23350, "dynamics_loss_avg": 0.03579639289528132}
+{"step": 23350, "action_loss_avg": 0.0039249706314876676}
+{"step": 23360, "dynamics_loss_avg": 0.033935885224491355}
+{"step": 23360, "action_loss_avg": 0.0035607392201200128}
+{"step": 23370, "dynamics_loss_avg": 0.0356685477308929}
+{"step": 23370, "action_loss_avg": 0.0033731797244399785}
+{"step": 23380, "dynamics_loss_avg": 0.03226554449647665}
+{"step": 23380, "action_loss_avg": 0.0033972644188906996}
+{"step": 23390, "dynamics_loss_avg": 0.04135460294783115}
+{"step": 23390, "action_loss_avg": 0.004712470073718578}
+{"step": 23400, "loss": 0.0366, "learning_rate": 9.102692539473518e-05}
+{"step": 23400, "dynamics_loss_avg": 0.039442498795688154}
+{"step": 23400, "action_loss_avg": 0.0046652380609884855}
+{"step": 23410, "dynamics_loss_avg": 0.030950998328626154}
+{"step": 23410, "action_loss_avg": 0.003938283398747444}
+{"step": 23420, "dynamics_loss_avg": 0.03824727069586516}
+{"step": 23420, "action_loss_avg": 0.004506634641438722}
+{"step": 23430, "dynamics_loss_avg": 0.027977884467691182}
+{"step": 23430, "action_loss_avg": 0.002907504525501281}
+{"step": 23440, "dynamics_loss_avg": 0.038354250509291886}
+{"step": 23440, "action_loss_avg": 0.0034625980246346445}
+{"step": 23450, "loss": 0.0342, "learning_rate": 9.097961388924873e-05}
+{"step": 23450, "dynamics_loss_avg": 0.036201785504817965}
+{"step": 23450, "action_loss_avg": 0.003541634732391685}
+{"step": 23460, "dynamics_loss_avg": 0.036225549224764106}
+{"step": 23460, "action_loss_avg": 0.0032427438942249863}
+{"step": 23470, "dynamics_loss_avg": 0.023774833604693412}
+{"step": 23470, "action_loss_avg": 0.0019280272303149105}
+{"step": 23480, "dynamics_loss_avg": 0.03996117748320103}
+{"step": 23480, "action_loss_avg": 0.00414986782707274}
+{"step": 23490, "dynamics_loss_avg": 0.029131739493459465}
+{"step": 23490, "action_loss_avg": 0.0030252421274781227}
+{"step": 23500, "loss": 0.0341, "learning_rate": 9.093219034706273e-05}
+{"step": 23500, "dynamics_loss_avg": 0.02900403756648302}
+{"step": 23500, "action_loss_avg": 0.002703422331251204}
+{"step": 23510, "dynamics_loss_avg": 0.028785125724971293}
+{"step": 23510, "action_loss_avg": 0.0028980999923078343}
+{"step": 23520, "dynamics_loss_avg": 0.027971434779465197}
+{"step": 23520, "action_loss_avg": 0.0021483055432327093}
+{"step": 23530, "dynamics_loss_avg": 0.027309343777596952}
+{"step": 23530, "action_loss_avg": 0.0021636482095345856}
+{"step": 23540, "dynamics_loss_avg": 0.04702749997377396}
+{"step": 23540, "action_loss_avg": 0.0043285294668748975}
+{"step": 23550, "loss": 0.034, "learning_rate": 9.088465489783131e-05}
+{"step": 23550, "dynamics_loss_avg": 0.027169691305607556}
+{"step": 23550, "action_loss_avg": 0.002714807668235153}
+{"step": 23560, "dynamics_loss_avg": 0.033210689574480055}
+{"step": 23560, "action_loss_avg": 0.003298267110949382}
+{"step": 23570, "dynamics_loss_avg": 0.028449750691652297}
+{"step": 23570, "action_loss_avg": 0.002792096452321857}
+{"step": 23580, "dynamics_loss_avg": 0.032697207760065794}
+{"step": 23580, "action_loss_avg": 0.002715967857511714}
+{"step": 23590, "dynamics_loss_avg": 0.03595560025423765}
+{"step": 23590, "action_loss_avg": 0.003862538398243487}
+{"step": 23600, "loss": 0.0322, "learning_rate": 9.083700767151457e-05}
+{"step": 23600, "dynamics_loss_avg": 0.02991185523569584}
+{"step": 23600, "action_loss_avg": 0.00235309440176934}
+{"step": 23610, "dynamics_loss_avg": 0.02378534683957696}
+{"step": 23610, "action_loss_avg": 0.0028391613683197646}
+{"step": 23620, "dynamics_loss_avg": 0.03674794593825936}
+{"step": 23620, "action_loss_avg": 0.004816040763398632}
+{"step": 23630, "dynamics_loss_avg": 0.027353502251207827}
+{"step": 23630, "action_loss_avg": 0.0033919863752089443}
+{"step": 23640, "dynamics_loss_avg": 0.03352328278124332}
+{"step": 23640, "action_loss_avg": 0.003126925270771608}
+{"step": 23650, "loss": 0.033, "learning_rate": 9.078924879837822e-05}
+{"step": 23650, "dynamics_loss_avg": 0.03338943631388247}
+{"step": 23650, "action_loss_avg": 0.0035442256659734992}
+{"step": 23660, "dynamics_loss_avg": 0.028929295763373376}
+{"step": 23660, "action_loss_avg": 0.0027461266843602063}
+{"step": 23670, "dynamics_loss_avg": 0.04489357620477676}
+{"step": 23670, "action_loss_avg": 0.005207790248095989}
+{"step": 23680, "dynamics_loss_avg": 0.027053921576589347}
+{"step": 23680, "action_loss_avg": 0.003372264688368887}
+{"step": 23690, "dynamics_loss_avg": 0.029645750392228366}
+{"step": 23690, "action_loss_avg": 0.0035732105607166886}
+{"step": 23700, "loss": 0.0345, "learning_rate": 9.074137840899318e-05}
+{"step": 23700, "dynamics_loss_avg": 0.032664841040968895}
+{"step": 23700, "action_loss_avg": 0.003187634714413434}
+{"step": 23710, "dynamics_loss_avg": 0.042253034003078935}
+{"step": 23710, "action_loss_avg": 0.00540084159001708}
+{"step": 23720, "dynamics_loss_avg": 0.029042589850723742}
+{"step": 23720, "action_loss_avg": 0.002919051714707166}
+{"step": 23730, "dynamics_loss_avg": 0.028891782369464637}
+{"step": 23730, "action_loss_avg": 0.002705114416312426}
+{"step": 23740, "dynamics_loss_avg": 0.024858732195571064}
+{"step": 23740, "action_loss_avg": 0.0018145697482395916}
+{"step": 23750, "loss": 0.0317, "learning_rate": 9.069339663423528e-05}
+{"step": 23750, "dynamics_loss_avg": 0.023253212636336684}
+{"step": 23750, "action_loss_avg": 0.002367522264830768}
+{"step": 23760, "dynamics_loss_avg": 0.03890234464779496}
+{"step": 23760, "action_loss_avg": 0.003667207213584334}
+{"step": 23770, "dynamics_loss_avg": 0.028815711475908758}
+{"step": 23770, "action_loss_avg": 0.0031307189608924093}
+{"step": 23780, "dynamics_loss_avg": 0.03996701873838902}
+{"step": 23780, "action_loss_avg": 0.00443459494272247}
+{"step": 23790, "dynamics_loss_avg": 0.03864745879545808}
+{"step": 23790, "action_loss_avg": 0.0032679407158866525}
+{"step": 23800, "loss": 0.0374, "learning_rate": 9.064530360528484e-05}
+{"step": 23800, "dynamics_loss_avg": 0.047489880677312614}
+{"step": 23800, "action_loss_avg": 0.005832456611096859}
+{"step": 23810, "dynamics_loss_avg": 0.03321072831749916}
+{"step": 23810, "action_loss_avg": 0.0027442143298685552}
+{"step": 23820, "dynamics_loss_avg": 0.026983365043997766}
+{"step": 23820, "action_loss_avg": 0.00323048178688623}
+{"step": 23830, "dynamics_loss_avg": 0.026259929407387972}
+{"step": 23830, "action_loss_avg": 0.002605033709551208}
+{"step": 23840, "dynamics_loss_avg": 0.04291377533227205}
+{"step": 23840, "action_loss_avg": 0.004778594197705388}
+{"step": 23850, "loss": 0.0343, "learning_rate": 9.05970994536264e-05}
+{"step": 23850, "dynamics_loss_avg": 0.03539122184738517}
+{"step": 23850, "action_loss_avg": 0.0033460237202234564}
+{"step": 23860, "dynamics_loss_avg": 0.038486839085817334}
+{"step": 23860, "action_loss_avg": 0.003810455754864961}
+{"step": 23870, "dynamics_loss_avg": 0.027215545810759068}
+{"step": 23870, "action_loss_avg": 0.002440065867267549}
+{"step": 23880, "dynamics_loss_avg": 0.02887699003331363}
+{"step": 23880, "action_loss_avg": 0.003856264508794993}
+{"step": 23890, "dynamics_loss_avg": 0.04276553615927696}
+{"step": 23890, "action_loss_avg": 0.004907750384882092}
+{"step": 23900, "loss": 0.0351, "learning_rate": 9.054878431104825e-05}
+{"step": 23900, "dynamics_loss_avg": 0.038668008986860514}
+{"step": 23900, "action_loss_avg": 0.004750432434957474}
+{"step": 23910, "dynamics_loss_avg": 0.03523197844624519}
+{"step": 23910, "action_loss_avg": 0.0030596205266192555}
+{"step": 23920, "dynamics_loss_avg": 0.03190682549029589}
+{"step": 23920, "action_loss_avg": 0.0032211623154580595}
+{"step": 23930, "dynamics_loss_avg": 0.028339651180431247}
+{"step": 23930, "action_loss_avg": 0.0027400781982578337}
+{"step": 23940, "dynamics_loss_avg": 0.03874617628753185}
+{"step": 23940, "action_loss_avg": 0.004327934887260199}
+{"step": 23950, "loss": 0.0358, "learning_rate": 9.050035830964215e-05}
+{"step": 23950, "dynamics_loss_avg": 0.029356595035642384}
+{"step": 23950, "action_loss_avg": 0.002804142626700923}
+{"step": 23960, "dynamics_loss_avg": 0.039916728436946866}
+{"step": 23960, "action_loss_avg": 0.003887035325169563}
+{"step": 23970, "dynamics_loss_avg": 0.04506257362663746}
+{"step": 23970, "action_loss_avg": 0.004725080123171211}
+{"step": 23980, "dynamics_loss_avg": 0.031451936531811955}
+{"step": 23980, "action_loss_avg": 0.0041626636171713475}
+{"step": 23990, "dynamics_loss_avg": 0.03748870026320219}
+{"step": 23990, "action_loss_avg": 0.003849129530135542}
+{"step": 24000, "loss": 0.0347, "learning_rate": 9.045182158180292e-05}
+{"step": 24000, "dynamics_loss_avg": 0.029873982630670072}
+{"step": 24000, "action_loss_avg": 0.003094610176049173}
+{"step": 24010, "dynamics_loss_avg": 0.038367574103176594}
+{"step": 24010, "action_loss_avg": 0.004297009506262839}
+{"step": 24020, "dynamics_loss_avg": 0.029994077142328025}
+{"step": 24020, "action_loss_avg": 0.0025539212045259775}
+{"step": 24030, "dynamics_loss_avg": 0.028056914266198874}
+{"step": 24030, "action_loss_avg": 0.0026236129458993675}
+{"step": 24040, "dynamics_loss_avg": 0.02881078701466322}
+{"step": 24040, "action_loss_avg": 0.003834523051045835}
+{"step": 24050, "loss": 0.0344, "learning_rate": 9.040317426022814e-05}
+{"step": 24050, "dynamics_loss_avg": 0.04064572667703033}
+{"step": 24050, "action_loss_avg": 0.005454085220117122}
+{"step": 24060, "dynamics_loss_avg": 0.030229681357741355}
+{"step": 24060, "action_loss_avg": 0.002789091516751796}
+{"step": 24070, "dynamics_loss_avg": 0.029342071060091256}
+{"step": 24070, "action_loss_avg": 0.0027983243635389954}
+{"step": 24080, "dynamics_loss_avg": 0.04175789169967174}
+{"step": 24080, "action_loss_avg": 0.0033375116996467113}
+{"step": 24090, "dynamics_loss_avg": 0.027135165594518184}
+{"step": 24090, "action_loss_avg": 0.002886785345617682}
+{"step": 24100, "loss": 0.0343, "learning_rate": 9.035441647791773e-05}
+{"step": 24100, "dynamics_loss_avg": 0.030222125444561244}
+{"step": 24100, "action_loss_avg": 0.0029739275749307128}
+{"step": 24110, "dynamics_loss_avg": 0.03435925552621484}
+{"step": 24110, "action_loss_avg": 0.00431576962582767}
+{"step": 24120, "dynamics_loss_avg": 0.028433520719408988}
+{"step": 24120, "action_loss_avg": 0.002740089374128729}
+{"step": 24130, "dynamics_loss_avg": 0.04603171572089195}
+{"step": 24130, "action_loss_avg": 0.004668145044706762}
+{"step": 24140, "dynamics_loss_avg": 0.0387892204336822}
+{"step": 24140, "action_loss_avg": 0.004339023784268647}
+{"step": 24150, "loss": 0.0363, "learning_rate": 9.030554836817358e-05}
+{"step": 24150, "dynamics_loss_avg": 0.0382829743437469}
+{"step": 24150, "action_loss_avg": 0.003452157322317362}
+{"step": 24160, "dynamics_loss_avg": 0.030478913430124523}
+{"step": 24160, "action_loss_avg": 0.0026496212543861476}
+{"step": 24170, "dynamics_loss_avg": 0.036258215364068744}
+{"step": 24170, "action_loss_avg": 0.004674304416403175}
+{"step": 24180, "dynamics_loss_avg": 0.0395270143635571}
+{"step": 24180, "action_loss_avg": 0.00347917890176177}
+{"step": 24190, "dynamics_loss_avg": 0.020557325426489116}
+{"step": 24190, "action_loss_avg": 0.0023011167126242072}
+{"step": 24200, "loss": 0.0319, "learning_rate": 9.025657006459927e-05}
+{"step": 24200, "dynamics_loss_avg": 0.02911555632017553}
+{"step": 24200, "action_loss_avg": 0.0031240293581504376}
+{"step": 24210, "dynamics_loss_avg": 0.030797990411520003}
+{"step": 24210, "action_loss_avg": 0.003397135331761092}
+{"step": 24220, "dynamics_loss_avg": 0.041582840774208304}
+{"step": 24220, "action_loss_avg": 0.004899543710052967}
+{"step": 24230, "dynamics_loss_avg": 0.031320896744728086}
+{"step": 24230, "action_loss_avg": 0.0032183378702029587}
+{"step": 24240, "dynamics_loss_avg": 0.024012441094964743}
+{"step": 24240, "action_loss_avg": 0.0026825364329852164}
+{"step": 24250, "loss": 0.0339, "learning_rate": 9.02074817010996e-05}
+{"step": 24250, "dynamics_loss_avg": 0.03087571859359741}
+{"step": 24250, "action_loss_avg": 0.00254033578094095}
+{"step": 24260, "dynamics_loss_avg": 0.03788787228986621}
+{"step": 24260, "action_loss_avg": 0.00391339382622391}
+{"step": 24270, "dynamics_loss_avg": 0.03226645151153207}
+{"step": 24270, "action_loss_avg": 0.0026389840291813015}
+{"step": 24280, "dynamics_loss_avg": 0.033448740374296904}
+{"step": 24280, "action_loss_avg": 0.003122376149985939}
+{"step": 24290, "dynamics_loss_avg": 0.03384518530219793}
+{"step": 24290, "action_loss_avg": 0.002578827057732269}
+{"step": 24300, "loss": 0.0345, "learning_rate": 9.015828341188027e-05}
+{"step": 24300, "dynamics_loss_avg": 0.031602500658482316}
+{"step": 24300, "action_loss_avg": 0.0030516743543557824}
+{"step": 24310, "dynamics_loss_avg": 0.027139101549983023}
+{"step": 24310, "action_loss_avg": 0.0029459305573254825}
+{"step": 24320, "dynamics_loss_avg": 0.024452371522784233}
+{"step": 24320, "action_loss_avg": 0.0027364888112060724}
+{"step": 24330, "dynamics_loss_avg": 0.03627485632896423}
+{"step": 24330, "action_loss_avg": 0.0039934445987455545}
+{"step": 24340, "dynamics_loss_avg": 0.02657801497261971}
+{"step": 24340, "action_loss_avg": 0.002459138905396685}
+{"step": 24350, "loss": 0.0324, "learning_rate": 9.010897533144754e-05}
+{"step": 24350, "dynamics_loss_avg": 0.030798340495675803}
+{"step": 24350, "action_loss_avg": 0.003105462377425283}
+{"step": 24360, "dynamics_loss_avg": 0.02772613801062107}
+{"step": 24360, "action_loss_avg": 0.002836509491316974}
+{"step": 24370, "dynamics_loss_avg": 0.03209917536005378}
+{"step": 24370, "action_loss_avg": 0.004073745757341385}
+{"step": 24380, "dynamics_loss_avg": 0.03325516050681472}
+{"step": 24380, "action_loss_avg": 0.003074142767582089}
+{"step": 24390, "dynamics_loss_avg": 0.02953424546867609}
+{"step": 24390, "action_loss_avg": 0.0030760749941691756}
+{"step": 24400, "loss": 0.0359, "learning_rate": 9.005955759460779e-05}
+{"step": 24400, "dynamics_loss_avg": 0.03414279967546463}
+{"step": 24400, "action_loss_avg": 0.004474275792017579}
+{"step": 24410, "dynamics_loss_avg": 0.035425833985209466}
+{"step": 24410, "action_loss_avg": 0.004291910032043234}
+{"step": 24420, "dynamics_loss_avg": 0.036432192847132686}
+{"step": 24420, "action_loss_avg": 0.0040031927754171194}
+{"step": 24430, "dynamics_loss_avg": 0.03633450986817479}
+{"step": 24430, "action_loss_avg": 0.0035580807365477086}
+{"step": 24440, "dynamics_loss_avg": 0.030512635502964257}
+{"step": 24440, "action_loss_avg": 0.0029833741369657218}
+{"step": 24450, "loss": 0.0353, "learning_rate": 9.001003033646727e-05}
+{"step": 24450, "dynamics_loss_avg": 0.03075534859672189}
+{"step": 24450, "action_loss_avg": 0.003786973131354898}
+{"step": 24460, "dynamics_loss_avg": 0.03293519737198949}
+{"step": 24460, "action_loss_avg": 0.004117277241311968}
+{"step": 24470, "dynamics_loss_avg": 0.026475403271615506}
+{"step": 24470, "action_loss_avg": 0.002762490476015955}
+{"step": 24480, "dynamics_loss_avg": 0.037753349915146825}
+{"step": 24480, "action_loss_avg": 0.004051335924305022}
+{"step": 24490, "dynamics_loss_avg": 0.03898820606991649}
+{"step": 24490, "action_loss_avg": 0.004815056594088674}
+{"step": 24500, "loss": 0.0346, "learning_rate": 8.996039369243156e-05}
+{"step": 24500, "dynamics_loss_avg": 0.032803804986178874}
+{"step": 24500, "action_loss_avg": 0.004515505011659116}
+{"step": 24510, "dynamics_loss_avg": 0.029502533469349147}
+{"step": 24510, "action_loss_avg": 0.005154908954864368}
+{"step": 24520, "dynamics_loss_avg": 0.03719205930829048}
+{"step": 24520, "action_loss_avg": 0.0033418881706893445}
+{"step": 24530, "dynamics_loss_avg": 0.033509650640189646}
+{"step": 24530, "action_loss_avg": 0.004310726129915565}
+{"step": 24540, "dynamics_loss_avg": 0.03655149429105222}
+{"step": 24540, "action_loss_avg": 0.005686428607441485}
+{"step": 24550, "loss": 0.0355, "learning_rate": 8.991064779820542e-05}
+{"step": 24550, "dynamics_loss_avg": 0.0401293558999896}
+{"step": 24550, "action_loss_avg": 0.004350312694441527}
+{"step": 24560, "dynamics_loss_avg": 0.026239527203142644}
+{"step": 24560, "action_loss_avg": 0.0032475066895131023}
+{"step": 24570, "dynamics_loss_avg": 0.037849669344723225}
+{"step": 24570, "action_loss_avg": 0.005270012863911688}
+{"step": 24580, "dynamics_loss_avg": 0.038602871168404815}
+{"step": 24580, "action_loss_avg": 0.004998011991847307}
+{"step": 24590, "dynamics_loss_avg": 0.0302285339217633}
+{"step": 24590, "action_loss_avg": 0.0038839730725158004}
+{"step": 24600, "loss": 0.0343, "learning_rate": 8.986079278979216e-05}
+{"step": 24600, "dynamics_loss_avg": 0.037259628623723985}
+{"step": 24600, "action_loss_avg": 0.0035566409584134816}
+{"step": 24610, "dynamics_loss_avg": 0.03440510183572769}
+{"step": 24610, "action_loss_avg": 0.002684829116333276}
+{"step": 24620, "dynamics_loss_avg": 0.029457655735313892}
+{"step": 24620, "action_loss_avg": 0.0034632480703294275}
+{"step": 24630, "dynamics_loss_avg": 0.030607624910771847}
+{"step": 24630, "action_loss_avg": 0.003895593894412741}
+{"step": 24640, "dynamics_loss_avg": 0.03496051505208016}
+{"step": 24640, "action_loss_avg": 0.004075098305474967}
+{"step": 24650, "loss": 0.0329, "learning_rate": 8.98108288034935e-05}
+{"step": 24650, "dynamics_loss_avg": 0.025941629940643907}
+{"step": 24650, "action_loss_avg": 0.0025030839431565257}
+{"step": 24660, "dynamics_loss_avg": 0.03855112120509148}
+{"step": 24660, "action_loss_avg": 0.003624339582165703}
+{"step": 24670, "dynamics_loss_avg": 0.03128049494698644}
+{"step": 24670, "action_loss_avg": 0.00376329189457465}
+{"step": 24680, "dynamics_loss_avg": 0.022683008387684823}
+{"step": 24680, "action_loss_avg": 0.0022190780960954725}
+{"step": 24690, "dynamics_loss_avg": 0.03408485166728496}
+{"step": 24690, "action_loss_avg": 0.002842948562465608}
+{"step": 24700, "loss": 0.0326, "learning_rate": 8.976075597590905e-05}
+{"step": 24700, "dynamics_loss_avg": 0.033339939173310996}
+{"step": 24700, "action_loss_avg": 0.0028133668820373714}
+{"step": 24710, "dynamics_loss_avg": 0.030672872625291347}
+{"step": 24710, "action_loss_avg": 0.0034480749163776636}
+{"step": 24720, "dynamics_loss_avg": 0.03594626057893038}
+{"step": 24720, "action_loss_avg": 0.002632111869752407}
+{"step": 24730, "dynamics_loss_avg": 0.034543348103761674}
+{"step": 24730, "action_loss_avg": 0.0025012061232700944}
+{"step": 24740, "dynamics_loss_avg": 0.020189517363905906}
+{"step": 24740, "action_loss_avg": 0.001530178071698174}
+{"step": 24750, "loss": 0.0344, "learning_rate": 8.971057444393603e-05}
+{"step": 24750, "dynamics_loss_avg": 0.03749623596668243}
+{"step": 24750, "action_loss_avg": 0.0026371689746156335}
+{"step": 24760, "dynamics_loss_avg": 0.03451949092559516}
+{"step": 24760, "action_loss_avg": 0.0029538293601945043}
+{"step": 24770, "dynamics_loss_avg": 0.030170877650380134}
+{"step": 24770, "action_loss_avg": 0.0034184793825261296}
+{"step": 24780, "dynamics_loss_avg": 0.02487570596858859}
+{"step": 24780, "action_loss_avg": 0.002661316189914942}
+{"step": 24790, "dynamics_loss_avg": 0.0321643091738224}
+{"step": 24790, "action_loss_avg": 0.0032865970279090106}
+{"step": 24800, "loss": 0.0323, "learning_rate": 8.966028434476883e-05}
+{"step": 24800, "dynamics_loss_avg": 0.030423987470567227}
+{"step": 24800, "action_loss_avg": 0.0025017332518473268}
+{"step": 24810, "dynamics_loss_avg": 0.028181733377277852}
+{"step": 24810, "action_loss_avg": 0.002587905031396076}
+{"step": 24820, "dynamics_loss_avg": 0.027599705010652544}
+{"step": 24820, "action_loss_avg": 0.0016091960365884005}
+{"step": 24830, "dynamics_loss_avg": 0.026142140850424767}
+{"step": 24830, "action_loss_avg": 0.002271223784191534}
+{"step": 24840, "dynamics_loss_avg": 0.042621205747127536}
+{"step": 24840, "action_loss_avg": 0.004387680324725807}
+{"step": 24850, "loss": 0.032, "learning_rate": 8.960988581589865e-05}
+{"step": 24850, "dynamics_loss_avg": 0.02918014982715249}
+{"step": 24850, "action_loss_avg": 0.0035703312256373464}
+{"step": 24860, "dynamics_loss_avg": 0.034312783274799585}
+{"step": 24860, "action_loss_avg": 0.0036288217175751924}
+{"step": 24870, "dynamics_loss_avg": 0.03648285772651434}
+{"step": 24870, "action_loss_avg": 0.002978944720234722}
+{"step": 24880, "dynamics_loss_avg": 0.033155471086502075}
+{"step": 24880, "action_loss_avg": 0.0031490541994571688}
+{"step": 24890, "dynamics_loss_avg": 0.0342497912235558}
+{"step": 24890, "action_loss_avg": 0.00390359319280833}
+{"step": 24900, "loss": 0.0336, "learning_rate": 8.955937899511315e-05}
+{"step": 24900, "dynamics_loss_avg": 0.024755195435136556}
+{"step": 24900, "action_loss_avg": 0.002272639027796686}
+{"step": 24910, "dynamics_loss_avg": 0.03776988759636879}
+{"step": 24910, "action_loss_avg": 0.004190928814932704}
+{"step": 24920, "dynamics_loss_avg": 0.02925756201148033}
+{"step": 24920, "action_loss_avg": 0.0028130392864113675}
+{"step": 24930, "dynamics_loss_avg": 0.03296039570122957}
+{"step": 24930, "action_loss_avg": 0.0035374666796997188}
+{"step": 24940, "dynamics_loss_avg": 0.02681604279205203}
+{"step": 24940, "action_loss_avg": 0.003591818327549845}
+{"step": 24950, "loss": 0.0313, "learning_rate": 8.950876402049606e-05}
+{"step": 24950, "dynamics_loss_avg": 0.03363691437989473}
+{"step": 24950, "action_loss_avg": 0.002671024901792407}
+{"step": 24960, "dynamics_loss_avg": 0.03619134891778231}
+{"step": 24960, "action_loss_avg": 0.003241322562098503}
+{"step": 24970, "dynamics_loss_avg": 0.0363201848231256}
+{"step": 24970, "action_loss_avg": 0.0034217095584608615}
+{"step": 24980, "dynamics_loss_avg": 0.03556480053812265}
+{"step": 24980, "action_loss_avg": 0.003630203171633184}
+{"step": 24990, "dynamics_loss_avg": 0.029543277341872454}
+{"step": 24990, "action_loss_avg": 0.002421193482587114}
+{"step": 25000, "loss": 0.0348, "learning_rate": 8.945804103042676e-05}
+{"step": 25000, "dynamics_loss_avg": 0.024583870684728025}
+{"step": 25000, "action_loss_avg": 0.001819462643470615}
+{"step": 25010, "dynamics_loss_avg": 0.0366859408095479}
+{"step": 25010, "action_loss_avg": 0.004294754017610103}
+{"step": 25020, "dynamics_loss_avg": 0.032921730913221835}
+{"step": 25020, "action_loss_avg": 0.0039951079641468825}
+{"step": 25030, "dynamics_loss_avg": 0.025130007416009903}
+{"step": 25030, "action_loss_avg": 0.0030144534655846657}
+{"step": 25040, "dynamics_loss_avg": 0.03961145523935557}
+{"step": 25040, "action_loss_avg": 0.0037028443184681237}
+{"step": 25050, "loss": 0.0344, "learning_rate": 8.940721016357999e-05}
+{"step": 25050, "dynamics_loss_avg": 0.03577994192019105}
+{"step": 25050, "action_loss_avg": 0.0034852853132179007}
+{"step": 25060, "dynamics_loss_avg": 0.03677741046994924}
+{"step": 25060, "action_loss_avg": 0.0040792344487272205}
+{"step": 25070, "dynamics_loss_avg": 0.035047844517976046}
+{"step": 25070, "action_loss_avg": 0.004113928368315101}
+{"step": 25080, "dynamics_loss_avg": 0.033310259506106374}
+{"step": 25080, "action_loss_avg": 0.0031157297664321957}
+{"step": 25090, "dynamics_loss_avg": 0.027771079819649457}
+{"step": 25090, "action_loss_avg": 0.003304063167888671}
+{"step": 25100, "loss": 0.0359, "learning_rate": 8.93562715589254e-05}
+{"step": 25100, "dynamics_loss_avg": 0.041105471551418304}
+{"step": 25100, "action_loss_avg": 0.004667461849749088}
+{"step": 25110, "dynamics_loss_avg": 0.030212816037237644}
+{"step": 25110, "action_loss_avg": 0.0032500326400622726}
+{"step": 25120, "dynamics_loss_avg": 0.027228346094489098}
+{"step": 25120, "action_loss_avg": 0.002663014194695279}
+{"step": 25130, "dynamics_loss_avg": 0.03476219763979316}
+{"step": 25130, "action_loss_avg": 0.003679444780573249}
+{"step": 25140, "dynamics_loss_avg": 0.02999385669827461}
+{"step": 25140, "action_loss_avg": 0.0032628977904096248}
+{"step": 25150, "loss": 0.0314, "learning_rate": 8.930522535572718e-05}
+{"step": 25150, "dynamics_loss_avg": 0.03478276617825031}
+{"step": 25150, "action_loss_avg": 0.0031760880956426263}
+{"step": 25160, "dynamics_loss_avg": 0.025884486362338067}
+{"step": 25160, "action_loss_avg": 0.0029940027510747314}
+{"step": 25170, "dynamics_loss_avg": 0.03445247709751129}
+{"step": 25170, "action_loss_avg": 0.0035932206636061894}
+{"step": 25180, "dynamics_loss_avg": 0.028794060833752154}
+{"step": 25180, "action_loss_avg": 0.0025819595786742864}
+{"step": 25190, "dynamics_loss_avg": 0.03345215348526835}
+{"step": 25190, "action_loss_avg": 0.004096198931802064}
+{"step": 25200, "loss": 0.0336, "learning_rate": 8.925407169354369e-05}
+{"step": 25200, "dynamics_loss_avg": 0.034535128809511664}
+{"step": 25200, "action_loss_avg": 0.0032191308913752438}
+{"step": 25210, "dynamics_loss_avg": 0.040384162310510875}
+{"step": 25210, "action_loss_avg": 0.002893685316666961}
+{"step": 25220, "dynamics_loss_avg": 0.02745981076732278}
+{"step": 25220, "action_loss_avg": 0.0024651839048601687}
+{"step": 25230, "dynamics_loss_avg": 0.023996210657060146}
+{"step": 25230, "action_loss_avg": 0.0025855528860120104}
+{"step": 25240, "dynamics_loss_avg": 0.032014789246022704}
+{"step": 25240, "action_loss_avg": 0.0027428375266026705}
+{"step": 25250, "loss": 0.033, "learning_rate": 8.920281071222712e-05}
+{"step": 25250, "dynamics_loss_avg": 0.029593867342919113}
+{"step": 25250, "action_loss_avg": 0.0027900368091650306}
+{"step": 25260, "dynamics_loss_avg": 0.03887549042701721}
+{"step": 25260, "action_loss_avg": 0.004110311158001423}
+{"step": 25270, "dynamics_loss_avg": 0.036865984462201594}
+{"step": 25270, "action_loss_avg": 0.003789627575315535}
+{"step": 25280, "dynamics_loss_avg": 0.03807163182646036}
+{"step": 25280, "action_loss_avg": 0.004919411416631192}
+{"step": 25290, "dynamics_loss_avg": 0.03173016952350736}
+{"step": 25290, "action_loss_avg": 0.0026818347396329045}
+{"step": 25300, "loss": 0.0373, "learning_rate": 8.915144255192302e-05}
+{"step": 25300, "dynamics_loss_avg": 0.03356889197602868}
+{"step": 25300, "action_loss_avg": 0.003955006727483124}
+{"step": 25310, "dynamics_loss_avg": 0.03573614982888103}
+{"step": 25310, "action_loss_avg": 0.0034294410957954823}
+{"step": 25320, "dynamics_loss_avg": 0.03224724503234029}
+{"step": 25320, "action_loss_avg": 0.0032804921502247453}
+{"step": 25330, "dynamics_loss_avg": 0.02817720710299909}
+{"step": 25330, "action_loss_avg": 0.0029016222862992434}
+{"step": 25340, "dynamics_loss_avg": 0.030240474734455347}
+{"step": 25340, "action_loss_avg": 0.0031661252898629753}
+{"step": 25350, "loss": 0.033, "learning_rate": 8.909996735306996e-05}
+{"step": 25350, "dynamics_loss_avg": 0.03960632709786296}
+{"step": 25350, "action_loss_avg": 0.0050426225061528385}
+{"step": 25360, "dynamics_loss_avg": 0.025372328981757165}
+{"step": 25360, "action_loss_avg": 0.0017545995069667697}
+{"step": 25370, "dynamics_loss_avg": 0.03675170103088021}
+{"step": 25370, "action_loss_avg": 0.003874619700945914}
+{"step": 25380, "dynamics_loss_avg": 0.030985933728516102}
+{"step": 25380, "action_loss_avg": 0.0022757620201446114}
+{"step": 25390, "dynamics_loss_avg": 0.030287110060453416}
+{"step": 25390, "action_loss_avg": 0.0027797954477136954}
+{"step": 25400, "loss": 0.032, "learning_rate": 8.90483852563992e-05}
+{"step": 25400, "dynamics_loss_avg": 0.03410086305812001}
+{"step": 25400, "action_loss_avg": 0.004434088990092277}
+{"step": 25410, "dynamics_loss_avg": 0.03740553464740515}
+{"step": 25410, "action_loss_avg": 0.003532764734700322}
+{"step": 25420, "dynamics_loss_avg": 0.03394714780151844}
+{"step": 25420, "action_loss_avg": 0.00303392517962493}
+{"step": 25430, "dynamics_loss_avg": 0.04155972469598055}
+{"step": 25430, "action_loss_avg": 0.0035910058999434114}
+{"step": 25440, "dynamics_loss_avg": 0.03321594130247831}
+{"step": 25440, "action_loss_avg": 0.002491740486584604}
+{"step": 25450, "loss": 0.0357, "learning_rate": 8.89966964029342e-05}
+{"step": 25450, "dynamics_loss_avg": 0.03858137764036655}
+{"step": 25450, "action_loss_avg": 0.003706271492410451}
+{"step": 25460, "dynamics_loss_avg": 0.035898602847009894}
+{"step": 25460, "action_loss_avg": 0.0023424694139976055}
+{"step": 25470, "dynamics_loss_avg": 0.03193107736296952}
+{"step": 25470, "action_loss_avg": 0.003190024383366108}
+{"step": 25480, "dynamics_loss_avg": 0.027204034104943275}
+{"step": 25480, "action_loss_avg": 0.0024146704585291446}
+{"step": 25490, "dynamics_loss_avg": 0.03694547358900309}
+{"step": 25490, "action_loss_avg": 0.002914005087222904}
+{"step": 25500, "loss": 0.0325, "learning_rate": 8.894490093399033e-05}
+{"step": 25500, "dynamics_loss_avg": 0.025328038074076176}
+{"step": 25500, "action_loss_avg": 0.002196399518288672}
+{"step": 25510, "dynamics_loss_avg": 0.03639472294598818}
+{"step": 25510, "action_loss_avg": 0.0036139095784164963}
+{"step": 25520, "dynamics_loss_avg": 0.0384554348886013}
+{"step": 25520, "action_loss_avg": 0.003697588969953358}
+{"step": 25530, "dynamics_loss_avg": 0.030113789532333613}
+{"step": 25530, "action_loss_avg": 0.002881345577770844}
+{"step": 25540, "dynamics_loss_avg": 0.03684885613620281}
+{"step": 25540, "action_loss_avg": 0.0033249580475967376}
+{"step": 25550, "loss": 0.0343, "learning_rate": 8.88929989911744e-05}
+{"step": 25550, "dynamics_loss_avg": 0.03117037480697036}
+{"step": 25550, "action_loss_avg": 0.0030037221498787404}
+{"step": 25560, "dynamics_loss_avg": 0.025256123673170806}
+{"step": 25560, "action_loss_avg": 0.002214846451533958}
+{"step": 25570, "dynamics_loss_avg": 0.028013052605092525}
+{"step": 25570, "action_loss_avg": 0.00279503685887903}
+{"step": 25580, "dynamics_loss_avg": 0.03624505428597331}
+{"step": 25580, "action_loss_avg": 0.003670753352344036}
+{"step": 25590, "dynamics_loss_avg": 0.028266333881765603}
+{"step": 25590, "action_loss_avg": 0.0023827636148780586}
+{"step": 25600, "loss": 0.0332, "learning_rate": 8.884099071638436e-05}
+{"step": 25600, "dynamics_loss_avg": 0.036277607968077066}
+{"step": 25600, "action_loss_avg": 0.0029585218522697686}
+{"step": 25610, "dynamics_loss_avg": 0.033282877411693335}
+{"step": 25610, "action_loss_avg": 0.003021424065809697}
+{"step": 25620, "dynamics_loss_avg": 0.033683580532670024}
+{"step": 25620, "action_loss_avg": 0.0032938033749815077}
+{"step": 25630, "dynamics_loss_avg": 0.02398095391690731}
+{"step": 25630, "action_loss_avg": 0.0020160247513558716}
+{"step": 25640, "dynamics_loss_avg": 0.028845840506255625}
+{"step": 25640, "action_loss_avg": 0.003194396512117237}
+{"step": 25650, "loss": 0.031, "learning_rate": 8.878887625180884e-05}
+{"step": 25650, "dynamics_loss_avg": 0.028781396336853504}
+{"step": 25650, "action_loss_avg": 0.0035814909264445306}
+{"step": 25660, "dynamics_loss_avg": 0.03170429207384586}
+{"step": 25660, "action_loss_avg": 0.0037628975289408116}
+{"step": 25670, "dynamics_loss_avg": 0.031003065500408412}
+{"step": 25670, "action_loss_avg": 0.0029407835740130396}
+{"step": 25680, "dynamics_loss_avg": 0.03580003511160612}
+{"step": 25680, "action_loss_avg": 0.003541021142154932}
+{"step": 25690, "dynamics_loss_avg": 0.03200374892912805}
+{"step": 25690, "action_loss_avg": 0.0034706242557149382}
+{"step": 25700, "loss": 0.0342, "learning_rate": 8.87366557399268e-05}
+{"step": 25700, "dynamics_loss_avg": 0.026710270438343287}
+{"step": 25700, "action_loss_avg": 0.003046483325306326}
+{"step": 25710, "dynamics_loss_avg": 0.03259998713620007}
+{"step": 25710, "action_loss_avg": 0.003152251782012172}
+{"step": 25720, "dynamics_loss_avg": 0.029141706507653}
+{"step": 25720, "action_loss_avg": 0.003576284029986709}
+{"step": 25730, "dynamics_loss_avg": 0.03503689067438245}
+{"step": 25730, "action_loss_avg": 0.003561455907765776}
+{"step": 25740, "dynamics_loss_avg": 0.03664378114044666}
+{"step": 25740, "action_loss_avg": 0.0039378705143462865}
+{"step": 25750, "loss": 0.034, "learning_rate": 8.868432932350712e-05}
+{"step": 25750, "dynamics_loss_avg": 0.02461370509117842}
+{"step": 25750, "action_loss_avg": 0.0022335943183861675}
+{"step": 25760, "dynamics_loss_avg": 0.037202402390539645}
+{"step": 25760, "action_loss_avg": 0.0032961666700430216}
+{"step": 25770, "dynamics_loss_avg": 0.038439064379781486}
+{"step": 25770, "action_loss_avg": 0.003985974530223757}
+{"step": 25780, "dynamics_loss_avg": 0.03788723889738321}
+{"step": 25780, "action_loss_avg": 0.004066788358613849}
+{"step": 25790, "dynamics_loss_avg": 0.025039371103048325}
+{"step": 25790, "action_loss_avg": 0.0018858821713365614}
+{"step": 25800, "loss": 0.0356, "learning_rate": 8.863189714560822e-05}
+{"step": 25800, "dynamics_loss_avg": 0.03056549858301878}
+{"step": 25800, "action_loss_avg": 0.003929141501430422}
+{"step": 25810, "dynamics_loss_avg": 0.03442344795912504}
+{"step": 25810, "action_loss_avg": 0.00390706657199189}
+{"step": 25820, "dynamics_loss_avg": 0.022740177856758238}
+{"step": 25820, "action_loss_avg": 0.0016953045182162897}
+{"step": 25830, "dynamics_loss_avg": 0.03301093932241202}
+{"step": 25830, "action_loss_avg": 0.002923374169040471}
+{"step": 25840, "dynamics_loss_avg": 0.030937503837049008}
+{"step": 25840, "action_loss_avg": 0.004705364024266601}
+{"step": 25850, "loss": 0.0322, "learning_rate": 8.857935934957769e-05}
+{"step": 25850, "dynamics_loss_avg": 0.03130614580586553}
+{"step": 25850, "action_loss_avg": 0.003473019128432497}
+{"step": 25860, "dynamics_loss_avg": 0.030065974127501248}
+{"step": 25860, "action_loss_avg": 0.0033100927073974164}
+{"step": 25870, "dynamics_loss_avg": 0.03163580279797316}
+{"step": 25870, "action_loss_avg": 0.002604271110612899}
+{"step": 25880, "dynamics_loss_avg": 0.031639337353408334}
+{"step": 25880, "action_loss_avg": 0.0034184422926045953}
+{"step": 25890, "dynamics_loss_avg": 0.039655865915119645}
+{"step": 25890, "action_loss_avg": 0.003794615960214287}
+{"step": 25900, "loss": 0.0338, "learning_rate": 8.852671607905185e-05}
+{"step": 25900, "dynamics_loss_avg": 0.024865716230124235}
+{"step": 25900, "action_loss_avg": 0.0023326908762101085}
+{"step": 25910, "dynamics_loss_avg": 0.030843484122306107}
+{"step": 25910, "action_loss_avg": 0.0030665227328427135}
+{"step": 25920, "dynamics_loss_avg": 0.03539542844519019}
+{"step": 25920, "action_loss_avg": 0.003481220093090087}
+{"step": 25930, "dynamics_loss_avg": 0.028958138078451157}
+{"step": 25930, "action_loss_avg": 0.002963078278116882}
+{"step": 25940, "dynamics_loss_avg": 0.027015209989622237}
+{"step": 25940, "action_loss_avg": 0.002476866904180497}
+{"step": 25950, "loss": 0.0307, "learning_rate": 8.847396747795538e-05}
+{"step": 25950, "dynamics_loss_avg": 0.03580394741147756}
+{"step": 25950, "action_loss_avg": 0.00369225722970441}
+{"step": 25960, "dynamics_loss_avg": 0.029148030234500764}
+{"step": 25960, "action_loss_avg": 0.0033418561448343097}
+{"step": 25970, "dynamics_loss_avg": 0.03151879087090492}
+{"step": 25970, "action_loss_avg": 0.002846132661215961}
+{"step": 25980, "dynamics_loss_avg": 0.026438052020967006}
+{"step": 25980, "action_loss_avg": 0.0022095592692494394}
+{"step": 25990, "dynamics_loss_avg": 0.03105687042698264}
+{"step": 25990, "action_loss_avg": 0.003930301347281784}
+{"step": 26000, "loss": 0.031, "learning_rate": 8.842111369050094e-05}
+{"step": 26000, "dynamics_loss_avg": 0.03298924108967185}
+{"step": 26000, "action_loss_avg": 0.0038609358220128343}
+{"step": 26010, "dynamics_loss_avg": 0.03592966934666038}
+{"step": 26010, "action_loss_avg": 0.0036329028953332454}
+{"step": 26020, "dynamics_loss_avg": 0.03915463350713253}
+{"step": 26020, "action_loss_avg": 0.003626706951763481}
+{"step": 26030, "dynamics_loss_avg": 0.03216192144900561}
+{"step": 26030, "action_loss_avg": 0.0032331364811398087}
+{"step": 26040, "dynamics_loss_avg": 0.038568570744246244}
+{"step": 26040, "action_loss_avg": 0.0036377264885231854}
+{"step": 26050, "loss": 0.0369, "learning_rate": 8.83681548611888e-05}
+{"step": 26050, "dynamics_loss_avg": 0.036288075242191555}
+{"step": 26050, "action_loss_avg": 0.0032823535322677342}
+{"step": 26060, "dynamics_loss_avg": 0.02763909278437495}
+{"step": 26060, "action_loss_avg": 0.002074574213474989}
+{"step": 26070, "dynamics_loss_avg": 0.04130563512444496}
+{"step": 26070, "action_loss_avg": 0.0037915330787654964}
+{"step": 26080, "dynamics_loss_avg": 0.021348364232107998}
+{"step": 26080, "action_loss_avg": 0.0021256780426483603}
+{"step": 26090, "dynamics_loss_avg": 0.03735406380146742}
+{"step": 26090, "action_loss_avg": 0.003360392909962684}
+{"step": 26100, "loss": 0.0346, "learning_rate": 8.831509113480634e-05}
+{"step": 26100, "dynamics_loss_avg": 0.039344159746542574}
+{"step": 26100, "action_loss_avg": 0.0035281694465084}
+{"step": 26110, "dynamics_loss_avg": 0.029150409903377295}
+{"step": 26110, "action_loss_avg": 0.0023965667351149023}
+{"step": 26120, "dynamics_loss_avg": 0.028843293618410825}
+{"step": 26120, "action_loss_avg": 0.0029877216671593486}
+{"step": 26130, "dynamics_loss_avg": 0.02911186181008816}
+{"step": 26130, "action_loss_avg": 0.0032209290307946502}
+{"step": 26140, "dynamics_loss_avg": 0.03297425033524633}
+{"step": 26140, "action_loss_avg": 0.0028692865278571846}
+{"step": 26150, "loss": 0.0312, "learning_rate": 8.826192265642778e-05}
+{"step": 26150, "dynamics_loss_avg": 0.03516018521040678}
+{"step": 26150, "action_loss_avg": 0.0034605388063937426}
+{"step": 26160, "dynamics_loss_avg": 0.0300223627127707}
+{"step": 26160, "action_loss_avg": 0.0027723591425456106}
+{"step": 26170, "dynamics_loss_avg": 0.03625571168959141}
+{"step": 26170, "action_loss_avg": 0.0037151588941924272}
+{"step": 26180, "dynamics_loss_avg": 0.030250806640833617}
+{"step": 26180, "action_loss_avg": 0.0034098615520633756}
+{"step": 26190, "dynamics_loss_avg": 0.037205974012613295}
+{"step": 26190, "action_loss_avg": 0.003143519605509937}
+{"step": 26200, "loss": 0.0361, "learning_rate": 8.82086495714137e-05}
+{"step": 26200, "dynamics_loss_avg": 0.041448050551116465}
+{"step": 26200, "action_loss_avg": 0.005312352860346437}
+{"step": 26210, "dynamics_loss_avg": 0.024171765986829997}
+{"step": 26210, "action_loss_avg": 0.002660442219348624}
+{"step": 26220, "dynamics_loss_avg": 0.034606247674673796}
+{"step": 26220, "action_loss_avg": 0.00386510094976984}
+{"step": 26230, "dynamics_loss_avg": 0.03241264782845974}
+{"step": 26230, "action_loss_avg": 0.0036125865299254656}
+{"step": 26240, "dynamics_loss_avg": 0.037937693670392035}
+{"step": 26240, "action_loss_avg": 0.003636514116078615}
+{"step": 26250, "loss": 0.0331, "learning_rate": 8.81552720254107e-05}
+{"step": 26250, "dynamics_loss_avg": 0.04676797613501549}
+{"step": 26250, "action_loss_avg": 0.005168810387840494}
+{"step": 26260, "dynamics_loss_avg": 0.028581746108829974}
+{"step": 26260, "action_loss_avg": 0.0025120090169366447}
+{"step": 26270, "dynamics_loss_avg": 0.03910662494599819}
+{"step": 26270, "action_loss_avg": 0.005174942768644541}
+{"step": 26280, "dynamics_loss_avg": 0.02554709170944989}
+{"step": 26280, "action_loss_avg": 0.0029238720308057964}
+{"step": 26290, "dynamics_loss_avg": 0.026848918572068215}
+{"step": 26290, "action_loss_avg": 0.002221540070604533}
+{"step": 26300, "loss": 0.0309, "learning_rate": 8.810179016435092e-05}
+{"step": 26300, "dynamics_loss_avg": 0.030964539293199776}
+{"step": 26300, "action_loss_avg": 0.002604613360017538}
+{"step": 26310, "dynamics_loss_avg": 0.04258655235171318}
+{"step": 26310, "action_loss_avg": 0.004250937199685723}
+{"step": 26320, "dynamics_loss_avg": 0.03642470445483923}
+{"step": 26320, "action_loss_avg": 0.003612923179753125}
+{"step": 26330, "dynamics_loss_avg": 0.03676252570003271}
+{"step": 26330, "action_loss_avg": 0.0038325976696796716}
+{"step": 26340, "dynamics_loss_avg": 0.036702797189354895}
+{"step": 26340, "action_loss_avg": 0.003481458919122815}
+{"step": 26350, "loss": 0.0383, "learning_rate": 8.804820413445175e-05}
+{"step": 26350, "dynamics_loss_avg": 0.03217451656237245}
+{"step": 26350, "action_loss_avg": 0.003503001213539392}
+{"step": 26360, "dynamics_loss_avg": 0.025146585982292892}
+{"step": 26360, "action_loss_avg": 0.002443467627745122}
+{"step": 26370, "dynamics_loss_avg": 0.03146496457047761}
+{"step": 26370, "action_loss_avg": 0.00344170059543103}
+{"step": 26380, "dynamics_loss_avg": 0.03890197277069092}
+{"step": 26380, "action_loss_avg": 0.005081844312371686}
+{"step": 26390, "dynamics_loss_avg": 0.0327331192791462}
+{"step": 26390, "action_loss_avg": 0.0033215809147804976}
+{"step": 26400, "loss": 0.0338, "learning_rate": 8.799451408221535e-05}
+{"step": 26400, "dynamics_loss_avg": 0.03062197482213378}
+{"step": 26400, "action_loss_avg": 0.0031708407448604705}
+{"step": 26410, "dynamics_loss_avg": 0.03186580035835505}
+{"step": 26410, "action_loss_avg": 0.0030080428172368557}
+{"step": 26420, "dynamics_loss_avg": 0.034853418450802566}
+{"step": 26420, "action_loss_avg": 0.00392313590273261}
+{"step": 26430, "dynamics_loss_avg": 0.029272647108882666}
+{"step": 26430, "action_loss_avg": 0.0025296475389041005}
+{"step": 26440, "dynamics_loss_avg": 0.04147065095603466}
+{"step": 26440, "action_loss_avg": 0.005260806169826537}
+{"step": 26450, "loss": 0.0319, "learning_rate": 8.794072015442825e-05}
+{"step": 26450, "dynamics_loss_avg": 0.02654493465088308}
+{"step": 26450, "action_loss_avg": 0.003296907211188227}
+{"step": 26460, "dynamics_loss_avg": 0.02022124514915049}
+{"step": 26460, "action_loss_avg": 0.002257992239901796}
+{"step": 26470, "dynamics_loss_avg": 0.026624664850533008}
+{"step": 26470, "action_loss_avg": 0.002591029985342175}
+{"step": 26480, "dynamics_loss_avg": 0.02876288937404752}
+{"step": 26480, "action_loss_avg": 0.0028599258163012563}
+{"step": 26490, "dynamics_loss_avg": 0.0337229214143008}
+{"step": 26490, "action_loss_avg": 0.003124686738010496}
+{"step": 26500, "loss": 0.0318, "learning_rate": 8.788682249816103e-05}
+{"step": 26500, "dynamics_loss_avg": 0.03440232761204243}
+{"step": 26500, "action_loss_avg": 0.003606429579667747}
+{"step": 26510, "dynamics_loss_avg": 0.026211148593574762}
+{"step": 26510, "action_loss_avg": 0.002329753257799894}
+{"step": 26520, "dynamics_loss_avg": 0.03244899660348892}
+{"step": 26520, "action_loss_avg": 0.0035704375244677068}
+{"step": 26530, "dynamics_loss_avg": 0.04209382049739361}
+{"step": 26530, "action_loss_avg": 0.004649111640173942}
+{"step": 26540, "dynamics_loss_avg": 0.024385781213641166}
+{"step": 26540, "action_loss_avg": 0.0023362233070656655}
+{"step": 26550, "loss": 0.0326, "learning_rate": 8.783282126076779e-05}
+{"step": 26550, "dynamics_loss_avg": 0.026178876613266767}
+{"step": 26550, "action_loss_avg": 0.0026333628222346304}
+{"step": 26560, "dynamics_loss_avg": 0.0233455847017467}
+{"step": 26560, "action_loss_avg": 0.001954933474189602}
+{"step": 26570, "dynamics_loss_avg": 0.03380073262378573}
+{"step": 26570, "action_loss_avg": 0.003389894682914019}
+{"step": 26580, "dynamics_loss_avg": 0.020767526305280625}
+{"step": 26580, "action_loss_avg": 0.002277446442167275}
+{"step": 26590, "dynamics_loss_avg": 0.03465608321130276}
+{"step": 26590, "action_loss_avg": 0.0035194904543459416}
+{"step": 26600, "loss": 0.0323, "learning_rate": 8.777871658988588e-05}
+{"step": 26600, "dynamics_loss_avg": 0.030417513195425273}
+{"step": 26600, "action_loss_avg": 0.0025028246687725185}
+{"step": 26610, "dynamics_loss_avg": 0.02485983232036233}
+{"step": 26610, "action_loss_avg": 0.0020440999185666444}
+{"step": 26620, "dynamics_loss_avg": 0.02759809624403715}
+{"step": 26620, "action_loss_avg": 0.002173418621532619}
+{"step": 26630, "dynamics_loss_avg": 0.03506546737626195}
+{"step": 26630, "action_loss_avg": 0.004533182526938617}
+{"step": 26640, "dynamics_loss_avg": 0.030701524391770364}
+{"step": 26640, "action_loss_avg": 0.0024778920109383763}
+{"step": 26650, "loss": 0.0313, "learning_rate": 8.772450863343538e-05}
+{"step": 26650, "dynamics_loss_avg": 0.024593658559024335}
+{"step": 26650, "action_loss_avg": 0.003375349775888026}
+{"step": 26660, "dynamics_loss_avg": 0.025925352051854134}
+{"step": 26660, "action_loss_avg": 0.0024277156102471054}
+{"step": 26670, "dynamics_loss_avg": 0.03196093337610364}
+{"step": 26670, "action_loss_avg": 0.0029057898151222616}
+{"step": 26680, "dynamics_loss_avg": 0.040068383980542424}
+{"step": 26680, "action_loss_avg": 0.0034434346714988353}
+{"step": 26690, "dynamics_loss_avg": 0.03621417535468936}
+{"step": 26690, "action_loss_avg": 0.0031190808571409435}
+{"step": 26700, "loss": 0.0348, "learning_rate": 8.767019753961878e-05}
+{"step": 26700, "dynamics_loss_avg": 0.030743981152772902}
+{"step": 26700, "action_loss_avg": 0.0033014528453350067}
+{"step": 26710, "dynamics_loss_avg": 0.0390537204220891}
+{"step": 26710, "action_loss_avg": 0.0034971248707734047}
+{"step": 26720, "dynamics_loss_avg": 0.031674384232610465}
+{"step": 26720, "action_loss_avg": 0.0032443280215375125}
+{"step": 26730, "dynamics_loss_avg": 0.030660273879766463}
+{"step": 26730, "action_loss_avg": 0.0029571597347967326}
+{"step": 26740, "dynamics_loss_avg": 0.0325289067812264}
+{"step": 26740, "action_loss_avg": 0.0025816561421379445}
+{"step": 26750, "loss": 0.0357, "learning_rate": 8.761578345692053e-05}
+{"step": 26750, "dynamics_loss_avg": 0.041913865692913534}
+{"step": 26750, "action_loss_avg": 0.0034539940766990184}
+{"step": 26760, "dynamics_loss_avg": 0.03172216136008501}
+{"step": 26760, "action_loss_avg": 0.0035523195168934763}
+{"step": 26770, "dynamics_loss_avg": 0.03164723077788949}
+{"step": 26770, "action_loss_avg": 0.002820295630954206}
+{"step": 26780, "dynamics_loss_avg": 0.030384599044919015}
+{"step": 26780, "action_loss_avg": 0.003748076886404306}
+{"step": 26790, "dynamics_loss_avg": 0.03433939842507243}
+{"step": 26790, "action_loss_avg": 0.003408111969474703}
+{"step": 26800, "loss": 0.0341, "learning_rate": 8.75612665341067e-05}
+{"step": 26800, "dynamics_loss_avg": 0.027504826430231333}
+{"step": 26800, "action_loss_avg": 0.002847636048682034}
+{"step": 26810, "dynamics_loss_avg": 0.03585162563249469}
+{"step": 26810, "action_loss_avg": 0.0034774589934386314}
+{"step": 26820, "dynamics_loss_avg": 0.03448229087516665}
+{"step": 26820, "action_loss_avg": 0.003503666544565931}
+{"step": 26830, "dynamics_loss_avg": 0.03377293236553669}
+{"step": 26830, "action_loss_avg": 0.003330957243451849}
+{"step": 26840, "dynamics_loss_avg": 0.026790890283882617}
+{"step": 26840, "action_loss_avg": 0.003574501583352685}
+{"step": 26850, "loss": 0.0336, "learning_rate": 8.75066469202244e-05}
+{"step": 26850, "dynamics_loss_avg": 0.037263241782784465}
+{"step": 26850, "action_loss_avg": 0.00377164373639971}
+{"step": 26860, "dynamics_loss_avg": 0.042777938582003114}
+{"step": 26860, "action_loss_avg": 0.005020077945664525}
+{"step": 26870, "dynamics_loss_avg": 0.034815358463674784}
+{"step": 26870, "action_loss_avg": 0.004017523769289255}
+{"step": 26880, "dynamics_loss_avg": 0.031987310480326415}
+{"step": 26880, "action_loss_avg": 0.0029800173244439064}
+{"step": 26890, "dynamics_loss_avg": 0.03563880398869514}
+{"step": 26890, "action_loss_avg": 0.00416570597444661}
+{"step": 26900, "loss": 0.0353, "learning_rate": 8.745192476460165e-05}
+{"step": 26900, "dynamics_loss_avg": 0.02906324723735452}
+{"step": 26900, "action_loss_avg": 0.003791196772363037}
+{"step": 26910, "dynamics_loss_avg": 0.0266039633192122}
+{"step": 26910, "action_loss_avg": 0.0025911379372701047}
+{"step": 26920, "dynamics_loss_avg": 0.03367991335690022}
+{"step": 26920, "action_loss_avg": 0.0025677322642877697}
+{"step": 26930, "dynamics_loss_avg": 0.03344725510105491}
+{"step": 26930, "action_loss_avg": 0.003142346761887893}
+{"step": 26940, "dynamics_loss_avg": 0.032883504871279}
+{"step": 26940, "action_loss_avg": 0.003572880814317614}
+{"step": 26950, "loss": 0.0335, "learning_rate": 8.739710021684667e-05}
+{"step": 26950, "dynamics_loss_avg": 0.040613337978720666}
+{"step": 26950, "action_loss_avg": 0.003478060907218605}
+{"step": 26960, "dynamics_loss_avg": 0.0339803378097713}
+{"step": 26960, "action_loss_avg": 0.0030428987462073564}
+{"step": 26970, "dynamics_loss_avg": 0.035599898919463156}
+{"step": 26970, "action_loss_avg": 0.00393035524757579}
+{"step": 26980, "dynamics_loss_avg": 0.03226118292659521}
+{"step": 26980, "action_loss_avg": 0.0032262510154396295}
+{"step": 26990, "dynamics_loss_avg": 0.029110955353826285}
+{"step": 26990, "action_loss_avg": 0.0028307714557740836}
+{"step": 27000, "loss": 0.034, "learning_rate": 8.734217342684769e-05}
+{"step": 27000, "dynamics_loss_avg": 0.03030073158442974}
+{"step": 27000, "action_loss_avg": 0.0024876322539057584}
+{"step": 27010, "dynamics_loss_avg": 0.035840675327926876}
+{"step": 27010, "action_loss_avg": 0.003260251774918288}
+{"step": 27020, "dynamics_loss_avg": 0.02553038401529193}
+{"step": 27020, "action_loss_avg": 0.0029994090320542453}
+{"step": 27030, "dynamics_loss_avg": 0.030005947221070528}
+{"step": 27030, "action_loss_avg": 0.003237100248225033}
+{"step": 27040, "dynamics_loss_avg": 0.029279317520558835}
+{"step": 27040, "action_loss_avg": 0.002973964676493779}
+{"step": 27050, "loss": 0.0329, "learning_rate": 8.728714454477247e-05}
+{"step": 27050, "dynamics_loss_avg": 0.032659525983035564}
+{"step": 27050, "action_loss_avg": 0.0038052552263252437}
+{"step": 27060, "dynamics_loss_avg": 0.029493473563343288}
+{"step": 27060, "action_loss_avg": 0.0028358780313283206}
+{"step": 27070, "dynamics_loss_avg": 0.03896178249269724}
+{"step": 27070, "action_loss_avg": 0.0035022613184992222}
+{"step": 27080, "dynamics_loss_avg": 0.034199210023507474}
+{"step": 27080, "action_loss_avg": 0.0028934198839124293}
+{"step": 27090, "dynamics_loss_avg": 0.03912234725430608}
+{"step": 27090, "action_loss_avg": 0.003936300822533667}
+{"step": 27100, "loss": 0.0339, "learning_rate": 8.723201372106788e-05}
+{"step": 27100, "dynamics_loss_avg": 0.03501086067408323}
+{"step": 27100, "action_loss_avg": 0.0037590485124383123}
+{"step": 27110, "dynamics_loss_avg": 0.030608135322108865}
+{"step": 27110, "action_loss_avg": 0.003167344507528469}
+{"step": 27120, "dynamics_loss_avg": 0.036506214551627635}
+{"step": 27120, "action_loss_avg": 0.003851398325059563}
+{"step": 27130, "dynamics_loss_avg": 0.03035600818693638}
+{"step": 27130, "action_loss_avg": 0.002532512880861759}
+{"step": 27140, "dynamics_loss_avg": 0.036352749448269606}
+{"step": 27140, "action_loss_avg": 0.003621842572465539}
+{"step": 27150, "loss": 0.0354, "learning_rate": 8.717678110645948e-05}
+{"step": 27150, "dynamics_loss_avg": 0.03490318553522229}
+{"step": 27150, "action_loss_avg": 0.003573830088134855}
+{"step": 27160, "dynamics_loss_avg": 0.025405125878751277}
+{"step": 27160, "action_loss_avg": 0.0026991583989001812}
+{"step": 27170, "dynamics_loss_avg": 0.02763464916497469}
+{"step": 27170, "action_loss_avg": 0.0026958533679135145}
+{"step": 27180, "dynamics_loss_avg": 0.03914118222892284}
+{"step": 27180, "action_loss_avg": 0.0032418289105407895}
+{"step": 27190, "dynamics_loss_avg": 0.030430804844945668}
+{"step": 27190, "action_loss_avg": 0.0037598284427076576}
+{"step": 27200, "loss": 0.0354, "learning_rate": 8.712144685195112e-05}
+{"step": 27200, "dynamics_loss_avg": 0.03981471359729767}
+{"step": 27200, "action_loss_avg": 0.003834579000249505}
+{"step": 27210, "dynamics_loss_avg": 0.03408871907740831}
+{"step": 27210, "action_loss_avg": 0.0035411436809226872}
+{"step": 27220, "dynamics_loss_avg": 0.039283053809776904}
+{"step": 27220, "action_loss_avg": 0.0034539413987658917}
+{"step": 27230, "dynamics_loss_avg": 0.039566651731729505}
+{"step": 27230, "action_loss_avg": 0.003727269812952727}
+{"step": 27240, "dynamics_loss_avg": 0.029658980667591095}
+{"step": 27240, "action_loss_avg": 0.002244542445987463}
+{"step": 27250, "loss": 0.0345, "learning_rate": 8.706601110882455e-05}
+{"step": 27250, "dynamics_loss_avg": 0.030914112646132707}
+{"step": 27250, "action_loss_avg": 0.0024789545452222226}
+{"step": 27260, "dynamics_loss_avg": 0.029679470509290696}
+{"step": 27260, "action_loss_avg": 0.002872944076079875}
+{"step": 27270, "dynamics_loss_avg": 0.035605130111798645}
+{"step": 27270, "action_loss_avg": 0.003192466153996065}
+{"step": 27280, "dynamics_loss_avg": 0.03941984814591706}
+{"step": 27280, "action_loss_avg": 0.0035674036713317036}
+{"step": 27290, "dynamics_loss_avg": 0.03911482337862253}
+{"step": 27290, "action_loss_avg": 0.0032852609059773386}
+{"step": 27300, "loss": 0.0336, "learning_rate": 8.701047402863896e-05}
+{"step": 27300, "dynamics_loss_avg": 0.027908471692353488}
+{"step": 27300, "action_loss_avg": 0.002009531925432384}
+{"step": 27310, "dynamics_loss_avg": 0.03418514970690012}
+{"step": 27310, "action_loss_avg": 0.002925173204857856}
+{"step": 27320, "dynamics_loss_avg": 0.03604707070626319}
+{"step": 27320, "action_loss_avg": 0.0035749361501075327}
+{"step": 27330, "dynamics_loss_avg": 0.03309953054413199}
+{"step": 27330, "action_loss_avg": 0.004000056569930166}
+{"step": 27340, "dynamics_loss_avg": 0.04308282276615501}
+{"step": 27340, "action_loss_avg": 0.004206984909251333}
+{"step": 27350, "loss": 0.036, "learning_rate": 8.695483576323063e-05}
+{"step": 27350, "dynamics_loss_avg": 0.03595341052860022}
+{"step": 27350, "action_loss_avg": 0.003353642602451146}
+{"step": 27360, "dynamics_loss_avg": 0.027460836363025008}
+{"step": 27360, "action_loss_avg": 0.0030015730124432595}
+{"step": 27370, "dynamics_loss_avg": 0.03636635765433312}
+{"step": 27370, "action_loss_avg": 0.003562110895290971}
+{"step": 27380, "dynamics_loss_avg": 0.036672267224639656}
+{"step": 27380, "action_loss_avg": 0.0034966937673743814}
+{"step": 27390, "dynamics_loss_avg": 0.03479553600773215}
+{"step": 27390, "action_loss_avg": 0.0025581385707482696}
+{"step": 27400, "loss": 0.0328, "learning_rate": 8.689909646471243e-05}
+{"step": 27400, "dynamics_loss_avg": 0.032407864835113286}
+{"step": 27400, "action_loss_avg": 0.003031925472896546}
+{"step": 27410, "dynamics_loss_avg": 0.0320020217448473}
+{"step": 27410, "action_loss_avg": 0.0027833107917103915}
+{"step": 27420, "dynamics_loss_avg": 0.03295380594208837}
+{"step": 27420, "action_loss_avg": 0.003662061190698296}
+{"step": 27430, "dynamics_loss_avg": 0.031213511526584626}
+{"step": 27430, "action_loss_avg": 0.002986487769521773}
+{"step": 27440, "dynamics_loss_avg": 0.025868137925863267}
+{"step": 27440, "action_loss_avg": 0.0022255576273892074}
+{"step": 27450, "loss": 0.0315, "learning_rate": 8.68432562854735e-05}
+{"step": 27450, "dynamics_loss_avg": 0.027738002501428126}
+{"step": 27450, "action_loss_avg": 0.002747631061356515}
+{"step": 27460, "dynamics_loss_avg": 0.026865608245134353}
+{"step": 27460, "action_loss_avg": 0.0031499128206633033}
+{"step": 27470, "dynamics_loss_avg": 0.03411769955419004}
+{"step": 27470, "action_loss_avg": 0.0033216411480680107}
+{"step": 27480, "dynamics_loss_avg": 0.03475997801870108}
+{"step": 27480, "action_loss_avg": 0.004180405742954463}
+{"step": 27490, "dynamics_loss_avg": 0.03862913744524121}
+{"step": 27490, "action_loss_avg": 0.004157703381497413}
+{"step": 27500, "loss": 0.0351, "learning_rate": 8.678731537817873e-05}
+{"step": 27500, "dynamics_loss_avg": 0.03558173198252916}
+{"step": 27500, "action_loss_avg": 0.0030316931894049048}
+{"step": 27510, "dynamics_loss_avg": 0.02938239062204957}
+{"step": 27510, "action_loss_avg": 0.0037466614914592354}
+{"step": 27520, "dynamics_loss_avg": 0.029371701972559096}
+{"step": 27520, "action_loss_avg": 0.003613003733335063}
+{"step": 27530, "dynamics_loss_avg": 0.027537128049880268}
+{"step": 27530, "action_loss_avg": 0.00227648169384338}
+{"step": 27540, "dynamics_loss_avg": 0.029297230020165443}
+{"step": 27540, "action_loss_avg": 0.0028552120085805653}
+{"step": 27550, "loss": 0.0325, "learning_rate": 8.673127389576843e-05}
+{"step": 27550, "dynamics_loss_avg": 0.03490702072158456}
+{"step": 27550, "action_loss_avg": 0.0037935530999675393}
+{"step": 27560, "dynamics_loss_avg": 0.029552052821964027}
+{"step": 27560, "action_loss_avg": 0.002989171806257218}
+{"step": 27570, "dynamics_loss_avg": 0.03197277979925275}
+{"step": 27570, "action_loss_avg": 0.002763030678033829}
+{"step": 27580, "dynamics_loss_avg": 0.02958360929042101}
+{"step": 27580, "action_loss_avg": 0.0024030354688875377}
+{"step": 27590, "dynamics_loss_avg": 0.041193814901635054}
+{"step": 27590, "action_loss_avg": 0.003859218582510948}
+{"step": 27600, "loss": 0.031, "learning_rate": 8.667513199145789e-05}
+{"step": 27600, "dynamics_loss_avg": 0.032159652933478354}
+{"step": 27600, "action_loss_avg": 0.0028077625727746637}
+{"step": 27610, "dynamics_loss_avg": 0.0243927086237818}
+{"step": 27610, "action_loss_avg": 0.0023749282816424968}
+{"step": 27620, "dynamics_loss_avg": 0.027389547042548656}
+{"step": 27620, "action_loss_avg": 0.0024978516856208445}
+{"step": 27630, "dynamics_loss_avg": 0.03464817451313138}
+{"step": 27630, "action_loss_avg": 0.003005888324696571}
+{"step": 27640, "dynamics_loss_avg": 0.032513427967205646}
+{"step": 27640, "action_loss_avg": 0.002780745486961678}
+{"step": 27650, "loss": 0.0307, "learning_rate": 8.661888981873691e-05}
+{"step": 27650, "dynamics_loss_avg": 0.02825848525390029}
+{"step": 27650, "action_loss_avg": 0.002420122630428523}
+{"step": 27660, "dynamics_loss_avg": 0.03013015314936638}
+{"step": 27660, "action_loss_avg": 0.0023450449225492775}
+{"step": 27670, "dynamics_loss_avg": 0.03491235673427582}
+{"step": 27670, "action_loss_avg": 0.003232769120950252}
+{"step": 27680, "dynamics_loss_avg": 0.03302629962563515}
+{"step": 27680, "action_loss_avg": 0.004029736749362201}
+{"step": 27690, "dynamics_loss_avg": 0.03814880987629295}
+{"step": 27690, "action_loss_avg": 0.004245728580281138}
+{"step": 27700, "loss": 0.0325, "learning_rate": 8.656254753136946e-05}
+{"step": 27700, "dynamics_loss_avg": 0.027777891233563425}
+{"step": 27700, "action_loss_avg": 0.003069357143249363}
+{"step": 27710, "dynamics_loss_avg": 0.034406680054962634}
+{"step": 27710, "action_loss_avg": 0.0034159724367782474}
+{"step": 27720, "dynamics_loss_avg": 0.026103417761623858}
+{"step": 27720, "action_loss_avg": 0.0026084849261678754}
+{"step": 27730, "dynamics_loss_avg": 0.02983798524364829}
+{"step": 27730, "action_loss_avg": 0.0037955639185383917}
+{"step": 27740, "dynamics_loss_avg": 0.039076049253344534}
+{"step": 27740, "action_loss_avg": 0.003559859795495868}
+{"step": 27750, "loss": 0.0321, "learning_rate": 8.65061052833932e-05}
+{"step": 27750, "dynamics_loss_avg": 0.026293412037193774}
+{"step": 27750, "action_loss_avg": 0.002863696636632085}
+{"step": 27760, "dynamics_loss_avg": 0.028642184752970933}
+{"step": 27760, "action_loss_avg": 0.001899732812307775}
+{"step": 27770, "dynamics_loss_avg": 0.037880546413362026}
+{"step": 27770, "action_loss_avg": 0.00469013269757852}
+{"step": 27780, "dynamics_loss_avg": 0.02600766597315669}
+{"step": 27780, "action_loss_avg": 0.002057582780253142}
+{"step": 27790, "dynamics_loss_avg": 0.023690312495455147}
+{"step": 27790, "action_loss_avg": 0.0022485522844363005}
+{"step": 27800, "loss": 0.0322, "learning_rate": 8.644956322911908e-05}
+{"step": 27800, "dynamics_loss_avg": 0.044199797231703995}
+{"step": 27800, "action_loss_avg": 0.003565079084364697}
+{"step": 27810, "dynamics_loss_avg": 0.02644891059026122}
+{"step": 27810, "action_loss_avg": 0.002491839588037692}
+{"step": 27820, "dynamics_loss_avg": 0.03422581357881427}
+{"step": 27820, "action_loss_avg": 0.003114964347332716}
+{"step": 27830, "dynamics_loss_avg": 0.03608887679874897}
+{"step": 27830, "action_loss_avg": 0.0026079505449160935}
+{"step": 27840, "dynamics_loss_avg": 0.042668516375124456}
+{"step": 27840, "action_loss_avg": 0.004534086969215423}
+{"step": 27850, "loss": 0.0342, "learning_rate": 8.639292152313091e-05}
+{"step": 27850, "dynamics_loss_avg": 0.03201289298012853}
+{"step": 27850, "action_loss_avg": 0.0029929625801742078}
+{"step": 27860, "dynamics_loss_avg": 0.03199748913757503}
+{"step": 27860, "action_loss_avg": 0.002919850719626993}
+{"step": 27870, "dynamics_loss_avg": 0.030242927465587856}
+{"step": 27870, "action_loss_avg": 0.0023087103152647616}
+{"step": 27880, "dynamics_loss_avg": 0.0269208415877074}
+{"step": 27880, "action_loss_avg": 0.0023171503620687873}
+{"step": 27890, "dynamics_loss_avg": 0.02811113968491554}
+{"step": 27890, "action_loss_avg": 0.0024006842751987277}
+{"step": 27900, "loss": 0.0301, "learning_rate": 8.633618032028496e-05}
+{"step": 27900, "dynamics_loss_avg": 0.0258996550925076}
+{"step": 27900, "action_loss_avg": 0.0019425887381657957}
+{"step": 27910, "dynamics_loss_avg": 0.028636310994625092}
+{"step": 27910, "action_loss_avg": 0.002424475195584819}
+{"step": 27920, "dynamics_loss_avg": 0.029864966310560702}
+{"step": 27920, "action_loss_avg": 0.0025010034325532613}
+{"step": 27930, "dynamics_loss_avg": 0.022968269791454075}
+{"step": 27930, "action_loss_avg": 0.0015663172554923222}
+{"step": 27940, "dynamics_loss_avg": 0.033328605256974696}
+{"step": 27940, "action_loss_avg": 0.0024212938151322305}
+{"step": 27950, "loss": 0.0281, "learning_rate": 8.62793397757095e-05}
+{"step": 27950, "dynamics_loss_avg": 0.03015517517924309}
+{"step": 27950, "action_loss_avg": 0.002351945557165891}
+{"step": 27960, "dynamics_loss_avg": 0.02660049251280725}
+{"step": 27960, "action_loss_avg": 0.0019544408045476303}
+{"step": 27970, "dynamics_loss_avg": 0.030929691158235073}
+{"step": 27970, "action_loss_avg": 0.002713513339404017}
+{"step": 27980, "dynamics_loss_avg": 0.03427257360890508}
+{"step": 27980, "action_loss_avg": 0.0033708377450238913}
+{"step": 27990, "dynamics_loss_avg": 0.0355993028730154}
+{"step": 27990, "action_loss_avg": 0.00287571054068394}
+{"step": 28000, "loss": 0.0319, "learning_rate": 8.622240004480441e-05}
+{"step": 28000, "dynamics_loss_avg": 0.02786538302898407}
+{"step": 28000, "action_loss_avg": 0.0023363522603176536}
+{"step": 28010, "dynamics_loss_avg": 0.036969923228025434}
+{"step": 28010, "action_loss_avg": 0.0033155390061438083}
+{"step": 28020, "dynamics_loss_avg": 0.025087843369692563}
+{"step": 28020, "action_loss_avg": 0.0021842418354935944}
+{"step": 28030, "dynamics_loss_avg": 0.026150387804955245}
+{"step": 28030, "action_loss_avg": 0.0025991501403041183}
+{"step": 28040, "dynamics_loss_avg": 0.033141205459833144}
+{"step": 28040, "action_loss_avg": 0.0026261632796376944}
+{"step": 28050, "loss": 0.0319, "learning_rate": 8.616536128324078e-05}
+{"step": 28050, "dynamics_loss_avg": 0.028755435813218357}
+{"step": 28050, "action_loss_avg": 0.0024517359561286867}
+{"step": 28060, "dynamics_loss_avg": 0.02956794062629342}
+{"step": 28060, "action_loss_avg": 0.002858205488882959}
+{"step": 28070, "dynamics_loss_avg": 0.03300820840522647}
+{"step": 28070, "action_loss_avg": 0.004178613773547113}
+{"step": 28080, "dynamics_loss_avg": 0.0312552310526371}
+{"step": 28080, "action_loss_avg": 0.0036195082124322654}
+{"step": 28090, "dynamics_loss_avg": 0.03524751737713814}
+{"step": 28090, "action_loss_avg": 0.0025338591658510268}
+{"step": 28100, "loss": 0.0329, "learning_rate": 8.610822364696034e-05}
+{"step": 28100, "dynamics_loss_avg": 0.03252262175083161}
+{"step": 28100, "action_loss_avg": 0.0031979955034330486}
+{"step": 28110, "dynamics_loss_avg": 0.03774769455194473}
+{"step": 28110, "action_loss_avg": 0.00353809722000733}
+{"step": 28120, "dynamics_loss_avg": 0.020341629115864634}
+{"step": 28120, "action_loss_avg": 0.0018009808962233364}
+{"step": 28130, "dynamics_loss_avg": 0.02807876169681549}
+{"step": 28130, "action_loss_avg": 0.0021067110588774084}
+{"step": 28140, "dynamics_loss_avg": 0.024591472558677198}
+{"step": 28140, "action_loss_avg": 0.0016620943759335205}
+{"step": 28150, "loss": 0.0298, "learning_rate": 8.605098729217525e-05}
+{"step": 28150, "dynamics_loss_avg": 0.031789738684892654}
+{"step": 28150, "action_loss_avg": 0.003206545568536967}
+{"step": 28160, "dynamics_loss_avg": 0.03185280538164079}
+{"step": 28160, "action_loss_avg": 0.003000397502910346}
+{"step": 28170, "dynamics_loss_avg": 0.037704589497298005}
+{"step": 28170, "action_loss_avg": 0.0024334684305358676}
+{"step": 28180, "dynamics_loss_avg": 0.02731609232723713}
+{"step": 28180, "action_loss_avg": 0.002287500537931919}
+{"step": 28190, "dynamics_loss_avg": 0.03104224530979991}
+{"step": 28190, "action_loss_avg": 0.0027048499148804696}
+{"step": 28200, "loss": 0.0337, "learning_rate": 8.59936523753675e-05}
+{"step": 28200, "dynamics_loss_avg": 0.025433185417205094}
+{"step": 28200, "action_loss_avg": 0.00215121858054772}
+{"step": 28210, "dynamics_loss_avg": 0.03547337725758552}
+{"step": 28210, "action_loss_avg": 0.0030368784675374625}
+{"step": 28220, "dynamics_loss_avg": 0.03407636424526572}
+{"step": 28220, "action_loss_avg": 0.003025254042586312}
+{"step": 28230, "dynamics_loss_avg": 0.02919185571372509}
+{"step": 28230, "action_loss_avg": 0.0025684006861411033}
+{"step": 28240, "dynamics_loss_avg": 0.03064079973846674}
+{"step": 28240, "action_loss_avg": 0.002940563065931201}
+{"step": 28250, "loss": 0.0343, "learning_rate": 8.593621905328858e-05}
+{"step": 28250, "dynamics_loss_avg": 0.026557125616818666}
+{"step": 28250, "action_loss_avg": 0.003028355597052723}
+{"step": 28260, "dynamics_loss_avg": 0.02615031721070409}
+{"step": 28260, "action_loss_avg": 0.0030383480538148434}
+{"step": 28270, "dynamics_loss_avg": 0.0287980692461133}
+{"step": 28270, "action_loss_avg": 0.002977761556394398}
+{"step": 28280, "dynamics_loss_avg": 0.030489136651158332}
+{"step": 28280, "action_loss_avg": 0.002341019851155579}
+{"step": 28290, "dynamics_loss_avg": 0.029108716268092395}
+{"step": 28290, "action_loss_avg": 0.0024799401813652366}
+{"step": 28300, "loss": 0.0305, "learning_rate": 8.587868748295898e-05}
+{"step": 28300, "dynamics_loss_avg": 0.028684933297336103}
+{"step": 28300, "action_loss_avg": 0.0027674543205648662}
+{"step": 28310, "dynamics_loss_avg": 0.02748478688299656}
+{"step": 28310, "action_loss_avg": 0.0022746653761714698}
+{"step": 28320, "dynamics_loss_avg": 0.03285604971460998}
+{"step": 28320, "action_loss_avg": 0.0029177913209423425}
+{"step": 28330, "dynamics_loss_avg": 0.03227030504494906}
+{"step": 28330, "action_loss_avg": 0.003296550805680454}
+{"step": 28340, "dynamics_loss_avg": 0.03778210915625095}
+{"step": 28340, "action_loss_avg": 0.0027070312644355}
+{"step": 28350, "loss": 0.0332, "learning_rate": 8.582105782166783e-05}
+{"step": 28350, "dynamics_loss_avg": 0.038794684875756505}
+{"step": 28350, "action_loss_avg": 0.0030499064887408167}
+{"step": 28360, "dynamics_loss_avg": 0.037208940647542474}
+{"step": 28360, "action_loss_avg": 0.0034925382351502776}
+{"step": 28370, "dynamics_loss_avg": 0.029860304761677982}
+{"step": 28370, "action_loss_avg": 0.0025624608038924634}
+{"step": 28380, "dynamics_loss_avg": 0.033057578932493926}
+{"step": 28380, "action_loss_avg": 0.0038455789908766747}
+{"step": 28390, "dynamics_loss_avg": 0.03304175855591893}
+{"step": 28390, "action_loss_avg": 0.004326082079205662}
+{"step": 28400, "loss": 0.0327, "learning_rate": 8.576333022697242e-05}
+{"step": 28400, "dynamics_loss_avg": 0.026772054191678763}
+{"step": 28400, "action_loss_avg": 0.003458686184603721}
+{"step": 28410, "dynamics_loss_avg": 0.03470959942787886}
+{"step": 28410, "action_loss_avg": 0.0032975179608911278}
+{"step": 28420, "dynamics_loss_avg": 0.028738446719944476}
+{"step": 28420, "action_loss_avg": 0.0024195558158680796}
+{"step": 28430, "dynamics_loss_avg": 0.027839966304600238}
+{"step": 28430, "action_loss_avg": 0.0025328040355816483}
+{"step": 28440, "dynamics_loss_avg": 0.02966103944927454}
+{"step": 28440, "action_loss_avg": 0.003740854619536549}
+{"step": 28450, "loss": 0.0335, "learning_rate": 8.57055048566978e-05}
+{"step": 28450, "dynamics_loss_avg": 0.04460193905979395}
+{"step": 28450, "action_loss_avg": 0.004624205239815637}
+{"step": 28460, "dynamics_loss_avg": 0.03152844104915857}
+{"step": 28460, "action_loss_avg": 0.00242264837725088}
+{"step": 28470, "dynamics_loss_avg": 0.03287827651947737}
+{"step": 28470, "action_loss_avg": 0.0031830308376811444}
+{"step": 28480, "dynamics_loss_avg": 0.024071381893008947}
+{"step": 28480, "action_loss_avg": 0.0020119989174418153}
+{"step": 28490, "dynamics_loss_avg": 0.03536576507613063}
+{"step": 28490, "action_loss_avg": 0.0034767470322549345}
+{"step": 28500, "loss": 0.0317, "learning_rate": 8.564758186893628e-05}
+{"step": 28500, "dynamics_loss_avg": 0.026318060606718062}
+{"step": 28500, "action_loss_avg": 0.002703953464515507}
+{"step": 28510, "dynamics_loss_avg": 0.027748087234795094}
+{"step": 28510, "action_loss_avg": 0.0016527778992895038}
+{"step": 28520, "dynamics_loss_avg": 0.031207925733178855}
+{"step": 28520, "action_loss_avg": 0.0031252774031599985}
+{"step": 28530, "dynamics_loss_avg": 0.028422245010733604}
+{"step": 28530, "action_loss_avg": 0.0021761034469818695}
+{"step": 28540, "dynamics_loss_avg": 0.034871914377436045}
+{"step": 28540, "action_loss_avg": 0.0030251594143919647}
+{"step": 28550, "loss": 0.0303, "learning_rate": 8.558956142204717e-05}
+{"step": 28550, "dynamics_loss_avg": 0.026332360785454513}
+{"step": 28550, "action_loss_avg": 0.0024888588348403575}
+{"step": 28560, "dynamics_loss_avg": 0.024259837809950113}
+{"step": 28560, "action_loss_avg": 0.002658884791890159}
+{"step": 28570, "dynamics_loss_avg": 0.023998748697340488}
+{"step": 28570, "action_loss_avg": 0.0019001670472789556}
+{"step": 28580, "dynamics_loss_avg": 0.0352902926504612}
+{"step": 28580, "action_loss_avg": 0.003098096715984866}
+{"step": 28590, "dynamics_loss_avg": 0.03306782823055983}
+{"step": 28590, "action_loss_avg": 0.0026858615688979625}
+{"step": 28600, "loss": 0.0306, "learning_rate": 8.553144367465609e-05}
+{"step": 28600, "dynamics_loss_avg": 0.030133255291730165}
+{"step": 28600, "action_loss_avg": 0.0027569428959395735}
+{"step": 28610, "dynamics_loss_avg": 0.02685037925839424}
+{"step": 28610, "action_loss_avg": 0.0025216603302396835}
+{"step": 28620, "dynamics_loss_avg": 0.03434941191226244}
+{"step": 28620, "action_loss_avg": 0.0027865054900757967}
+{"step": 28630, "dynamics_loss_avg": 0.029894388932734727}
+{"step": 28630, "action_loss_avg": 0.0030150737380608915}
+{"step": 28640, "dynamics_loss_avg": 0.028382817236706614}
+{"step": 28640, "action_loss_avg": 0.0026592434209305794}
+{"step": 28650, "loss": 0.0315, "learning_rate": 8.547322878565478e-05}
+{"step": 28650, "dynamics_loss_avg": 0.028677313588559628}
+{"step": 28650, "action_loss_avg": 0.002251039951806888}
+{"step": 28660, "dynamics_loss_avg": 0.023666601162403822}
+{"step": 28660, "action_loss_avg": 0.002350501119508408}
+{"step": 28670, "dynamics_loss_avg": 0.03131897794082761}
+{"step": 28670, "action_loss_avg": 0.0029741070582531394}
+{"step": 28680, "dynamics_loss_avg": 0.03420978933572769}
+{"step": 28680, "action_loss_avg": 0.002646706544328481}
+{"step": 28690, "dynamics_loss_avg": 0.03806464765220881}
+{"step": 28690, "action_loss_avg": 0.00330705177038908}
+{"step": 28700, "loss": 0.0333, "learning_rate": 8.541491691420051e-05}
+{"step": 28700, "dynamics_loss_avg": 0.039769341424107554}
+{"step": 28700, "action_loss_avg": 0.002913936332333833}
+{"step": 28710, "dynamics_loss_avg": 0.031371935782954094}
+{"step": 28710, "action_loss_avg": 0.0029913459846284242}
+{"step": 28720, "dynamics_loss_avg": 0.03334117503836751}
+{"step": 28720, "action_loss_avg": 0.0035481573635479436}
+{"step": 28730, "dynamics_loss_avg": 0.03646625187247991}
+{"step": 28730, "action_loss_avg": 0.004691857093712315}
+{"step": 28740, "dynamics_loss_avg": 0.027762315329164268}
+{"step": 28740, "action_loss_avg": 0.001892413559835404}
+{"step": 28750, "loss": 0.0335, "learning_rate": 8.53565082197157e-05}
+{"step": 28750, "dynamics_loss_avg": 0.03168584955856204}
+{"step": 28750, "action_loss_avg": 0.0025077818834688516}
+{"step": 28760, "dynamics_loss_avg": 0.03412710484117269}
+{"step": 28760, "action_loss_avg": 0.0028462795191444455}
+{"step": 28770, "dynamics_loss_avg": 0.029298535734415054}
+{"step": 28770, "action_loss_avg": 0.0029492619214579463}
+{"step": 28780, "dynamics_loss_avg": 0.033917094394564626}
+{"step": 28780, "action_loss_avg": 0.0026902221608906983}
+{"step": 28790, "dynamics_loss_avg": 0.0305735785048455}
+{"step": 28790, "action_loss_avg": 0.002630379571928643}
+{"step": 28800, "loss": 0.0316, "learning_rate": 8.529800286188752e-05}
+{"step": 28800, "dynamics_loss_avg": 0.031678395718336104}
+{"step": 28800, "action_loss_avg": 0.0018960891989991068}
+{"step": 28810, "dynamics_loss_avg": 0.03619200531393289}
+{"step": 28810, "action_loss_avg": 0.00292255450040102}
+{"step": 28820, "dynamics_loss_avg": 0.029503681231290102}
+{"step": 28820, "action_loss_avg": 0.002209266572026536}
+{"step": 28830, "dynamics_loss_avg": 0.032658861577510835}
+{"step": 28830, "action_loss_avg": 0.002752445824444294}
+{"step": 28840, "dynamics_loss_avg": 0.03085606200620532}
+{"step": 28840, "action_loss_avg": 0.0027524743927642703}
+{"step": 28850, "loss": 0.032, "learning_rate": 8.523940100066735e-05}
+{"step": 28850, "dynamics_loss_avg": 0.02460219906643033}
+{"step": 28850, "action_loss_avg": 0.0019493267522193492}
+{"step": 28860, "dynamics_loss_avg": 0.030819275043904783}
+{"step": 28860, "action_loss_avg": 0.0028712863859254867}
+{"step": 28870, "dynamics_loss_avg": 0.03513322388753295}
+{"step": 28870, "action_loss_avg": 0.0034230472985655068}
+{"step": 28880, "dynamics_loss_avg": 0.029940359108150006}
+{"step": 28880, "action_loss_avg": 0.002381781325675547}
+{"step": 28890, "dynamics_loss_avg": 0.035748927388340235}
+{"step": 28890, "action_loss_avg": 0.0031178991310298445}
+{"step": 28900, "loss": 0.0342, "learning_rate": 8.518070279627047e-05}
+{"step": 28900, "dynamics_loss_avg": 0.029816762916743754}
+{"step": 28900, "action_loss_avg": 0.002441486844327301}
+{"step": 28910, "dynamics_loss_avg": 0.0304853182984516}
+{"step": 28910, "action_loss_avg": 0.0027952706615906207}
+{"step": 28920, "dynamics_loss_avg": 0.03108496554195881}
+{"step": 28920, "action_loss_avg": 0.0027714075054973363}
+{"step": 28930, "dynamics_loss_avg": 0.034243514947593215}
+{"step": 28930, "action_loss_avg": 0.0029262520314659924}
+{"step": 28940, "dynamics_loss_avg": 0.031966625386849044}
+{"step": 28940, "action_loss_avg": 0.0032654560229275374}
+{"step": 28950, "loss": 0.0332, "learning_rate": 8.51219084091755e-05}
+{"step": 28950, "dynamics_loss_avg": 0.03403240591287613}
+{"step": 28950, "action_loss_avg": 0.002977179811568931}
+{"step": 28960, "dynamics_loss_avg": 0.03300257306545973}
+{"step": 28960, "action_loss_avg": 0.0033798901946283876}
+{"step": 28970, "dynamics_loss_avg": 0.022286593867465853}
+{"step": 28970, "action_loss_avg": 0.0026884604478254913}
+{"step": 28980, "dynamics_loss_avg": 0.03559603905305266}
+{"step": 28980, "action_loss_avg": 0.0033298802678473293}
+{"step": 28990, "dynamics_loss_avg": 0.0349390085786581}
+{"step": 28990, "action_loss_avg": 0.0036184587283059956}
+{"step": 29000, "loss": 0.0309, "learning_rate": 8.506301800012408e-05}
+{"step": 29000, "dynamics_loss_avg": 0.022601614706218243}
+{"step": 29000, "action_loss_avg": 0.002395815902855247}
+{"step": 29010, "dynamics_loss_avg": 0.02962510446086526}
+{"step": 29010, "action_loss_avg": 0.0032481809495948253}
+{"step": 29020, "dynamics_loss_avg": 0.026849678438156842}
+{"step": 29020, "action_loss_avg": 0.002240825357148424}
+{"step": 29030, "dynamics_loss_avg": 0.029597997758537532}
+{"step": 29030, "action_loss_avg": 0.003077232354553416}
+{"step": 29040, "dynamics_loss_avg": 0.03339270073920488}
+{"step": 29040, "action_loss_avg": 0.0029270005587022753}
+{"step": 29050, "loss": 0.0306, "learning_rate": 8.500403173012032e-05}
+{"step": 29050, "dynamics_loss_avg": 0.03159610177390278}
+{"step": 29050, "action_loss_avg": 0.0030069982167333364}
+{"step": 29060, "dynamics_loss_avg": 0.03146954895928502}
+{"step": 29060, "action_loss_avg": 0.0029145389155019073}
+{"step": 29070, "dynamics_loss_avg": 0.028013757057487966}
+{"step": 29070, "action_loss_avg": 0.002927996852668002}
+{"step": 29080, "dynamics_loss_avg": 0.032375136855989695}
+{"step": 29080, "action_loss_avg": 0.0023761592630762605}
+{"step": 29090, "dynamics_loss_avg": 0.03454699832946062}
+{"step": 29090, "action_loss_avg": 0.002538858586922288}
+{"step": 29100, "loss": 0.0313, "learning_rate": 8.494494976043045e-05}
+{"step": 29100, "dynamics_loss_avg": 0.031062886212021114}
+{"step": 29100, "action_loss_avg": 0.002687238098587841}
+{"step": 29110, "dynamics_loss_avg": 0.03990995064377785}
+{"step": 29110, "action_loss_avg": 0.00340806370950304}
+{"step": 29120, "dynamics_loss_avg": 0.028375958744436502}
+{"step": 29120, "action_loss_avg": 0.0023138280492275955}
+{"step": 29130, "dynamics_loss_avg": 0.023146547935903074}
+{"step": 29130, "action_loss_avg": 0.0017071689886506646}
+{"step": 29140, "dynamics_loss_avg": 0.031595134548842906}
+{"step": 29140, "action_loss_avg": 0.0025880463537760077}
+{"step": 29150, "loss": 0.0331, "learning_rate": 8.48857722525823e-05}
+{"step": 29150, "dynamics_loss_avg": 0.03241406446322799}
+{"step": 29150, "action_loss_avg": 0.002899675408843905}
+{"step": 29160, "dynamics_loss_avg": 0.02515326561406255}
+{"step": 29160, "action_loss_avg": 0.001645712897880003}
+{"step": 29170, "dynamics_loss_avg": 0.032608026079833506}
+{"step": 29170, "action_loss_avg": 0.002124056173488498}
+{"step": 29180, "dynamics_loss_avg": 0.02873837510123849}
+{"step": 29180, "action_loss_avg": 0.0027623561676591636}
+{"step": 29190, "dynamics_loss_avg": 0.03578533157706261}
+{"step": 29190, "action_loss_avg": 0.002780863957013935}
+{"step": 29200, "loss": 0.0308, "learning_rate": 8.482649936836491e-05}
+{"step": 29200, "dynamics_loss_avg": 0.03264578636735678}
+{"step": 29200, "action_loss_avg": 0.0032086059160064905}
+{"step": 29210, "dynamics_loss_avg": 0.023420830629765986}
+{"step": 29210, "action_loss_avg": 0.0019868894945830108}
+{"step": 29220, "dynamics_loss_avg": 0.027123206946998834}
+{"step": 29220, "action_loss_avg": 0.002113854675553739}
+{"step": 29230, "dynamics_loss_avg": 0.02763034226372838}
+{"step": 29230, "action_loss_avg": 0.0023558297427371143}
+{"step": 29240, "dynamics_loss_avg": 0.02632018392905593}
+{"step": 29240, "action_loss_avg": 0.0030499786022119223}
+{"step": 29250, "loss": 0.0294, "learning_rate": 8.47671312698281e-05}
+{"step": 29250, "dynamics_loss_avg": 0.036494463589042424}
+{"step": 29250, "action_loss_avg": 0.0030065205704886467}
+{"step": 29260, "dynamics_loss_avg": 0.02570842169225216}
+{"step": 29260, "action_loss_avg": 0.0021532559941988437}
+{"step": 29270, "dynamics_loss_avg": 0.035171343851834534}
+{"step": 29270, "action_loss_avg": 0.0028932967106811702}
+{"step": 29280, "dynamics_loss_avg": 0.034048454090952876}
+{"step": 29280, "action_loss_avg": 0.0033413678756915033}
+{"step": 29290, "dynamics_loss_avg": 0.044559210911393164}
+{"step": 29290, "action_loss_avg": 0.0038981376914307476}
+{"step": 29300, "loss": 0.035, "learning_rate": 8.470766811928197e-05}
+{"step": 29300, "dynamics_loss_avg": 0.02577650835737586}
+{"step": 29300, "action_loss_avg": 0.0018146841030102223}
+{"step": 29310, "dynamics_loss_avg": 0.02544143805280328}
+{"step": 29310, "action_loss_avg": 0.0024469819676596672}
+{"step": 29320, "dynamics_loss_avg": 0.043442736752331255}
+{"step": 29320, "action_loss_avg": 0.0040401510545052585}
+{"step": 29330, "dynamics_loss_avg": 0.036450520530343054}
+{"step": 29330, "action_loss_avg": 0.002972925384528935}
+{"step": 29340, "dynamics_loss_avg": 0.028270881064236163}
+{"step": 29340, "action_loss_avg": 0.0021394506213255225}
+{"step": 29350, "loss": 0.0324, "learning_rate": 8.464811007929651e-05}
+{"step": 29350, "dynamics_loss_avg": 0.02526066149584949}
+{"step": 29350, "action_loss_avg": 0.0022284818202024325}
+{"step": 29360, "dynamics_loss_avg": 0.03180819498375058}
+{"step": 29360, "action_loss_avg": 0.0034155930334236473}
+{"step": 29370, "dynamics_loss_avg": 0.042013864405453204}
+{"step": 29370, "action_loss_avg": 0.004553552478319034}
+{"step": 29380, "dynamics_loss_avg": 0.029842723719775678}
+{"step": 29380, "action_loss_avg": 0.0034288767958059905}
+{"step": 29390, "dynamics_loss_avg": 0.0440694791264832}
+{"step": 29390, "action_loss_avg": 0.004202443384565413}
+{"step": 29400, "loss": 0.0368, "learning_rate": 8.458845731270115e-05}
+{"step": 29400, "dynamics_loss_avg": 0.04403219353407621}
+{"step": 29400, "action_loss_avg": 0.003373378631658852}
+{"step": 29410, "dynamics_loss_avg": 0.037073965463787315}
+{"step": 29410, "action_loss_avg": 0.002987840457353741}
+{"step": 29420, "dynamics_loss_avg": 0.02350242966786027}
+{"step": 29420, "action_loss_avg": 0.0017798996181227268}
+{"step": 29430, "dynamics_loss_avg": 0.027477882616221905}
+{"step": 29430, "action_loss_avg": 0.002130401425529271}
+{"step": 29440, "dynamics_loss_avg": 0.02547989273443818}
+{"step": 29440, "action_loss_avg": 0.0023655314696952702}
+{"step": 29450, "loss": 0.0304, "learning_rate": 8.452870998258423e-05}
+{"step": 29450, "dynamics_loss_avg": 0.023453544080257415}
+{"step": 29450, "action_loss_avg": 0.002436707663582638}
+{"step": 29460, "dynamics_loss_avg": 0.039850285090506074}
+{"step": 29460, "action_loss_avg": 0.00330959134735167}
+{"step": 29470, "dynamics_loss_avg": 0.0366375595331192}
+{"step": 29470, "action_loss_avg": 0.0026445074763614684}
+{"step": 29480, "dynamics_loss_avg": 0.03930307757109404}
+{"step": 29480, "action_loss_avg": 0.002929551457054913}
+{"step": 29490, "dynamics_loss_avg": 0.03032219158485532}
+{"step": 29490, "action_loss_avg": 0.002026485779788345}
+{"step": 29500, "loss": 0.0343, "learning_rate": 8.446886825229271e-05}
+{"step": 29500, "dynamics_loss_avg": 0.030288193468004466}
+{"step": 29500, "action_loss_avg": 0.003049044625367969}
+{"step": 29510, "dynamics_loss_avg": 0.03199481200426817}
+{"step": 29510, "action_loss_avg": 0.0022612711880356075}
+{"step": 29520, "dynamics_loss_avg": 0.026829738914966584}
+{"step": 29520, "action_loss_avg": 0.002179147390415892}
+{"step": 29530, "dynamics_loss_avg": 0.030075947102159262}
+{"step": 29530, "action_loss_avg": 0.002426009179907851}
+{"step": 29540, "dynamics_loss_avg": 0.028916187491267918}
+{"step": 29540, "action_loss_avg": 0.0028095856425352393}
+{"step": 29550, "loss": 0.0285, "learning_rate": 8.440893228543156e-05}
+{"step": 29550, "dynamics_loss_avg": 0.02402097899466753}
+{"step": 29550, "action_loss_avg": 0.0020429061725735663}
+{"step": 29560, "dynamics_loss_avg": 0.03216796820051968}
+{"step": 29560, "action_loss_avg": 0.002521669294219464}
+{"step": 29570, "dynamics_loss_avg": 0.036629500612616536}
+{"step": 29570, "action_loss_avg": 0.00275465160375461}
+{"step": 29580, "dynamics_loss_avg": 0.02620811890810728}
+{"step": 29580, "action_loss_avg": 0.001845999149372801}
+{"step": 29590, "dynamics_loss_avg": 0.03060115100815892}
+{"step": 29590, "action_loss_avg": 0.0028947101964149624}
+{"step": 29600, "loss": 0.0321, "learning_rate": 8.434890224586347e-05}
+{"step": 29600, "dynamics_loss_avg": 0.031711280718445777}
+{"step": 29600, "action_loss_avg": 0.002276693715248257}
+{"step": 29610, "dynamics_loss_avg": 0.03357492778450251}
+{"step": 29610, "action_loss_avg": 0.003141327074263245}
+{"step": 29620, "dynamics_loss_avg": 0.028844835050404073}
+{"step": 29620, "action_loss_avg": 0.001982521783793345}
+{"step": 29630, "dynamics_loss_avg": 0.04088372047990561}
+{"step": 29630, "action_loss_avg": 0.003858016594313085}
+{"step": 29640, "dynamics_loss_avg": 0.03481971994042397}
+{"step": 29640, "action_loss_avg": 0.002221742330584675}
+{"step": 29650, "loss": 0.0322, "learning_rate": 8.428877829770823e-05}
+{"step": 29650, "dynamics_loss_avg": 0.03384239487349987}
+{"step": 29650, "action_loss_avg": 0.003149336454225704}
+{"step": 29660, "dynamics_loss_avg": 0.03585119042545557}
+{"step": 29660, "action_loss_avg": 0.0036695511778816583}
+{"step": 29670, "dynamics_loss_avg": 0.025179911172017455}
+{"step": 29670, "action_loss_avg": 0.0023528584046289326}
+{"step": 29680, "dynamics_loss_avg": 0.0304276617243886}
+{"step": 29680, "action_loss_avg": 0.0024727245909161866}
+{"step": 29690, "dynamics_loss_avg": 0.03389087379910052}
+{"step": 29690, "action_loss_avg": 0.0033700325700920077}
+{"step": 29700, "loss": 0.0318, "learning_rate": 8.422856060534243e-05}
+{"step": 29700, "dynamics_loss_avg": 0.0265543382614851}
+{"step": 29700, "action_loss_avg": 0.003178236854728311}
+{"step": 29710, "dynamics_loss_avg": 0.0295634092297405}
+{"step": 29710, "action_loss_avg": 0.003139674197882414}
+{"step": 29720, "dynamics_loss_avg": 0.03736652107909322}
+{"step": 29720, "action_loss_avg": 0.0030788350908551366}
+{"step": 29730, "dynamics_loss_avg": 0.027919226698577403}
+{"step": 29730, "action_loss_avg": 0.002418258064426482}
+{"step": 29740, "dynamics_loss_avg": 0.03036391707137227}
+{"step": 29740, "action_loss_avg": 0.0035228868713602425}
+{"step": 29750, "loss": 0.0314, "learning_rate": 8.416824933339898e-05}
+{"step": 29750, "dynamics_loss_avg": 0.03131846757605672}
+{"step": 29750, "action_loss_avg": 0.002450533991213888}
+{"step": 29760, "dynamics_loss_avg": 0.031309667974710464}
+{"step": 29760, "action_loss_avg": 0.0033358843822497873}
+{"step": 29770, "dynamics_loss_avg": 0.029798878310248255}
+{"step": 29770, "action_loss_avg": 0.0025928118033334614}
+{"step": 29780, "dynamics_loss_avg": 0.029297336377203463}
+{"step": 29780, "action_loss_avg": 0.0027592767437454313}
+{"step": 29790, "dynamics_loss_avg": 0.03061349056661129}
+{"step": 29790, "action_loss_avg": 0.0024977718479931355}
+{"step": 29800, "loss": 0.0327, "learning_rate": 8.410784464676654e-05}
+{"step": 29800, "dynamics_loss_avg": 0.03650345541536808}
+{"step": 29800, "action_loss_avg": 0.004271968291141093}
+{"step": 29810, "dynamics_loss_avg": 0.029308726266026496}
+{"step": 29810, "action_loss_avg": 0.0027389088761992754}
+{"step": 29820, "dynamics_loss_avg": 0.032968667522072795}
+{"step": 29820, "action_loss_avg": 0.003482001763768494}
+{"step": 29830, "dynamics_loss_avg": 0.032271919026970866}
+{"step": 29830, "action_loss_avg": 0.0038532548234798012}
+{"step": 29840, "dynamics_loss_avg": 0.03414586270228028}
+{"step": 29840, "action_loss_avg": 0.0030725668417289852}
+{"step": 29850, "loss": 0.0333, "learning_rate": 8.404734671058924e-05}
+{"step": 29850, "dynamics_loss_avg": 0.028511388506740332}
+{"step": 29850, "action_loss_avg": 0.002125618897844106}
+{"step": 29860, "dynamics_loss_avg": 0.036382142640650275}
+{"step": 29860, "action_loss_avg": 0.0026472573052160444}
+{"step": 29870, "dynamics_loss_avg": 0.03833909574896097}
+{"step": 29870, "action_loss_avg": 0.004046773590380326}
+{"step": 29880, "dynamics_loss_avg": 0.030483371019363402}
+{"step": 29880, "action_loss_avg": 0.0027533512795343993}
+{"step": 29890, "dynamics_loss_avg": 0.038476706854999064}
+{"step": 29890, "action_loss_avg": 0.003136213112156838}
+{"step": 29900, "loss": 0.036, "learning_rate": 8.398675569026613e-05}
+{"step": 29900, "dynamics_loss_avg": 0.033421683870255944}
+{"step": 29900, "action_loss_avg": 0.0030481638037599622}
+{"step": 29910, "dynamics_loss_avg": 0.03337679216638208}
+{"step": 29910, "action_loss_avg": 0.0035904823336750267}
+{"step": 29920, "dynamics_loss_avg": 0.0345272708684206}
+{"step": 29920, "action_loss_avg": 0.0033576732792425902}
+{"step": 29930, "dynamics_loss_avg": 0.026664153020828963}
+{"step": 29930, "action_loss_avg": 0.0031085422029718756}
+{"step": 29940, "dynamics_loss_avg": 0.03256521746516228}
+{"step": 29940, "action_loss_avg": 0.0034731198800727727}
+{"step": 29950, "loss": 0.0322, "learning_rate": 8.392607175145075e-05}
+{"step": 29950, "dynamics_loss_avg": 0.03593188840895891}
+{"step": 29950, "action_loss_avg": 0.0028243669657967985}
+{"step": 29960, "dynamics_loss_avg": 0.036872221436351535}
+{"step": 29960, "action_loss_avg": 0.0031032514874823392}
+{"step": 29970, "dynamics_loss_avg": 0.028324566129595042}
+{"step": 29970, "action_loss_avg": 0.0022810433350969107}
+{"step": 29980, "dynamics_loss_avg": 0.03454705588519573}
+{"step": 29980, "action_loss_avg": 0.003799303260166198}
+{"step": 29990, "dynamics_loss_avg": 0.03207853185012936}
+{"step": 29990, "action_loss_avg": 0.003617201279848814}
+{"step": 30000, "loss": 0.0332, "learning_rate": 8.386529506005065e-05}
+{"step": 30000, "dynamics_loss_avg": 0.033176838606595996}
+{"step": 30000, "action_loss_avg": 0.002657194048515521}
+{"step": 30010, "dynamics_loss_avg": 0.03604877013713122}
+{"step": 30010, "action_loss_avg": 0.002484902791911736}
+{"step": 30020, "dynamics_loss_avg": 0.027017096197232603}
+{"step": 30020, "action_loss_avg": 0.0024579621851444243}
+{"step": 30030, "dynamics_loss_avg": 0.02911528628319502}
+{"step": 30030, "action_loss_avg": 0.002385661957669072}
+{"step": 30040, "dynamics_loss_avg": 0.04017298836261034}
+{"step": 30040, "action_loss_avg": 0.003077706036856398}
+{"step": 30050, "loss": 0.0333, "learning_rate": 8.380442578222702e-05}
+{"step": 30050, "dynamics_loss_avg": 0.03313823565840721}
+{"step": 30050, "action_loss_avg": 0.0026395682711154223}
+{"step": 30060, "dynamics_loss_avg": 0.0287992469035089}
+{"step": 30060, "action_loss_avg": 0.002621550753246993}
+{"step": 30070, "dynamics_loss_avg": 0.03270786106586456}
+{"step": 30070, "action_loss_avg": 0.0030972790555097163}
+{"step": 30080, "dynamics_loss_avg": 0.03152386443689466}
+{"step": 30080, "action_loss_avg": 0.00235213243868202}
+{"step": 30090, "dynamics_loss_avg": 0.03561150738969445}
+{"step": 30090, "action_loss_avg": 0.003412423946429044}
+{"step": 30100, "loss": 0.0297, "learning_rate": 8.374346408439411e-05}
+{"step": 30100, "dynamics_loss_avg": 0.03938962686806917}
+{"step": 30100, "action_loss_avg": 0.0038073341827839615}
+{"step": 30110, "dynamics_loss_avg": 0.03444668436422944}
+{"step": 30110, "action_loss_avg": 0.00284139437135309}
+{"step": 30120, "dynamics_loss_avg": 0.02859267988242209}
+{"step": 30120, "action_loss_avg": 0.0022143245150800794}
+{"step": 30130, "dynamics_loss_avg": 0.03635554872453213}
+{"step": 30130, "action_loss_avg": 0.0038849151984322815}
+{"step": 30140, "dynamics_loss_avg": 0.030110508017241955}
+{"step": 30140, "action_loss_avg": 0.002789840009063482}
+{"step": 30150, "loss": 0.0309, "learning_rate": 8.36824101332189e-05}
+{"step": 30150, "dynamics_loss_avg": 0.025626847799867392}
+{"step": 30150, "action_loss_avg": 0.0017537818785058334}
+{"step": 30160, "dynamics_loss_avg": 0.03763168295845389}
+{"step": 30160, "action_loss_avg": 0.0029888925957493482}
+{"step": 30170, "dynamics_loss_avg": 0.03323921244591475}
+{"step": 30170, "action_loss_avg": 0.003221106337150559}
+{"step": 30180, "dynamics_loss_avg": 0.03305397890508175}
+{"step": 30180, "action_loss_avg": 0.00324740867363289}
+{"step": 30190, "dynamics_loss_avg": 0.030280649848282336}
+{"step": 30190, "action_loss_avg": 0.0021606065100058915}
+{"step": 30200, "loss": 0.0332, "learning_rate": 8.362126409562053e-05}
+{"step": 30200, "dynamics_loss_avg": 0.032253011036664246}
+{"step": 30200, "action_loss_avg": 0.0025759169773664327}
+{"step": 30210, "dynamics_loss_avg": 0.04024970643222332}
+{"step": 30210, "action_loss_avg": 0.004006726725492626}
+{"step": 30220, "dynamics_loss_avg": 0.029929202608764173}
+{"step": 30220, "action_loss_avg": 0.0030811214179266243}
+{"step": 30230, "dynamics_loss_avg": 0.0385440313257277}
+{"step": 30230, "action_loss_avg": 0.0034342746483162047}
+{"step": 30240, "dynamics_loss_avg": 0.021978492382913828}
+{"step": 30240, "action_loss_avg": 0.0018266725586727262}
+{"step": 30250, "loss": 0.0334, "learning_rate": 8.356002613876993e-05}
+{"step": 30250, "dynamics_loss_avg": 0.029958730284124612}
+{"step": 30250, "action_loss_avg": 0.0029181485064327718}
+{"step": 30260, "dynamics_loss_avg": 0.03681324780918658}
+{"step": 30260, "action_loss_avg": 0.0029828606493538246}
+{"step": 30270, "dynamics_loss_avg": 0.03851518239825964}
+{"step": 30270, "action_loss_avg": 0.004463507045875304}
+{"step": 30280, "dynamics_loss_avg": 0.026762635819613932}
+{"step": 30280, "action_loss_avg": 0.0025254415115341542}
+{"step": 30290, "dynamics_loss_avg": 0.038310122489929196}
+{"step": 30290, "action_loss_avg": 0.002858666458632797}
+{"step": 30300, "loss": 0.0303, "learning_rate": 8.349869643008937e-05}
+{"step": 30300, "dynamics_loss_avg": 0.024298946280032395}
+{"step": 30300, "action_loss_avg": 0.002393285447033122}
+{"step": 30310, "dynamics_loss_avg": 0.024946597591042518}
+{"step": 30310, "action_loss_avg": 0.002800153032876551}
+{"step": 30320, "dynamics_loss_avg": 0.02427226919680834}
+{"step": 30320, "action_loss_avg": 0.0016762209765147419}
+{"step": 30330, "dynamics_loss_avg": 0.03382856547832489}
+{"step": 30330, "action_loss_avg": 0.0035226441046688705}
+{"step": 30340, "dynamics_loss_avg": 0.036498126294463876}
+{"step": 30340, "action_loss_avg": 0.0038212345738429577}
+{"step": 30350, "loss": 0.0325, "learning_rate": 8.343727513725192e-05}
+{"step": 30350, "dynamics_loss_avg": 0.02892755139619112}
+{"step": 30350, "action_loss_avg": 0.0031346395669970663}
+{"step": 30360, "dynamics_loss_avg": 0.030608795955777167}
+{"step": 30360, "action_loss_avg": 0.0025624470203183592}
+{"step": 30370, "dynamics_loss_avg": 0.026782607100903986}
+{"step": 30370, "action_loss_avg": 0.0020618764159735293}
+{"step": 30380, "dynamics_loss_avg": 0.026101840566843747}
+{"step": 30380, "action_loss_avg": 0.0029248652164824305}
+{"step": 30390, "dynamics_loss_avg": 0.027998935617506503}
+{"step": 30390, "action_loss_avg": 0.0025649608694948258}
+{"step": 30400, "loss": 0.0305, "learning_rate": 8.337576242818103e-05}
+{"step": 30400, "dynamics_loss_avg": 0.030764294695109128}
+{"step": 30400, "action_loss_avg": 0.002561639528721571}
+{"step": 30410, "dynamics_loss_avg": 0.030906917527318}
+{"step": 30410, "action_loss_avg": 0.0026353990484494715}
+{"step": 30420, "dynamics_loss_avg": 0.03314994964748621}
+{"step": 30420, "action_loss_avg": 0.0031660653417930006}
+{"step": 30430, "dynamics_loss_avg": 0.030728043243288993}
+{"step": 30430, "action_loss_avg": 0.0025193111214321107}
+{"step": 30440, "dynamics_loss_avg": 0.026187263522297145}
+{"step": 30440, "action_loss_avg": 0.001873435894958675}
+{"step": 30450, "loss": 0.0294, "learning_rate": 8.331415847105013e-05}
+{"step": 30450, "dynamics_loss_avg": 0.025912738917395473}
+{"step": 30450, "action_loss_avg": 0.002449351246468723}
+{"step": 30460, "dynamics_loss_avg": 0.04408320393413305}
+{"step": 30460, "action_loss_avg": 0.0034118956187739967}
+{"step": 30470, "dynamics_loss_avg": 0.029915591049939395}
+{"step": 30470, "action_loss_avg": 0.0022654995147604494}
+{"step": 30480, "dynamics_loss_avg": 0.03412597589194775}
+{"step": 30480, "action_loss_avg": 0.002213820238830522}
+{"step": 30490, "dynamics_loss_avg": 0.03032649327069521}
+{"step": 30490, "action_loss_avg": 0.0026468327967450024}
+{"step": 30500, "loss": 0.0341, "learning_rate": 8.325246343428206e-05}
+{"step": 30500, "dynamics_loss_avg": 0.034113872330635786}
+{"step": 30500, "action_loss_avg": 0.0025323642417788505}
+{"step": 30510, "dynamics_loss_avg": 0.038029975909739736}
+{"step": 30510, "action_loss_avg": 0.003633038664702326}
+{"step": 30520, "dynamics_loss_avg": 0.025927477329969407}
+{"step": 30520, "action_loss_avg": 0.0029926531598903237}
+{"step": 30530, "dynamics_loss_avg": 0.028871117625385523}
+{"step": 30530, "action_loss_avg": 0.002886658924398944}
+{"step": 30540, "dynamics_loss_avg": 0.031814927142113446}
+{"step": 30540, "action_loss_avg": 0.003311757172923535}
+{"step": 30550, "loss": 0.0316, "learning_rate": 8.31906774865487e-05}
+{"step": 30550, "dynamics_loss_avg": 0.026731878379359843}
+{"step": 30550, "action_loss_avg": 0.0023160715820267795}
+{"step": 30560, "dynamics_loss_avg": 0.025959419459104537}
+{"step": 30560, "action_loss_avg": 0.0020893722772598266}
+{"step": 30570, "dynamics_loss_avg": 0.02920510284602642}
+{"step": 30570, "action_loss_avg": 0.0030981982476077975}
+{"step": 30580, "dynamics_loss_avg": 0.02367501799017191}
+{"step": 30580, "action_loss_avg": 0.0018613670952618122}
+{"step": 30590, "dynamics_loss_avg": 0.029025940550491215}
+{"step": 30590, "action_loss_avg": 0.0024794731492875145}
+{"step": 30600, "loss": 0.0292, "learning_rate": 8.312880079677048e-05}
+{"step": 30600, "dynamics_loss_avg": 0.03512045191600919}
+{"step": 30600, "action_loss_avg": 0.002947016281541437}
+{"step": 30610, "dynamics_loss_avg": 0.02960257586091757}
+{"step": 30610, "action_loss_avg": 0.0026723815826699138}
+{"step": 30620, "dynamics_loss_avg": 0.022805622033774852}
+{"step": 30620, "action_loss_avg": 0.0021612136799376456}
+{"step": 30630, "dynamics_loss_avg": 0.023400715831667186}
+{"step": 30630, "action_loss_avg": 0.0017140036448836326}
+{"step": 30640, "dynamics_loss_avg": 0.028973359009251}
+{"step": 30640, "action_loss_avg": 0.0023831362603232266}
+{"step": 30650, "loss": 0.0305, "learning_rate": 8.30668335341159e-05}
+{"step": 30650, "dynamics_loss_avg": 0.03721706122159958}
+{"step": 30650, "action_loss_avg": 0.002740555536001921}
+{"step": 30660, "dynamics_loss_avg": 0.02864184882491827}
+{"step": 30660, "action_loss_avg": 0.0021364345971960574}
+{"step": 30670, "dynamics_loss_avg": 0.02565564075484872}
+{"step": 30670, "action_loss_avg": 0.0024552085378672928}
+{"step": 30680, "dynamics_loss_avg": 0.030653495993465184}
+{"step": 30680, "action_loss_avg": 0.0025874768325593323}
+{"step": 30690, "dynamics_loss_avg": 0.03764133709482849}
+{"step": 30690, "action_loss_avg": 0.004598750162404031}
+{"step": 30700, "loss": 0.0323, "learning_rate": 8.300477586800108e-05}
+{"step": 30700, "dynamics_loss_avg": 0.03447063714265823}
+{"step": 30700, "action_loss_avg": 0.002976661652792245}
+{"step": 30710, "dynamics_loss_avg": 0.029951534792780878}
+{"step": 30710, "action_loss_avg": 0.002796748746186495}
+{"step": 30720, "dynamics_loss_avg": 0.029106034617871045}
+{"step": 30720, "action_loss_avg": 0.0025002280715852978}
+{"step": 30730, "dynamics_loss_avg": 0.03644161056727171}
+{"step": 30730, "action_loss_avg": 0.0034568192902952434}
+{"step": 30740, "dynamics_loss_avg": 0.03400428583845496}
+{"step": 30740, "action_loss_avg": 0.0031321320682764055}
+{"step": 30750, "loss": 0.0348, "learning_rate": 8.294262796808933e-05}
+{"step": 30750, "dynamics_loss_avg": 0.03275288292206824}
+{"step": 30750, "action_loss_avg": 0.0031578132417052983}
+{"step": 30760, "dynamics_loss_avg": 0.03639282863587141}
+{"step": 30760, "action_loss_avg": 0.0032091235858388244}
+{"step": 30770, "dynamics_loss_avg": 0.026683843415230512}
+{"step": 30770, "action_loss_avg": 0.002343635936267674}
+{"step": 30780, "dynamics_loss_avg": 0.03591896500438452}
+{"step": 30780, "action_loss_avg": 0.0030338481068611146}
+{"step": 30790, "dynamics_loss_avg": 0.03831378854811192}
+{"step": 30790, "action_loss_avg": 0.0036148865125142037}
+{"step": 30800, "loss": 0.0345, "learning_rate": 8.288039000429064e-05}
+{"step": 30800, "dynamics_loss_avg": 0.027669331803917886}
+{"step": 30800, "action_loss_avg": 0.0026964034943375735}
+{"step": 30810, "dynamics_loss_avg": 0.025188665837049484}
+{"step": 30810, "action_loss_avg": 0.002198177302489057}
+{"step": 30820, "dynamics_loss_avg": 0.02788785696029663}
+{"step": 30820, "action_loss_avg": 0.0021634984179399906}
+{"step": 30830, "dynamics_loss_avg": 0.04052647212520242}
+{"step": 30830, "action_loss_avg": 0.0035258065327070653}
+{"step": 30840, "dynamics_loss_avg": 0.027150866389274598}
+{"step": 30840, "action_loss_avg": 0.003149939206195995}
+{"step": 30850, "loss": 0.0312, "learning_rate": 8.28180621467612e-05}
+{"step": 30850, "dynamics_loss_avg": 0.0322098926641047}
+{"step": 30850, "action_loss_avg": 0.0034113838308257984}
+{"step": 30860, "dynamics_loss_avg": 0.029549111891537905}
+{"step": 30860, "action_loss_avg": 0.0023468906467314808}
+{"step": 30870, "dynamics_loss_avg": 0.036623390391469}
+{"step": 30870, "action_loss_avg": 0.0031072481186129155}
+{"step": 30880, "dynamics_loss_avg": 0.0297203054651618}
+{"step": 30880, "action_loss_avg": 0.002881692466326058}
+{"step": 30890, "dynamics_loss_avg": 0.028199714422225953}
+{"step": 30890, "action_loss_avg": 0.002324722521007061}
+{"step": 30900, "loss": 0.0324, "learning_rate": 8.2755644565903e-05}
+{"step": 30900, "dynamics_loss_avg": 0.030127375014126302}
+{"step": 30900, "action_loss_avg": 0.0028053061687387526}
+{"step": 30910, "dynamics_loss_avg": 0.03387410854920745}
+{"step": 30910, "action_loss_avg": 0.003949758794624359}
+{"step": 30920, "dynamics_loss_avg": 0.03178745461627841}
+{"step": 30920, "action_loss_avg": 0.0031593918800354006}
+{"step": 30930, "dynamics_loss_avg": 0.02592346635647118}
+{"step": 30930, "action_loss_avg": 0.0024995470710564406}
+{"step": 30940, "dynamics_loss_avg": 0.034454954974353316}
+{"step": 30940, "action_loss_avg": 0.0025623956345953046}
+{"step": 30950, "loss": 0.0323, "learning_rate": 8.269313743236333e-05}
+{"step": 30950, "dynamics_loss_avg": 0.03426036825403571}
+{"step": 30950, "action_loss_avg": 0.0031095391022972763}
+{"step": 30960, "dynamics_loss_avg": 0.032949245721101764}
+{"step": 30960, "action_loss_avg": 0.0025978157995268703}
+{"step": 30970, "dynamics_loss_avg": 0.04070583526045084}
+{"step": 30970, "action_loss_avg": 0.0034682180266827345}
+{"step": 30980, "dynamics_loss_avg": 0.0273868634365499}
+{"step": 30980, "action_loss_avg": 0.0024066293379291894}
+{"step": 30990, "dynamics_loss_avg": 0.033434180356562135}
+{"step": 30990, "action_loss_avg": 0.0027844011143315583}
+{"step": 31000, "loss": 0.0342, "learning_rate": 8.263054091703432e-05}
+{"step": 31000, "dynamics_loss_avg": 0.034505566209554674}
+{"step": 31000, "action_loss_avg": 0.003026891604531556}
+{"step": 31010, "dynamics_loss_avg": 0.03129085740074515}
+{"step": 31010, "action_loss_avg": 0.0023348613525740803}
+{"step": 31020, "dynamics_loss_avg": 0.02987136598676443}
+{"step": 31020, "action_loss_avg": 0.0031206530635245143}
+{"step": 31030, "dynamics_loss_avg": 0.03638592404313386}
+{"step": 31030, "action_loss_avg": 0.00354391603032127}
+{"step": 31040, "dynamics_loss_avg": 0.03110076691955328}
+{"step": 31040, "action_loss_avg": 0.003160216024843976}
+{"step": 31050, "loss": 0.032, "learning_rate": 8.256785519105241e-05}
+{"step": 31050, "dynamics_loss_avg": 0.026380535773932935}
+{"step": 31050, "action_loss_avg": 0.001978998677805066}
+{"step": 31060, "dynamics_loss_avg": 0.031052737776190043}
+{"step": 31060, "action_loss_avg": 0.0024977717665024103}
+{"step": 31070, "dynamics_loss_avg": 0.027998129650950433}
+{"step": 31070, "action_loss_avg": 0.0027326310053467752}
+{"step": 31080, "dynamics_loss_avg": 0.032512796390801665}
+{"step": 31080, "action_loss_avg": 0.003461846977006644}
+{"step": 31090, "dynamics_loss_avg": 0.04446397460997105}
+{"step": 31090, "action_loss_avg": 0.00313548311823979}
+{"step": 31100, "loss": 0.0338, "learning_rate": 8.250508042579803e-05}
+{"step": 31100, "dynamics_loss_avg": 0.049214803893119094}
+{"step": 31100, "action_loss_avg": 0.004655107192229479}
+{"step": 31110, "dynamics_loss_avg": 0.031042485777288676}
+{"step": 31110, "action_loss_avg": 0.0028584479936398567}
+{"step": 31120, "dynamics_loss_avg": 0.032108010817319156}
+{"step": 31120, "action_loss_avg": 0.0027847056626342237}
+{"step": 31130, "dynamics_loss_avg": 0.031997421849519016}
+{"step": 31130, "action_loss_avg": 0.001976319222012535}
+{"step": 31140, "dynamics_loss_avg": 0.033071907423436644}
+{"step": 31140, "action_loss_avg": 0.0020913763903081415}
+{"step": 31150, "loss": 0.032, "learning_rate": 8.244221679289496e-05}
+{"step": 31150, "dynamics_loss_avg": 0.03071024315431714}
+{"step": 31150, "action_loss_avg": 0.002396852627862245}
+{"step": 31160, "dynamics_loss_avg": 0.03458249699324369}
+{"step": 31160, "action_loss_avg": 0.0031138486403506247}
+{"step": 31170, "dynamics_loss_avg": 0.03293024953454733}
+{"step": 31170, "action_loss_avg": 0.002489597914973274}
+{"step": 31180, "dynamics_loss_avg": 0.026710420753806828}
+{"step": 31180, "action_loss_avg": 0.0021276473125908524}
+{"step": 31190, "dynamics_loss_avg": 0.028225256782025098}
+{"step": 31190, "action_loss_avg": 0.0026446462143212557}
+{"step": 31200, "loss": 0.033, "learning_rate": 8.237926446420998e-05}
+{"step": 31200, "dynamics_loss_avg": 0.02294901655986905}
+{"step": 31200, "action_loss_avg": 0.0018096350831910968}
+{"step": 31210, "dynamics_loss_avg": 0.030130827426910402}
+{"step": 31210, "action_loss_avg": 0.0024332092492841185}
+{"step": 31220, "dynamics_loss_avg": 0.033392035588622096}
+{"step": 31220, "action_loss_avg": 0.0029674294695723803}
+{"step": 31230, "dynamics_loss_avg": 0.043548275530338285}
+{"step": 31230, "action_loss_avg": 0.003277836320921779}
+{"step": 31240, "dynamics_loss_avg": 0.03084672773256898}
+{"step": 31240, "action_loss_avg": 0.0026815875433385374}
+{"step": 31250, "loss": 0.035, "learning_rate": 8.231622361185236e-05}
+{"step": 31250, "dynamics_loss_avg": 0.04444014923647046}
+{"step": 31250, "action_loss_avg": 0.003929208777844906}
+{"step": 31260, "dynamics_loss_avg": 0.03315626978874207}
+{"step": 31260, "action_loss_avg": 0.0030994258588179944}
+{"step": 31270, "dynamics_loss_avg": 0.025771098956465722}
+{"step": 31270, "action_loss_avg": 0.0025474990019574762}
+{"step": 31280, "dynamics_loss_avg": 0.031369401095435026}
+{"step": 31280, "action_loss_avg": 0.00330141467275098}
+{"step": 31290, "dynamics_loss_avg": 0.027030931320041418}
+{"step": 31290, "action_loss_avg": 0.0021753427223302423}
+{"step": 31300, "loss": 0.0335, "learning_rate": 8.225309440817336e-05}
+{"step": 31300, "dynamics_loss_avg": 0.02966024409979582}
+{"step": 31300, "action_loss_avg": 0.002929896977730095}
+{"step": 31310, "dynamics_loss_avg": 0.03628241494297981}
+{"step": 31310, "action_loss_avg": 0.0026503565371967853}
+{"step": 31320, "dynamics_loss_avg": 0.02285850830376148}
+{"step": 31320, "action_loss_avg": 0.0024663652351591737}
+{"step": 31330, "dynamics_loss_avg": 0.02428636634722352}
+{"step": 31330, "action_loss_avg": 0.0025430995476199312}
+{"step": 31340, "dynamics_loss_avg": 0.02181997471489012}
+{"step": 31340, "action_loss_avg": 0.001955748500768095}
+{"step": 31350, "loss": 0.0307, "learning_rate": 8.218987702576586e-05}
+{"step": 31350, "dynamics_loss_avg": 0.03513745609670878}
+{"step": 31350, "action_loss_avg": 0.0029740644444245846}
+{"step": 31360, "dynamics_loss_avg": 0.03694860767573118}
+{"step": 31360, "action_loss_avg": 0.0034172380343079566}
+{"step": 31370, "dynamics_loss_avg": 0.03197771161794662}
+{"step": 31370, "action_loss_avg": 0.00320728161605075}
+{"step": 31380, "dynamics_loss_avg": 0.029133780905976892}
+{"step": 31380, "action_loss_avg": 0.002159121847944334}
+{"step": 31390, "dynamics_loss_avg": 0.035217046923935416}
+{"step": 31390, "action_loss_avg": 0.00265208879718557}
+{"step": 31400, "loss": 0.0352, "learning_rate": 8.212657163746373e-05}
+{"step": 31400, "dynamics_loss_avg": 0.0322383277118206}
+{"step": 31400, "action_loss_avg": 0.002778965444304049}
+{"step": 31410, "dynamics_loss_avg": 0.02889797752723098}
+{"step": 31410, "action_loss_avg": 0.002850052952999249}
+{"step": 31420, "dynamics_loss_avg": 0.025465677864849566}
+{"step": 31420, "action_loss_avg": 0.002025180362397805}
+{"step": 31430, "dynamics_loss_avg": 0.03004514565691352}
+{"step": 31430, "action_loss_avg": 0.0024755412217928098}
+{"step": 31440, "dynamics_loss_avg": 0.03313934020698071}
+{"step": 31440, "action_loss_avg": 0.0029108169313985855}
+{"step": 31450, "loss": 0.0322, "learning_rate": 8.206317841634148e-05}
+{"step": 31450, "dynamics_loss_avg": 0.026125122047960758}
+{"step": 31450, "action_loss_avg": 0.0024133984232321383}
+{"step": 31460, "dynamics_loss_avg": 0.037200643215328455}
+{"step": 31460, "action_loss_avg": 0.002561546873766929}
+{"step": 31470, "dynamics_loss_avg": 0.03415782675147057}
+{"step": 31470, "action_loss_avg": 0.0031376917148008944}
+{"step": 31480, "dynamics_loss_avg": 0.03204572144895792}
+{"step": 31480, "action_loss_avg": 0.0024471925920806826}
+{"step": 31490, "dynamics_loss_avg": 0.03062532339245081}
+{"step": 31490, "action_loss_avg": 0.0024401267466600983}
+{"step": 31500, "loss": 0.0325, "learning_rate": 8.199969753571377e-05}
+{"step": 31500, "dynamics_loss_avg": 0.032883243076503275}
+{"step": 31500, "action_loss_avg": 0.003678114915965125}
+{"step": 31510, "dynamics_loss_avg": 0.02677514930255711}
+{"step": 31510, "action_loss_avg": 0.00234139368403703}
+{"step": 31520, "dynamics_loss_avg": 0.042620102688670156}
+{"step": 31520, "action_loss_avg": 0.003741447115316987}
+{"step": 31530, "dynamics_loss_avg": 0.03403779361397028}
+{"step": 31530, "action_loss_avg": 0.0026481693843379618}
+{"step": 31540, "dynamics_loss_avg": 0.03072197735309601}
+{"step": 31540, "action_loss_avg": 0.001974335464183241}
+{"step": 31550, "loss": 0.0355, "learning_rate": 8.193612916913491e-05}
+{"step": 31550, "dynamics_loss_avg": 0.03965762257575989}
+{"step": 31550, "action_loss_avg": 0.003586733911652118}
+{"step": 31560, "dynamics_loss_avg": 0.031211605202406643}
+{"step": 31560, "action_loss_avg": 0.0023962359759025277}
+{"step": 31570, "dynamics_loss_avg": 0.04122648136690259}
+{"step": 31570, "action_loss_avg": 0.003779202955774963}
+{"step": 31580, "dynamics_loss_avg": 0.03729936666786671}
+{"step": 31580, "action_loss_avg": 0.00297296455828473}
+{"step": 31590, "dynamics_loss_avg": 0.030367585923522712}
+{"step": 31590, "action_loss_avg": 0.0022320189862512054}
+{"step": 31600, "loss": 0.0342, "learning_rate": 8.187247349039837e-05}
+{"step": 31600, "dynamics_loss_avg": 0.022477908805012704}
+{"step": 31600, "action_loss_avg": 0.002055607468355447}
+{"step": 31610, "dynamics_loss_avg": 0.03032084070146084}
+{"step": 31610, "action_loss_avg": 0.003474728565197438}
+{"step": 31620, "dynamics_loss_avg": 0.02337341019883752}
+{"step": 31620, "action_loss_avg": 0.0029647475108504294}
+{"step": 31630, "dynamics_loss_avg": 0.02655356382019818}
+{"step": 31630, "action_loss_avg": 0.002684576017782092}
+{"step": 31640, "dynamics_loss_avg": 0.026931034680455924}
+{"step": 31640, "action_loss_avg": 0.0029026530217379333}
+{"step": 31650, "loss": 0.0285, "learning_rate": 8.180873067353636e-05}
+{"step": 31650, "dynamics_loss_avg": 0.02792096259072423}
+{"step": 31650, "action_loss_avg": 0.002683213067939505}
+{"step": 31660, "dynamics_loss_avg": 0.02754207467660308}
+{"step": 31660, "action_loss_avg": 0.003631035692524165}
+{"step": 31670, "dynamics_loss_avg": 0.024578190594911575}
+{"step": 31670, "action_loss_avg": 0.001633872400270775}
+{"step": 31680, "dynamics_loss_avg": 0.03448492158204317}
+{"step": 31680, "action_loss_avg": 0.004385462496429682}
+{"step": 31690, "dynamics_loss_avg": 0.033133004000410436}
+{"step": 31690, "action_loss_avg": 0.003105164837324992}
+{"step": 31700, "loss": 0.0323, "learning_rate": 8.174490089281932e-05}
+{"step": 31700, "dynamics_loss_avg": 0.04546528123319149}
+{"step": 31700, "action_loss_avg": 0.004656374850310385}
+{"step": 31710, "dynamics_loss_avg": 0.03802736308425665}
+{"step": 31710, "action_loss_avg": 0.0030583398649469016}
+{"step": 31720, "dynamics_loss_avg": 0.03292560623958707}
+{"step": 31720, "action_loss_avg": 0.002356928982771933}
+{"step": 31730, "dynamics_loss_avg": 0.031046979129314423}
+{"step": 31730, "action_loss_avg": 0.003065765229985118}
+{"step": 31740, "dynamics_loss_avg": 0.029672485310584307}
+{"step": 31740, "action_loss_avg": 0.002890429028775543}
+{"step": 31750, "loss": 0.0334, "learning_rate": 8.168098432275539e-05}
+{"step": 31750, "dynamics_loss_avg": 0.042332178261131045}
+{"step": 31750, "action_loss_avg": 0.003995590569684282}
+{"step": 31760, "dynamics_loss_avg": 0.02326775868423283}
+{"step": 31760, "action_loss_avg": 0.0020129184966208415}
+{"step": 31770, "dynamics_loss_avg": 0.035559252742677926}
+{"step": 31770, "action_loss_avg": 0.0026371544576250018}
+{"step": 31780, "dynamics_loss_avg": 0.042186318337917326}
+{"step": 31780, "action_loss_avg": 0.0032434002379886804}
+{"step": 31790, "dynamics_loss_avg": 0.03531409250572324}
+{"step": 31790, "action_loss_avg": 0.0035949280485510827}
+{"step": 31800, "loss": 0.033, "learning_rate": 8.161698113809007e-05}
+{"step": 31800, "dynamics_loss_avg": 0.03319436335004866}
+{"step": 31800, "action_loss_avg": 0.002803460118593648}
+{"step": 31810, "dynamics_loss_avg": 0.03857657136395574}
+{"step": 31810, "action_loss_avg": 0.0034991899272426965}
+{"step": 31820, "dynamics_loss_avg": 0.02951522362418473}
+{"step": 31820, "action_loss_avg": 0.0021262257418129594}
+{"step": 31830, "dynamics_loss_avg": 0.03377584312111139}
+{"step": 31830, "action_loss_avg": 0.0030504174064844847}
+{"step": 31840, "dynamics_loss_avg": 0.04049139358103275}
+{"step": 31840, "action_loss_avg": 0.003460114321205765}
+{"step": 31850, "loss": 0.0349, "learning_rate": 8.15528915138056e-05}
+{"step": 31850, "dynamics_loss_avg": 0.03152222288772464}
+{"step": 31850, "action_loss_avg": 0.0028203673980897294}
+{"step": 31860, "dynamics_loss_avg": 0.033650721237063405}
+{"step": 31860, "action_loss_avg": 0.003414977760985494}
+{"step": 31870, "dynamics_loss_avg": 0.031172007508575916}
+{"step": 31870, "action_loss_avg": 0.0030048733693547546}
+{"step": 31880, "dynamics_loss_avg": 0.019968723971396686}
+{"step": 31880, "action_loss_avg": 0.0019552980025764554}
+{"step": 31890, "dynamics_loss_avg": 0.02811430497094989}
+{"step": 31890, "action_loss_avg": 0.0027772667817771435}
+{"step": 31900, "loss": 0.0325, "learning_rate": 8.148871562512058e-05}
+{"step": 31900, "dynamics_loss_avg": 0.03493303488940001}
+{"step": 31900, "action_loss_avg": 0.002563075441867113}
+{"step": 31910, "dynamics_loss_avg": 0.02356083015911281}
+{"step": 31910, "action_loss_avg": 0.0015864240354858338}
+{"step": 31920, "dynamics_loss_avg": 0.03336041420698166}
+{"step": 31920, "action_loss_avg": 0.004087420814903453}
+{"step": 31930, "dynamics_loss_avg": 0.0344644358381629}
+{"step": 31930, "action_loss_avg": 0.0031116155034396796}
+{"step": 31940, "dynamics_loss_avg": 0.030783765390515326}
+{"step": 31940, "action_loss_avg": 0.002665843936847523}
+{"step": 31950, "loss": 0.0327, "learning_rate": 8.142445364748944e-05}
+{"step": 31950, "dynamics_loss_avg": 0.027161906589753926}
+{"step": 31950, "action_loss_avg": 0.0021751376276370137}
+{"step": 31960, "dynamics_loss_avg": 0.040429449267685415}
+{"step": 31960, "action_loss_avg": 0.0035128473624354228}
+{"step": 31970, "dynamics_loss_avg": 0.02887711375951767}
+{"step": 31970, "action_loss_avg": 0.00231261164881289}
+{"step": 31980, "dynamics_loss_avg": 0.02491288122255355}
+{"step": 31980, "action_loss_avg": 0.001681087831093464}
+{"step": 31990, "dynamics_loss_avg": 0.0274332988075912}
+{"step": 31990, "action_loss_avg": 0.002258188754785806}
+{"step": 32000, "loss": 0.0311, "learning_rate": 8.136010575660196e-05}
+{"step": 32000, "dynamics_loss_avg": 0.03164388556033373}
+{"step": 32000, "action_loss_avg": 0.0022630633524386213}
+{"step": 32010, "dynamics_loss_avg": 0.028903061337769032}
+{"step": 32010, "action_loss_avg": 0.00232340187067166}
+{"step": 32020, "dynamics_loss_avg": 0.029003906855359675}
+{"step": 32020, "action_loss_avg": 0.00225441743968986}
+{"step": 32030, "dynamics_loss_avg": 0.03236204907298088}
+{"step": 32030, "action_loss_avg": 0.0026955633249599485}
+{"step": 32040, "dynamics_loss_avg": 0.029262685449793935}
+{"step": 32040, "action_loss_avg": 0.0026318575110053644}
+{"step": 32050, "loss": 0.0326, "learning_rate": 8.129567212838283e-05}
+{"step": 32050, "dynamics_loss_avg": 0.03119055153802037}
+{"step": 32050, "action_loss_avg": 0.00239416848635301}
+{"step": 32060, "dynamics_loss_avg": 0.042877127043902875}
+{"step": 32060, "action_loss_avg": 0.003183448384515941}
+{"step": 32070, "dynamics_loss_avg": 0.03505314802750945}
+{"step": 32070, "action_loss_avg": 0.0031266271369531752}
+{"step": 32080, "dynamics_loss_avg": 0.02837230674922466}
+{"step": 32080, "action_loss_avg": 0.002510290947975591}
+{"step": 32090, "dynamics_loss_avg": 0.027274227514863015}
+{"step": 32090, "action_loss_avg": 0.002719125762814656}
+{"step": 32100, "loss": 0.0346, "learning_rate": 8.123115293899111e-05}
+{"step": 32100, "dynamics_loss_avg": 0.02943662405014038}
+{"step": 32100, "action_loss_avg": 0.002636934712063521}
+{"step": 32110, "dynamics_loss_avg": 0.03372381599619985}
+{"step": 32110, "action_loss_avg": 0.0032250971940811723}
+{"step": 32120, "dynamics_loss_avg": 0.03832639241591096}
+{"step": 32120, "action_loss_avg": 0.004107193916570395}
+{"step": 32130, "dynamics_loss_avg": 0.030860205087810753}
+{"step": 32130, "action_loss_avg": 0.0023650789342354985}
+{"step": 32140, "dynamics_loss_avg": 0.02647285843268037}
+{"step": 32140, "action_loss_avg": 0.0027454897994175554}
+{"step": 32150, "loss": 0.0339, "learning_rate": 8.116654836481982e-05}
+{"step": 32150, "dynamics_loss_avg": 0.025462361797690392}
+{"step": 32150, "action_loss_avg": 0.0026536688586929814}
+{"step": 32160, "dynamics_loss_avg": 0.025194200035184623}
+{"step": 32160, "action_loss_avg": 0.0024904569378122686}
+{"step": 32170, "dynamics_loss_avg": 0.030467237904667856}
+{"step": 32170, "action_loss_avg": 0.0035898547852411867}
+{"step": 32180, "dynamics_loss_avg": 0.03128826916217804}
+{"step": 32180, "action_loss_avg": 0.0032559832092374564}
+{"step": 32190, "dynamics_loss_avg": 0.031752765737473966}
+{"step": 32190, "action_loss_avg": 0.0026785312744323163}
+{"step": 32200, "loss": 0.0323, "learning_rate": 8.110185858249542e-05}
+{"step": 32200, "dynamics_loss_avg": 0.037875903956592086}
+{"step": 32200, "action_loss_avg": 0.003791950433515012}
+{"step": 32210, "dynamics_loss_avg": 0.03538295784965158}
+{"step": 32210, "action_loss_avg": 0.002787860424723476}
+{"step": 32220, "dynamics_loss_avg": 0.040517291985452175}
+{"step": 32220, "action_loss_avg": 0.003950150741729885}
+{"step": 32230, "dynamics_loss_avg": 0.0337571682408452}
+{"step": 32230, "action_loss_avg": 0.0031326688826084138}
+{"step": 32240, "dynamics_loss_avg": 0.035690760053694245}
+{"step": 32240, "action_loss_avg": 0.0030237066268455235}
+{"step": 32250, "loss": 0.0327, "learning_rate": 8.103708376887724e-05}
+{"step": 32250, "dynamics_loss_avg": 0.018992821453139186}
+{"step": 32250, "action_loss_avg": 0.0017760283953975886}
+{"step": 32260, "dynamics_loss_avg": 0.0328630056232214}
+{"step": 32260, "action_loss_avg": 0.0032058016047813}
+{"step": 32270, "dynamics_loss_avg": 0.02370500862598419}
+{"step": 32270, "action_loss_avg": 0.0018853035173378885}
+{"step": 32280, "dynamics_loss_avg": 0.041880720481276515}
+{"step": 32280, "action_loss_avg": 0.0036294137360528113}
+{"step": 32290, "dynamics_loss_avg": 0.040242891293019056}
+{"step": 32290, "action_loss_avg": 0.0038068347494117916}
+{"step": 32300, "loss": 0.033, "learning_rate": 8.09722241010572e-05}
+{"step": 32300, "dynamics_loss_avg": 0.0263908626511693}
+{"step": 32300, "action_loss_avg": 0.001974122307728976}
+{"step": 32310, "dynamics_loss_avg": 0.02690507178194821}
+{"step": 32310, "action_loss_avg": 0.0024287473584990948}
+{"step": 32320, "dynamics_loss_avg": 0.027803600020706653}
+{"step": 32320, "action_loss_avg": 0.0021341929561458526}
+{"step": 32330, "dynamics_loss_avg": 0.025662824092432857}
+{"step": 32330, "action_loss_avg": 0.0018908038560766726}
+{"step": 32340, "dynamics_loss_avg": 0.029579869564622642}
+{"step": 32340, "action_loss_avg": 0.0027574160136282443}
+{"step": 32350, "loss": 0.0317, "learning_rate": 8.090727975635913e-05}
+{"step": 32350, "dynamics_loss_avg": 0.030901107285171748}
+{"step": 32350, "action_loss_avg": 0.0026248373033013195}
+{"step": 32360, "dynamics_loss_avg": 0.03966965712606907}
+{"step": 32360, "action_loss_avg": 0.0036099702469073237}
+{"step": 32370, "dynamics_loss_avg": 0.042614104133099316}
+{"step": 32370, "action_loss_avg": 0.004305473901331425}
+{"step": 32380, "dynamics_loss_avg": 0.03618967570364475}
+{"step": 32380, "action_loss_avg": 0.0028197802661452443}
+{"step": 32390, "dynamics_loss_avg": 0.029288207925856114}
+{"step": 32390, "action_loss_avg": 0.0024194566998630763}
+{"step": 32400, "loss": 0.0344, "learning_rate": 8.084225091233842e-05}
+{"step": 32400, "dynamics_loss_avg": 0.03176699774339795}
+{"step": 32400, "action_loss_avg": 0.002581956679932773}
+{"step": 32410, "dynamics_loss_avg": 0.027197553869336845}
+{"step": 32410, "action_loss_avg": 0.0027391012874431906}
+{"step": 32420, "dynamics_loss_avg": 0.0309133468195796}
+{"step": 32420, "action_loss_avg": 0.00275030171032995}
+{"step": 32430, "dynamics_loss_avg": 0.03160858666524291}
+{"step": 32430, "action_loss_avg": 0.0028879559453343973}
+{"step": 32440, "dynamics_loss_avg": 0.03496049111708999}
+{"step": 32440, "action_loss_avg": 0.0030258365964982658}
+{"step": 32450, "loss": 0.0327, "learning_rate": 8.077713774678139e-05}
+{"step": 32450, "dynamics_loss_avg": 0.02610771991312504}
+{"step": 32450, "action_loss_avg": 0.0022764269029721617}
+{"step": 32460, "dynamics_loss_avg": 0.03143950514495373}
+{"step": 32460, "action_loss_avg": 0.0028105703357141467}
+{"step": 32470, "dynamics_loss_avg": 0.036502350494265555}
+{"step": 32470, "action_loss_avg": 0.0018900095834396779}
+{"step": 32480, "dynamics_loss_avg": 0.03273184197023511}
+{"step": 32480, "action_loss_avg": 0.0033194847172126176}
+{"step": 32490, "dynamics_loss_avg": 0.033112204913049934}
+{"step": 32490, "action_loss_avg": 0.003475337685085833}
+{"step": 32500, "loss": 0.0342, "learning_rate": 8.0711940437705e-05}
+{"step": 32500, "dynamics_loss_avg": 0.030398817174136637}
+{"step": 32500, "action_loss_avg": 0.0026121949427761137}
+{"step": 32510, "dynamics_loss_avg": 0.03442880753427744}
+{"step": 32510, "action_loss_avg": 0.002617948385886848}
+{"step": 32520, "dynamics_loss_avg": 0.030001982301473617}
+{"step": 32520, "action_loss_avg": 0.002506594080477953}
+{"step": 32530, "dynamics_loss_avg": 0.032284037582576273}
+{"step": 32530, "action_loss_avg": 0.0027362003806047142}
+{"step": 32540, "dynamics_loss_avg": 0.021548576839268207}
+{"step": 32540, "action_loss_avg": 0.0017873883189167827}
+{"step": 32550, "loss": 0.0286, "learning_rate": 8.064665916335618e-05}
+{"step": 32550, "dynamics_loss_avg": 0.029499310441315173}
+{"step": 32550, "action_loss_avg": 0.0022809058078564703}
+{"step": 32560, "dynamics_loss_avg": 0.03720894977450371}
+{"step": 32560, "action_loss_avg": 0.002554238447919488}
+{"step": 32570, "dynamics_loss_avg": 0.029944388102740048}
+{"step": 32570, "action_loss_avg": 0.002617476973682642}
+{"step": 32580, "dynamics_loss_avg": 0.03887407081201673}
+{"step": 32580, "action_loss_avg": 0.002608386514475569}
+{"step": 32590, "dynamics_loss_avg": 0.04526380030438304}
+{"step": 32590, "action_loss_avg": 0.0042921117506921295}
+{"step": 32600, "loss": 0.0377, "learning_rate": 8.058129410221146e-05}
+{"step": 32600, "dynamics_loss_avg": 0.030629452690482138}
+{"step": 32600, "action_loss_avg": 0.002725907904095948}
+{"step": 32610, "dynamics_loss_avg": 0.03187286537140608}
+{"step": 32610, "action_loss_avg": 0.0019390707078855486}
+{"step": 32620, "dynamics_loss_avg": 0.029351121839135887}
+{"step": 32620, "action_loss_avg": 0.0024436036765109748}
+{"step": 32630, "dynamics_loss_avg": 0.03157452214509249}
+{"step": 32630, "action_loss_avg": 0.0025212509324774148}
+{"step": 32640, "dynamics_loss_avg": 0.03044371111318469}
+{"step": 32640, "action_loss_avg": 0.003001700900495052}
+{"step": 32650, "loss": 0.0338, "learning_rate": 8.051584543297642e-05}
+{"step": 32650, "dynamics_loss_avg": 0.033145842235535385}
+{"step": 32650, "action_loss_avg": 0.0034590566880069672}
+{"step": 32660, "dynamics_loss_avg": 0.021844942681491376}
+{"step": 32660, "action_loss_avg": 0.001975232776021585}
+{"step": 32670, "dynamics_loss_avg": 0.04207456093281507}
+{"step": 32670, "action_loss_avg": 0.004131067346315831}
+{"step": 32680, "dynamics_loss_avg": 0.02873241645283997}
+{"step": 32680, "action_loss_avg": 0.0023110577603802085}
+{"step": 32690, "dynamics_loss_avg": 0.028088148962706328}
+{"step": 32690, "action_loss_avg": 0.0020712282770546154}
+{"step": 32700, "loss": 0.0331, "learning_rate": 8.045031333458517e-05}
+{"step": 32700, "dynamics_loss_avg": 0.030629123095422983}
+{"step": 32700, "action_loss_avg": 0.002874200316728093}
+{"step": 32710, "dynamics_loss_avg": 0.02200566646642983}
+{"step": 32710, "action_loss_avg": 0.0016393837286159396}
+{"step": 32720, "dynamics_loss_avg": 0.033734801691025496}
+{"step": 32720, "action_loss_avg": 0.0029047442716546358}
+{"step": 32730, "dynamics_loss_avg": 0.02950305715203285}
+{"step": 32730, "action_loss_avg": 0.0034793713595718144}
+{"step": 32740, "dynamics_loss_avg": 0.030964284017682076}
+{"step": 32740, "action_loss_avg": 0.0031087708426639437}
+{"step": 32750, "loss": 0.0288, "learning_rate": 8.038469798620004e-05}
+{"step": 32750, "dynamics_loss_avg": 0.02559325275942683}
+{"step": 32750, "action_loss_avg": 0.0021489682025276125}
+{"step": 32760, "dynamics_loss_avg": 0.026978319697082042}
+{"step": 32760, "action_loss_avg": 0.0028864847030490638}
+{"step": 32770, "dynamics_loss_avg": 0.02628995878621936}
+{"step": 32770, "action_loss_avg": 0.002135730953887105}
+{"step": 32780, "dynamics_loss_avg": 0.027584387641400098}
+{"step": 32780, "action_loss_avg": 0.002118026986136101}
+{"step": 32790, "dynamics_loss_avg": 0.032151312194764615}
+{"step": 32790, "action_loss_avg": 0.003277013753540814}
+{"step": 32800, "loss": 0.0324, "learning_rate": 8.031899956721083e-05}
+{"step": 32800, "dynamics_loss_avg": 0.035778090730309485}
+{"step": 32800, "action_loss_avg": 0.0030893478775396942}
+{"step": 32810, "dynamics_loss_avg": 0.03149431748315692}
+{"step": 32810, "action_loss_avg": 0.002703410584945232}
+{"step": 32820, "dynamics_loss_avg": 0.026530072558671236}
+{"step": 32820, "action_loss_avg": 0.002373132947832346}
+{"step": 32830, "dynamics_loss_avg": 0.028071353770792486}
+{"step": 32830, "action_loss_avg": 0.0016422668937593698}
+{"step": 32840, "dynamics_loss_avg": 0.026020984817296266}
+{"step": 32840, "action_loss_avg": 0.0026299728313460948}
+{"step": 32850, "loss": 0.0298, "learning_rate": 8.025321825723456e-05}
+{"step": 32850, "dynamics_loss_avg": 0.02825851459056139}
+{"step": 32850, "action_loss_avg": 0.0018945383897516876}
+{"step": 32860, "dynamics_loss_avg": 0.028322452493011952}
+{"step": 32860, "action_loss_avg": 0.002576330685405992}
+{"step": 32870, "dynamics_loss_avg": 0.02425011610612273}
+{"step": 32870, "action_loss_avg": 0.0018838875228539109}
+{"step": 32880, "dynamics_loss_avg": 0.03493289249017835}
+{"step": 32880, "action_loss_avg": 0.0029071692377328874}
+{"step": 32890, "dynamics_loss_avg": 0.023589939903467895}
+{"step": 32890, "action_loss_avg": 0.0017838115280028432}
+{"step": 32900, "loss": 0.0276, "learning_rate": 8.018735423611476e-05}
+{"step": 32900, "dynamics_loss_avg": 0.03220532713457942}
+{"step": 32900, "action_loss_avg": 0.002637882228009403}
+{"step": 32910, "dynamics_loss_avg": 0.025345413852483033}
+{"step": 32910, "action_loss_avg": 0.0015196257503703237}
+{"step": 32920, "dynamics_loss_avg": 0.031536571495234964}
+{"step": 32920, "action_loss_avg": 0.0026511557516641915}
+{"step": 32930, "dynamics_loss_avg": 0.03625611793249846}
+{"step": 32930, "action_loss_avg": 0.0031406475813128055}
+{"step": 32940, "dynamics_loss_avg": 0.041133697517216204}
+{"step": 32940, "action_loss_avg": 0.0040998250537086275}
+{"step": 32950, "loss": 0.0343, "learning_rate": 8.01214076839212e-05}
+{"step": 32950, "dynamics_loss_avg": 0.02748612305149436}
+{"step": 32950, "action_loss_avg": 0.002499829715816304}
+{"step": 32960, "dynamics_loss_avg": 0.022808561194688083}
+{"step": 32960, "action_loss_avg": 0.0027013789222110063}
+{"step": 32970, "dynamics_loss_avg": 0.030866124015301467}
+{"step": 32970, "action_loss_avg": 0.0030761984875425697}
+{"step": 32980, "dynamics_loss_avg": 0.027103772573173045}
+{"step": 32980, "action_loss_avg": 0.0022113072278443723}
+{"step": 32990, "dynamics_loss_avg": 0.033864726033061746}
+{"step": 32990, "action_loss_avg": 0.002459360123611987}
+{"step": 33000, "loss": 0.0301, "learning_rate": 8.005537878094921e-05}
+{"step": 33000, "dynamics_loss_avg": 0.03221142399124801}
+{"step": 33000, "action_loss_avg": 0.002616202464560047}
+{"step": 33010, "dynamics_loss_avg": 0.02769247433170676}
+{"step": 33010, "action_loss_avg": 0.0024963323841802774}
+{"step": 33020, "dynamics_loss_avg": 0.028312377631664276}
+{"step": 33020, "action_loss_avg": 0.001994241704232991}
+{"step": 33030, "dynamics_loss_avg": 0.020093945041298866}
+{"step": 33030, "action_loss_avg": 0.0016960383771220222}
+{"step": 33040, "dynamics_loss_avg": 0.03009620662778616}
+{"step": 33040, "action_loss_avg": 0.00229069993365556}
+{"step": 33050, "loss": 0.0308, "learning_rate": 7.998926770771928e-05}
+{"step": 33050, "dynamics_loss_avg": 0.03225976638495922}
+{"step": 33050, "action_loss_avg": 0.0028482715890277175}
+{"step": 33060, "dynamics_loss_avg": 0.03634743117727339}
+{"step": 33060, "action_loss_avg": 0.0025493879977148024}
+{"step": 33070, "dynamics_loss_avg": 0.026623227586969733}
+{"step": 33070, "action_loss_avg": 0.002870893926592544}
+{"step": 33080, "dynamics_loss_avg": 0.030367357656359673}
+{"step": 33080, "action_loss_avg": 0.0021586055052466692}
+{"step": 33090, "dynamics_loss_avg": 0.03090040571987629}
+{"step": 33090, "action_loss_avg": 0.0027055361308157442}
+{"step": 33100, "loss": 0.0334, "learning_rate": 7.992307464497659e-05}
+{"step": 33100, "dynamics_loss_avg": 0.0408809432759881}
+{"step": 33100, "action_loss_avg": 0.0029676193138584495}
+{"step": 33110, "dynamics_loss_avg": 0.03800465716049075}
+{"step": 33110, "action_loss_avg": 0.0031541357515379787}
+{"step": 33120, "dynamics_loss_avg": 0.027485441556200384}
+{"step": 33120, "action_loss_avg": 0.0023158676049206406}
+{"step": 33130, "dynamics_loss_avg": 0.028394925827160477}
+{"step": 33130, "action_loss_avg": 0.002139695722144097}
+{"step": 33140, "dynamics_loss_avg": 0.029751663096249104}
+{"step": 33140, "action_loss_avg": 0.0030135226144921033}
+{"step": 33150, "loss": 0.0325, "learning_rate": 7.985679977369043e-05}
+{"step": 33150, "dynamics_loss_avg": 0.033708554785698654}
+{"step": 33150, "action_loss_avg": 0.003429409590899013}
+{"step": 33160, "dynamics_loss_avg": 0.03521582931280136}
+{"step": 33160, "action_loss_avg": 0.002749927225522697}
+{"step": 33170, "dynamics_loss_avg": 0.0245765577070415}
+{"step": 33170, "action_loss_avg": 0.0019642702187411486}
+{"step": 33180, "dynamics_loss_avg": 0.035417542420327665}
+{"step": 33180, "action_loss_avg": 0.0029345570015721022}
+{"step": 33190, "dynamics_loss_avg": 0.027328671142458915}
+{"step": 33190, "action_loss_avg": 0.0020727224415168165}
+{"step": 33200, "loss": 0.0312, "learning_rate": 7.979044327505375e-05}
+{"step": 33200, "dynamics_loss_avg": 0.033020035829395056}
+{"step": 33200, "action_loss_avg": 0.0032929714187048377}
+{"step": 33210, "dynamics_loss_avg": 0.03678704109042883}
+{"step": 33210, "action_loss_avg": 0.0024743151850998403}
+{"step": 33220, "dynamics_loss_avg": 0.03129847124218941}
+{"step": 33220, "action_loss_avg": 0.0020152853685431182}
+{"step": 33230, "dynamics_loss_avg": 0.032303133700042966}
+{"step": 33230, "action_loss_avg": 0.002447049308102578}
+{"step": 33240, "dynamics_loss_avg": 0.03528701602481306}
+{"step": 33240, "action_loss_avg": 0.0024118188943248243}
+{"step": 33250, "loss": 0.0364, "learning_rate": 7.972400533048273e-05}
+{"step": 33250, "dynamics_loss_avg": 0.03606366468593478}
+{"step": 33250, "action_loss_avg": 0.0030626987863797694}
+{"step": 33260, "dynamics_loss_avg": 0.03876164425164461}
+{"step": 33260, "action_loss_avg": 0.003080614435020834}
+{"step": 33270, "dynamics_loss_avg": 0.02996135102584958}
+{"step": 33270, "action_loss_avg": 0.002793337940238416}
+{"step": 33280, "dynamics_loss_avg": 0.028813512809574605}
+{"step": 33280, "action_loss_avg": 0.002497538144234568}
+{"step": 33290, "dynamics_loss_avg": 0.03268155921250582}
+{"step": 33290, "action_loss_avg": 0.002842386136762798}
+{"step": 33300, "loss": 0.0328, "learning_rate": 7.965748612161612e-05}
+{"step": 33300, "dynamics_loss_avg": 0.034197410196065904}
+{"step": 33300, "action_loss_avg": 0.002883403527084738}
+{"step": 33310, "dynamics_loss_avg": 0.03693171255290508}
+{"step": 33310, "action_loss_avg": 0.0033752414223272354}
+{"step": 33320, "dynamics_loss_avg": 0.046186409704387185}
+{"step": 33320, "action_loss_avg": 0.0033255946589633824}
+{"step": 33330, "dynamics_loss_avg": 0.04319369830191135}
+{"step": 33330, "action_loss_avg": 0.0037795304611790924}
+{"step": 33340, "dynamics_loss_avg": 0.03886458929628134}
+{"step": 33340, "action_loss_avg": 0.0037505543092265724}
+{"step": 33350, "loss": 0.0362, "learning_rate": 7.959088583031496e-05}
+{"step": 33350, "dynamics_loss_avg": 0.02772444477304816}
+{"step": 33350, "action_loss_avg": 0.0020080895454157146}
+{"step": 33360, "dynamics_loss_avg": 0.03987550511956215}
+{"step": 33360, "action_loss_avg": 0.0026736155850812793}
+{"step": 33370, "dynamics_loss_avg": 0.029932540375739336}
+{"step": 33370, "action_loss_avg": 0.002391270874068141}
+{"step": 33380, "dynamics_loss_avg": 0.05639131143689156}
+{"step": 33380, "action_loss_avg": 0.004343106597661972}
+{"step": 33390, "dynamics_loss_avg": 0.029374864348210395}
+{"step": 33390, "action_loss_avg": 0.0033391507691703736}
+{"step": 33400, "loss": 0.0373, "learning_rate": 7.952420463866182e-05}
+{"step": 33400, "dynamics_loss_avg": 0.03383659878745675}
+{"step": 33400, "action_loss_avg": 0.003036451735533774}
+{"step": 33410, "dynamics_loss_avg": 0.04025288978591561}
+{"step": 33410, "action_loss_avg": 0.0033962308429181577}
+{"step": 33420, "dynamics_loss_avg": 0.03071399489417672}
+{"step": 33420, "action_loss_avg": 0.002947856846731156}
+{"step": 33430, "dynamics_loss_avg": 0.029600953590124844}
+{"step": 33430, "action_loss_avg": 0.0022388593526557086}
+{"step": 33440, "dynamics_loss_avg": 0.03825497217476368}
+{"step": 33440, "action_loss_avg": 0.002585219225147739}
+{"step": 33450, "loss": 0.0355, "learning_rate": 7.94574427289606e-05}
+{"step": 33450, "dynamics_loss_avg": 0.02459589745849371}
+{"step": 33450, "action_loss_avg": 0.0021247822791337968}
+{"step": 33460, "dynamics_loss_avg": 0.02939908392727375}
+{"step": 33460, "action_loss_avg": 0.002176170836901292}
+{"step": 33470, "dynamics_loss_avg": 0.03148835375905037}
+{"step": 33470, "action_loss_avg": 0.0022182740562129767}
+{"step": 33480, "dynamics_loss_avg": 0.028552085207775236}
+{"step": 33480, "action_loss_avg": 0.0022603190504014493}
+{"step": 33490, "dynamics_loss_avg": 0.03626901963725686}
+{"step": 33490, "action_loss_avg": 0.00276924860663712}
+{"step": 33500, "loss": 0.0316, "learning_rate": 7.939060028373577e-05}
+{"step": 33500, "dynamics_loss_avg": 0.02633758997544646}
+{"step": 33500, "action_loss_avg": 0.002254428219748661}
+{"step": 33510, "dynamics_loss_avg": 0.02866154662333429}
+{"step": 33510, "action_loss_avg": 0.0022352012572810056}
+{"step": 33520, "dynamics_loss_avg": 0.037642224691808224}
+{"step": 33520, "action_loss_avg": 0.0033283991389907895}
+{"step": 33530, "dynamics_loss_avg": 0.029811675287783147}
+{"step": 33530, "action_loss_avg": 0.002396851789671928}
+{"step": 33540, "dynamics_loss_avg": 0.03148156423121691}
+{"step": 33540, "action_loss_avg": 0.0022598396171815693}
+{"step": 33550, "loss": 0.0328, "learning_rate": 7.932367748573206e-05}
+{"step": 33550, "dynamics_loss_avg": 0.03639452587813139}
+{"step": 33550, "action_loss_avg": 0.0029757503303699195}
+{"step": 33560, "dynamics_loss_avg": 0.02425919957458973}
+{"step": 33560, "action_loss_avg": 0.002654027083190158}
+{"step": 33570, "dynamics_loss_avg": 0.024945790600031614}
+{"step": 33570, "action_loss_avg": 0.0016218846954870968}
+{"step": 33580, "dynamics_loss_avg": 0.02915372308343649}
+{"step": 33580, "action_loss_avg": 0.002642568800365552}
+{"step": 33590, "dynamics_loss_avg": 0.031029887776821852}
+{"step": 33590, "action_loss_avg": 0.0027328081836458296}
+{"step": 33600, "loss": 0.031, "learning_rate": 7.925667451791383e-05}
+{"step": 33600, "dynamics_loss_avg": 0.030877910275012254}
+{"step": 33600, "action_loss_avg": 0.0027832257095724345}
+{"step": 33610, "dynamics_loss_avg": 0.025879039987921716}
+{"step": 33610, "action_loss_avg": 0.002499283361248672}
+{"step": 33620, "dynamics_loss_avg": 0.04145521847531199}
+{"step": 33620, "action_loss_avg": 0.0038908652612008156}
+{"step": 33630, "dynamics_loss_avg": 0.03430120823904872}
+{"step": 33630, "action_loss_avg": 0.0034156398731283845}
+{"step": 33640, "dynamics_loss_avg": 0.039590155426412824}
+{"step": 33640, "action_loss_avg": 0.0033520431024953723}
+{"step": 33650, "loss": 0.0344, "learning_rate": 7.918959156346461e-05}
+{"step": 33650, "dynamics_loss_avg": 0.028685067035257816}
+{"step": 33650, "action_loss_avg": 0.0017086688545532524}
+{"step": 33660, "dynamics_loss_avg": 0.019495900673791765}
+{"step": 33660, "action_loss_avg": 0.0015057446784339846}
+{"step": 33670, "dynamics_loss_avg": 0.03619605286512524}
+{"step": 33670, "action_loss_avg": 0.0027771095497882924}
+{"step": 33680, "dynamics_loss_avg": 0.030212399922311305}
+{"step": 33680, "action_loss_avg": 0.0029328936187084766}
+{"step": 33690, "dynamics_loss_avg": 0.03078682404011488}
+{"step": 33690, "action_loss_avg": 0.002533474937081337}
+{"step": 33700, "loss": 0.0313, "learning_rate": 7.912242880578667e-05}
+{"step": 33700, "dynamics_loss_avg": 0.03197374120354653}
+{"step": 33700, "action_loss_avg": 0.0022594874317292124}
+{"step": 33710, "dynamics_loss_avg": 0.034397026989609}
+{"step": 33710, "action_loss_avg": 0.002284647454507649}
+{"step": 33720, "dynamics_loss_avg": 0.029239577241241932}
+{"step": 33720, "action_loss_avg": 0.002385232539381832}
+{"step": 33730, "dynamics_loss_avg": 0.030338507890701295}
+{"step": 33730, "action_loss_avg": 0.002726027852622792}
+{"step": 33740, "dynamics_loss_avg": 0.036004639323800804}
+{"step": 33740, "action_loss_avg": 0.003007016686024144}
+{"step": 33750, "loss": 0.0328, "learning_rate": 7.905518642850041e-05}
+{"step": 33750, "dynamics_loss_avg": 0.036802982352674006}
+{"step": 33750, "action_loss_avg": 0.002775755972834304}
+{"step": 33760, "dynamics_loss_avg": 0.043626597803086045}
+{"step": 33760, "action_loss_avg": 0.0039752050186507406}
+{"step": 33770, "dynamics_loss_avg": 0.026592161785811187}
+{"step": 33770, "action_loss_avg": 0.0023895851569250225}
+{"step": 33780, "dynamics_loss_avg": 0.039833962451666594}
+{"step": 33780, "action_loss_avg": 0.0032239022082649173}
+{"step": 33790, "dynamics_loss_avg": 0.02932589128613472}
+{"step": 33790, "action_loss_avg": 0.003167216037400067}
+{"step": 33800, "loss": 0.0357, "learning_rate": 7.898786461544395e-05}
+{"step": 33800, "dynamics_loss_avg": 0.04243094557896256}
+{"step": 33800, "action_loss_avg": 0.0034504573966842146}
+{"step": 33810, "dynamics_loss_avg": 0.02946758149191737}
+{"step": 33810, "action_loss_avg": 0.0020258317003026606}
+{"step": 33820, "dynamics_loss_avg": 0.03232139321044088}
+{"step": 33820, "action_loss_avg": 0.00291790664778091}
+{"step": 33830, "dynamics_loss_avg": 0.027004652097821234}
+{"step": 33830, "action_loss_avg": 0.0025164047081489118}
+{"step": 33840, "dynamics_loss_avg": 0.028495862521231173}
+{"step": 33840, "action_loss_avg": 0.0028821097686886786}
+{"step": 33850, "loss": 0.0315, "learning_rate": 7.892046355067248e-05}
+{"step": 33850, "dynamics_loss_avg": 0.031123596336692573}
+{"step": 33850, "action_loss_avg": 0.002406442124629393}
+{"step": 33860, "dynamics_loss_avg": 0.030368136800825597}
+{"step": 33860, "action_loss_avg": 0.0025759345153346658}
+{"step": 33870, "dynamics_loss_avg": 0.024575792578980328}
+{"step": 33870, "action_loss_avg": 0.0014978609600802884}
+{"step": 33880, "dynamics_loss_avg": 0.03673504665493965}
+{"step": 33880, "action_loss_avg": 0.003084196610143408}
+{"step": 33890, "dynamics_loss_avg": 0.03654187703505159}
+{"step": 33890, "action_loss_avg": 0.00309751377790235}
+{"step": 33900, "loss": 0.032, "learning_rate": 7.885298341845802e-05}
+{"step": 33900, "dynamics_loss_avg": 0.026685892138630152}
+{"step": 33900, "action_loss_avg": 0.001673056255094707}
+{"step": 33910, "dynamics_loss_avg": 0.036167599819600584}
+{"step": 33910, "action_loss_avg": 0.0028454344894271342}
+{"step": 33920, "dynamics_loss_avg": 0.03341274717822671}
+{"step": 33920, "action_loss_avg": 0.00274399071931839}
+{"step": 33930, "dynamics_loss_avg": 0.032810600753873584}
+{"step": 33930, "action_loss_avg": 0.0022544988372828812}
+{"step": 33940, "dynamics_loss_avg": 0.02897641072049737}
+{"step": 33940, "action_loss_avg": 0.001961305987788364}
+{"step": 33950, "loss": 0.0334, "learning_rate": 7.878542440328865e-05}
+{"step": 33950, "dynamics_loss_avg": 0.03379447795450687}
+{"step": 33950, "action_loss_avg": 0.002883941074833274}
+{"step": 33960, "dynamics_loss_avg": 0.030778982071205975}
+{"step": 33960, "action_loss_avg": 0.002084595404448919}
+{"step": 33970, "dynamics_loss_avg": 0.03782866783440113}
+{"step": 33970, "action_loss_avg": 0.0034445005003362894}
+{"step": 33980, "dynamics_loss_avg": 0.042165550962090494}
+{"step": 33980, "action_loss_avg": 0.003965582756791264}
+{"step": 33990, "dynamics_loss_avg": 0.03280529845505953}
+{"step": 33990, "action_loss_avg": 0.0024885025632102042}
+{"step": 34000, "loss": 0.037, "learning_rate": 7.87177866898681e-05}
+{"step": 34000, "dynamics_loss_avg": 0.035256782360374925}
+{"step": 34000, "action_loss_avg": 0.0026867301901802422}
+{"step": 34010, "dynamics_loss_avg": 0.0425518904812634}
+{"step": 34010, "action_loss_avg": 0.0032930315122939647}
+{"step": 34020, "dynamics_loss_avg": 0.02905542217195034}
+{"step": 34020, "action_loss_avg": 0.002382040928932838}
+{"step": 34030, "dynamics_loss_avg": 0.03149273386225104}
+{"step": 34030, "action_loss_avg": 0.0034002120606601237}
+{"step": 34040, "dynamics_loss_avg": 0.029674272611737253}
+{"step": 34040, "action_loss_avg": 0.0021646800683811306}
+{"step": 34050, "loss": 0.0339, "learning_rate": 7.865007046311534e-05}
+{"step": 34050, "dynamics_loss_avg": 0.033016433380544184}
+{"step": 34050, "action_loss_avg": 0.003392912441631779}
+{"step": 34060, "dynamics_loss_avg": 0.027038353309035302}
+{"step": 34060, "action_loss_avg": 0.002039398835040629}
+{"step": 34070, "dynamics_loss_avg": 0.043074766732752325}
+{"step": 34070, "action_loss_avg": 0.0032757504377514124}
+{"step": 34080, "dynamics_loss_avg": 0.03522047707810998}
+{"step": 34080, "action_loss_avg": 0.0026262426923494785}
+{"step": 34090, "dynamics_loss_avg": 0.026254460914060473}
+{"step": 34090, "action_loss_avg": 0.0021705965889850633}
+{"step": 34100, "loss": 0.0326, "learning_rate": 7.858227590816394e-05}
+{"step": 34100, "dynamics_loss_avg": 0.030960708390921354}
+{"step": 34100, "action_loss_avg": 0.0024282177531858907}
+{"step": 34110, "dynamics_loss_avg": 0.02678944612853229}
+{"step": 34110, "action_loss_avg": 0.0033148004906252025}
+{"step": 34120, "dynamics_loss_avg": 0.028866614494472743}
+{"step": 34120, "action_loss_avg": 0.002439316379604861}
+{"step": 34130, "dynamics_loss_avg": 0.03739287640200928}
+{"step": 34130, "action_loss_avg": 0.002850849906099029}
+{"step": 34140, "dynamics_loss_avg": 0.03128537591546774}
+{"step": 34140, "action_loss_avg": 0.0024679165333509447}
+{"step": 34150, "loss": 0.0315, "learning_rate": 7.851440321036161e-05}
+{"step": 34150, "dynamics_loss_avg": 0.03144082967191934}
+{"step": 34150, "action_loss_avg": 0.0028260106104426087}
+{"step": 34160, "dynamics_loss_avg": 0.0386650534812361}
+{"step": 34160, "action_loss_avg": 0.0033440494153182954}
+{"step": 34170, "dynamics_loss_avg": 0.026413022726774215}
+{"step": 34170, "action_loss_avg": 0.002492584189167246}
+{"step": 34180, "dynamics_loss_avg": 0.030045242328196765}
+{"step": 34180, "action_loss_avg": 0.0027305519906803966}
+{"step": 34190, "dynamics_loss_avg": 0.034763958863914014}
+{"step": 34190, "action_loss_avg": 0.0020701868226751683}
+{"step": 34200, "loss": 0.0339, "learning_rate": 7.844645255526972e-05}
+{"step": 34200, "dynamics_loss_avg": 0.033991345949470994}
+{"step": 34200, "action_loss_avg": 0.00233344939770177}
+{"step": 34210, "dynamics_loss_avg": 0.0354114512912929}
+{"step": 34210, "action_loss_avg": 0.002442611998412758}
+{"step": 34220, "dynamics_loss_avg": 0.022564811632037163}
+{"step": 34220, "action_loss_avg": 0.0018798871838953345}
+{"step": 34230, "dynamics_loss_avg": 0.03781815990805626}
+{"step": 34230, "action_loss_avg": 0.002768926974385977}
+{"step": 34240, "dynamics_loss_avg": 0.02091782451607287}
+{"step": 34240, "action_loss_avg": 0.0022443648776970804}
+{"step": 34250, "loss": 0.0305, "learning_rate": 7.837842412866279e-05}
+{"step": 34250, "dynamics_loss_avg": 0.03190821893513203}
+{"step": 34250, "action_loss_avg": 0.0033304001088254155}
+{"step": 34260, "dynamics_loss_avg": 0.02114991983398795}
+{"step": 34260, "action_loss_avg": 0.002674856665544212}
+{"step": 34270, "dynamics_loss_avg": 0.028303916845470668}
+{"step": 34270, "action_loss_avg": 0.0036674133618362246}
+{"step": 34280, "dynamics_loss_avg": 0.02652808390557766}
+{"step": 34280, "action_loss_avg": 0.0026746839983388783}
+{"step": 34290, "dynamics_loss_avg": 0.03752558948472142}
+{"step": 34290, "action_loss_avg": 0.002736803493462503}
+{"step": 34300, "loss": 0.0319, "learning_rate": 7.83103181165279e-05}
+{"step": 34300, "dynamics_loss_avg": 0.03509928490966559}
+{"step": 34300, "action_loss_avg": 0.003613394795684144}
+{"step": 34310, "dynamics_loss_avg": 0.03507245145738125}
+{"step": 34310, "action_loss_avg": 0.0031306375283747913}
+{"step": 34320, "dynamics_loss_avg": 0.0385861330665648}
+{"step": 34320, "action_loss_avg": 0.0038267203082796184}
+{"step": 34330, "dynamics_loss_avg": 0.03807531241327524}
+{"step": 34330, "action_loss_avg": 0.003138006234075874}
+{"step": 34340, "dynamics_loss_avg": 0.03558211624622345}
+{"step": 34340, "action_loss_avg": 0.002646421059034765}
+{"step": 34350, "loss": 0.035, "learning_rate": 7.824213470506431e-05}
+{"step": 34350, "dynamics_loss_avg": 0.035153822414577006}
+{"step": 34350, "action_loss_avg": 0.002495022868970409}
+{"step": 34360, "dynamics_loss_avg": 0.028640209510922433}
+{"step": 34360, "action_loss_avg": 0.0024596444563940167}
+{"step": 34370, "dynamics_loss_avg": 0.03317359164357185}
+{"step": 34370, "action_loss_avg": 0.003058119269553572}
+{"step": 34380, "dynamics_loss_avg": 0.0349202080629766}
+{"step": 34380, "action_loss_avg": 0.0028845132066635413}
+{"step": 34390, "dynamics_loss_avg": 0.030304643884301187}
+{"step": 34390, "action_loss_avg": 0.0031033993349410594}
+{"step": 34400, "loss": 0.0319, "learning_rate": 7.817387408068286e-05}
+{"step": 34400, "dynamics_loss_avg": 0.03132227286696434}
+{"step": 34400, "action_loss_avg": 0.0022681520320475103}
+{"step": 34410, "dynamics_loss_avg": 0.03271692916750908}
+{"step": 34410, "action_loss_avg": 0.0031154138618148864}
+{"step": 34420, "dynamics_loss_avg": 0.036924950405955316}
+{"step": 34420, "action_loss_avg": 0.0028157335007563235}
+{"step": 34430, "dynamics_loss_avg": 0.033041187934577464}
+{"step": 34430, "action_loss_avg": 0.002396190055878833}
+{"step": 34440, "dynamics_loss_avg": 0.026550992392003536}
+{"step": 34440, "action_loss_avg": 0.00216281833127141}
+{"step": 34450, "loss": 0.0311, "learning_rate": 7.810553643000549e-05}
+{"step": 34450, "dynamics_loss_avg": 0.025260608829557895}
+{"step": 34450, "action_loss_avg": 0.0021779978298582135}
+{"step": 34460, "dynamics_loss_avg": 0.030575397331267594}
+{"step": 34460, "action_loss_avg": 0.002369402121985331}
+{"step": 34470, "dynamics_loss_avg": 0.028459926880896092}
+{"step": 34470, "action_loss_avg": 0.0024643998476676643}
+{"step": 34480, "dynamics_loss_avg": 0.030987773928791283}
+{"step": 34480, "action_loss_avg": 0.0021233586070593447}
+{"step": 34490, "dynamics_loss_avg": 0.024184632953256367}
+{"step": 34490, "action_loss_avg": 0.0021985028753988443}
+{"step": 34500, "loss": 0.0308, "learning_rate": 7.803712193986474e-05}
+{"step": 34500, "dynamics_loss_avg": 0.03324744682759047}
+{"step": 34500, "action_loss_avg": 0.0022362326795700937}
+{"step": 34510, "dynamics_loss_avg": 0.030693626310676337}
+{"step": 34510, "action_loss_avg": 0.002047643726109527}
+{"step": 34520, "dynamics_loss_avg": 0.030843581445515154}
+{"step": 34520, "action_loss_avg": 0.0024262277700472625}
+{"step": 34530, "dynamics_loss_avg": 0.030335794761776926}
+{"step": 34530, "action_loss_avg": 0.0025339695159345864}
+{"step": 34540, "dynamics_loss_avg": 0.03255822043865919}
+{"step": 34540, "action_loss_avg": 0.0027148916095029564}
+{"step": 34550, "loss": 0.0322, "learning_rate": 7.796863079730318e-05}
+{"step": 34550, "dynamics_loss_avg": 0.03992924191989004}
+{"step": 34550, "action_loss_avg": 0.0029071446508169172}
+{"step": 34560, "dynamics_loss_avg": 0.03409637939184904}
+{"step": 34560, "action_loss_avg": 0.002819887429359369}
+{"step": 34570, "dynamics_loss_avg": 0.025623927172273398}
+{"step": 34570, "action_loss_avg": 0.0019246039330027998}
+{"step": 34580, "dynamics_loss_avg": 0.033486375492066144}
+{"step": 34580, "action_loss_avg": 0.002648636273806915}
+{"step": 34590, "dynamics_loss_avg": 0.030749334464780988}
+{"step": 34590, "action_loss_avg": 0.002350409526843578}
+{"step": 34600, "loss": 0.0332, "learning_rate": 7.790006318957301e-05}
+{"step": 34600, "dynamics_loss_avg": 0.02714499281719327}
+{"step": 34600, "action_loss_avg": 0.002773658069781959}
+{"step": 34610, "dynamics_loss_avg": 0.03499442040920257}
+{"step": 34610, "action_loss_avg": 0.004401180910645053}
+{"step": 34620, "dynamics_loss_avg": 0.03138017812743783}
+{"step": 34620, "action_loss_avg": 0.0028122277348302306}
+{"step": 34630, "dynamics_loss_avg": 0.03912156280130148}
+{"step": 34630, "action_loss_avg": 0.003700246918015182}
+{"step": 34640, "dynamics_loss_avg": 0.022937924903817474}
+{"step": 34640, "action_loss_avg": 0.0015871717187110335}
+{"step": 34650, "loss": 0.0332, "learning_rate": 7.783141930413545e-05}
+{"step": 34650, "dynamics_loss_avg": 0.034347177017480135}
+{"step": 34650, "action_loss_avg": 0.002717446576571092}
+{"step": 34660, "dynamics_loss_avg": 0.03132784320041537}
+{"step": 34660, "action_loss_avg": 0.002353502856567502}
+{"step": 34670, "dynamics_loss_avg": 0.031835080776363614}
+{"step": 34670, "action_loss_avg": 0.003745369834359735}
+{"step": 34680, "dynamics_loss_avg": 0.03126983046531677}
+{"step": 34680, "action_loss_avg": 0.002717508948990144}
+{"step": 34690, "dynamics_loss_avg": 0.03321332409977913}
+{"step": 34690, "action_loss_avg": 0.003174525871872902}
+{"step": 34700, "loss": 0.0319, "learning_rate": 7.776269932866023e-05}
+{"step": 34700, "dynamics_loss_avg": 0.02822131523862481}
+{"step": 34700, "action_loss_avg": 0.0021672042668797074}
+{"step": 34710, "dynamics_loss_avg": 0.039882400445640086}
+{"step": 34710, "action_loss_avg": 0.003910027025267482}
+{"step": 34720, "dynamics_loss_avg": 0.033745548222213984}
+{"step": 34720, "action_loss_avg": 0.0025638761871960014}
+{"step": 34730, "dynamics_loss_avg": 0.03724194904789328}
+{"step": 34730, "action_loss_avg": 0.003188061909168027}
+{"step": 34740, "dynamics_loss_avg": 0.029937869403511286}
+{"step": 34740, "action_loss_avg": 0.003746834985213354}
+{"step": 34750, "loss": 0.0349, "learning_rate": 7.769390345102518e-05}
+{"step": 34750, "dynamics_loss_avg": 0.03599500320851803}
+{"step": 34750, "action_loss_avg": 0.0024374558590352534}
+{"step": 34760, "dynamics_loss_avg": 0.03130788747221232}
+{"step": 34760, "action_loss_avg": 0.0022464209294412287}
+{"step": 34770, "dynamics_loss_avg": 0.041410839557647704}
+{"step": 34770, "action_loss_avg": 0.004146717512048781}
+{"step": 34780, "dynamics_loss_avg": 0.030703391879796982}
+{"step": 34780, "action_loss_avg": 0.002591337967896834}
+{"step": 34790, "dynamics_loss_avg": 0.026958018075674772}
+{"step": 34790, "action_loss_avg": 0.002642784849740565}
+{"step": 34800, "loss": 0.0328, "learning_rate": 7.762503185931558e-05}
+{"step": 34800, "dynamics_loss_avg": 0.027449477976188064}
+{"step": 34800, "action_loss_avg": 0.0020857229697867296}
+{"step": 34810, "dynamics_loss_avg": 0.03706049229949713}
+{"step": 34810, "action_loss_avg": 0.003908117534592748}
+{"step": 34820, "dynamics_loss_avg": 0.027012807549908757}
+{"step": 34820, "action_loss_avg": 0.0025052085053175687}
+{"step": 34830, "dynamics_loss_avg": 0.029931270238012075}
+{"step": 34830, "action_loss_avg": 0.0028181963571114466}
+{"step": 34840, "dynamics_loss_avg": 0.024916324857622386}
+{"step": 34840, "action_loss_avg": 0.002155815955484286}
+{"step": 34850, "loss": 0.0305, "learning_rate": 7.755608474182372e-05}
+{"step": 34850, "dynamics_loss_avg": 0.02857080101966858}
+{"step": 34850, "action_loss_avg": 0.002736144381924532}
+{"step": 34860, "dynamics_loss_avg": 0.032792705856263635}
+{"step": 34860, "action_loss_avg": 0.0033819316711742433}
+{"step": 34870, "dynamics_loss_avg": 0.03406624337658286}
+{"step": 34870, "action_loss_avg": 0.003462183091323823}
+{"step": 34880, "dynamics_loss_avg": 0.02722740629687905}
+{"step": 34880, "action_loss_avg": 0.0022061665658839047}
+{"step": 34890, "dynamics_loss_avg": 0.02871251795440912}
+{"step": 34890, "action_loss_avg": 0.002241948252776638}
+{"step": 34900, "loss": 0.0314, "learning_rate": 7.748706228704843e-05}
+{"step": 34900, "dynamics_loss_avg": 0.029352721106261016}
+{"step": 34900, "action_loss_avg": 0.002163237822242081}
+{"step": 34910, "dynamics_loss_avg": 0.03408259619027376}
+{"step": 34910, "action_loss_avg": 0.0024931280058808625}
+{"step": 34920, "dynamics_loss_avg": 0.03406536048278212}
+{"step": 34920, "action_loss_avg": 0.0028536923113279045}
+{"step": 34930, "dynamics_loss_avg": 0.034515938349068166}
+{"step": 34930, "action_loss_avg": 0.003177049069199711}
+{"step": 34940, "dynamics_loss_avg": 0.030939034791663288}
+{"step": 34940, "action_loss_avg": 0.001834249950479716}
+{"step": 34950, "loss": 0.0335, "learning_rate": 7.741796468369443e-05}
+{"step": 34950, "dynamics_loss_avg": 0.02815556973218918}
+{"step": 34950, "action_loss_avg": 0.0021121020312421025}
+{"step": 34960, "dynamics_loss_avg": 0.03237976618111134}
+{"step": 34960, "action_loss_avg": 0.002780957380309701}
+{"step": 34970, "dynamics_loss_avg": 0.03657009936869145}
+{"step": 34970, "action_loss_avg": 0.003384863887913525}
+{"step": 34980, "dynamics_loss_avg": 0.02731545167043805}
+{"step": 34980, "action_loss_avg": 0.002210150775499642}
+{"step": 34990, "dynamics_loss_avg": 0.04093554308637977}
+{"step": 34990, "action_loss_avg": 0.0035932281462009996}
+{"step": 35000, "loss": 0.0346, "learning_rate": 7.734879212067192e-05}
+{"step": 35000, "dynamics_loss_avg": 0.03699414562433958}
+{"step": 35000, "action_loss_avg": 0.0026125953765586017}
+{"step": 35010, "dynamics_loss_avg": 0.035767148295417425}
+{"step": 35010, "action_loss_avg": 0.002625813242048025}
+{"step": 35020, "dynamics_loss_avg": 0.025431140884757043}
+{"step": 35020, "action_loss_avg": 0.0023566788295283914}
+{"step": 35030, "dynamics_loss_avg": 0.03758285269141197}
+{"step": 35030, "action_loss_avg": 0.004199822433292866}
+{"step": 35040, "dynamics_loss_avg": 0.03453733678907156}
+{"step": 35040, "action_loss_avg": 0.002551205485360697}
+{"step": 35050, "loss": 0.0329, "learning_rate": 7.727954478709607e-05}
+{"step": 35050, "dynamics_loss_avg": 0.03454166706651449}
+{"step": 35050, "action_loss_avg": 0.003001370013225824}
+{"step": 35060, "dynamics_loss_avg": 0.02585643343627453}
+{"step": 35060, "action_loss_avg": 0.0021517554007004945}
+{"step": 35070, "dynamics_loss_avg": 0.03515720469877124}
+{"step": 35070, "action_loss_avg": 0.0026176522369496524}
+{"step": 35080, "dynamics_loss_avg": 0.03808219339698553}
+{"step": 35080, "action_loss_avg": 0.003061246615834534}
+{"step": 35090, "dynamics_loss_avg": 0.028039955534040928}
+{"step": 35090, "action_loss_avg": 0.0019945304258726535}
+{"step": 35100, "loss": 0.0316, "learning_rate": 7.721022287228645e-05}
+{"step": 35100, "dynamics_loss_avg": 0.029296598583459853}
+{"step": 35100, "action_loss_avg": 0.0016932002821704374}
+{"step": 35110, "dynamics_loss_avg": 0.03011457473039627}
+{"step": 35110, "action_loss_avg": 0.0022445965325459836}
+{"step": 35120, "dynamics_loss_avg": 0.027117016538977624}
+{"step": 35120, "action_loss_avg": 0.0019505773147102446}
+{"step": 35130, "dynamics_loss_avg": 0.0250108293723315}
+{"step": 35130, "action_loss_avg": 0.0014638379943789914}
+{"step": 35140, "dynamics_loss_avg": 0.03062276877462864}
+{"step": 35140, "action_loss_avg": 0.002356140594929457}
+{"step": 35150, "loss": 0.0328, "learning_rate": 7.714082656576651e-05}
+{"step": 35150, "dynamics_loss_avg": 0.03523642234504223}
+{"step": 35150, "action_loss_avg": 0.0028816133388318123}
+{"step": 35160, "dynamics_loss_avg": 0.03563648480921984}
+{"step": 35160, "action_loss_avg": 0.002720383240375668}
+{"step": 35170, "dynamics_loss_avg": 0.027854176331311466}
+{"step": 35170, "action_loss_avg": 0.0021251297439448535}
+{"step": 35180, "dynamics_loss_avg": 0.03214215533807874}
+{"step": 35180, "action_loss_avg": 0.0025448077300097792}
+{"step": 35190, "dynamics_loss_avg": 0.04434434287250042}
+{"step": 35190, "action_loss_avg": 0.004034218075685203}
+{"step": 35200, "loss": 0.033, "learning_rate": 7.707135605726311e-05}
+{"step": 35200, "dynamics_loss_avg": 0.03176840972155333}
+{"step": 35200, "action_loss_avg": 0.0022441163659095765}
+{"step": 35210, "dynamics_loss_avg": 0.03078501271083951}
+{"step": 35210, "action_loss_avg": 0.002479043451603502}
+{"step": 35220, "dynamics_loss_avg": 0.02175155933946371}
+{"step": 35220, "action_loss_avg": 0.0015481030044611544}
+{"step": 35230, "dynamics_loss_avg": 0.023828971153125166}
+{"step": 35230, "action_loss_avg": 0.00200542519451119}
+{"step": 35240, "dynamics_loss_avg": 0.03071737475693226}
+{"step": 35240, "action_loss_avg": 0.00196359624969773}
+{"step": 35250, "loss": 0.031, "learning_rate": 7.700181153670596e-05}
+{"step": 35250, "dynamics_loss_avg": 0.035950573068112134}
+{"step": 35250, "action_loss_avg": 0.0030057032010518013}
+{"step": 35260, "dynamics_loss_avg": 0.031015789695084096}
+{"step": 35260, "action_loss_avg": 0.002281157020479441}
+{"step": 35270, "dynamics_loss_avg": 0.032759861554950476}
+{"step": 35270, "action_loss_avg": 0.0028988057572860272}
+{"step": 35280, "dynamics_loss_avg": 0.03319939086213708}
+{"step": 35280, "action_loss_avg": 0.0022032482316717505}
+{"step": 35290, "dynamics_loss_avg": 0.028742037899792194}
+{"step": 35290, "action_loss_avg": 0.0022103565017459912}
+{"step": 35300, "loss": 0.0306, "learning_rate": 7.693219319422714e-05}
+{"step": 35300, "dynamics_loss_avg": 0.03125999514013529}
+{"step": 35300, "action_loss_avg": 0.002402217360213399}
+{"step": 35310, "dynamics_loss_avg": 0.03347909450531006}
+{"step": 35310, "action_loss_avg": 0.0027575897751376034}
+{"step": 35320, "dynamics_loss_avg": 0.0279217260889709}
+{"step": 35320, "action_loss_avg": 0.0021054321376141162}
+{"step": 35330, "dynamics_loss_avg": 0.029813878471031785}
+{"step": 35330, "action_loss_avg": 0.0019894695113180207}
+{"step": 35340, "dynamics_loss_avg": 0.021208738256245852}
+{"step": 35340, "action_loss_avg": 0.001633988635148853}
+{"step": 35350, "loss": 0.0319, "learning_rate": 7.686250122016053e-05}
+{"step": 35350, "dynamics_loss_avg": 0.030044609028846026}
+{"step": 35350, "action_loss_avg": 0.0024985092633869497}
+{"step": 35360, "dynamics_loss_avg": 0.033177513629198074}
+{"step": 35360, "action_loss_avg": 0.00238180584856309}
+{"step": 35370, "dynamics_loss_avg": 0.03183962581679225}
+{"step": 35370, "action_loss_avg": 0.0027550240745767953}
+{"step": 35380, "dynamics_loss_avg": 0.02624414972960949}
+{"step": 35380, "action_loss_avg": 0.001851543743396178}
+{"step": 35390, "dynamics_loss_avg": 0.02770868968218565}
+{"step": 35390, "action_loss_avg": 0.0017269973526708783}
+{"step": 35400, "loss": 0.0309, "learning_rate": 7.679273580504132e-05}
+{"step": 35400, "dynamics_loss_avg": 0.029812617227435112}
+{"step": 35400, "action_loss_avg": 0.002612631896045059}
+{"step": 35410, "dynamics_loss_avg": 0.03547275299206376}
+{"step": 35410, "action_loss_avg": 0.0031500676996074617}
+{"step": 35420, "dynamics_loss_avg": 0.027618759032338857}
+{"step": 35420, "action_loss_avg": 0.0019742921344004572}
+{"step": 35430, "dynamics_loss_avg": 0.0357716741040349}
+{"step": 35430, "action_loss_avg": 0.003744786337483674}
+{"step": 35440, "dynamics_loss_avg": 0.03697950169444084}
+{"step": 35440, "action_loss_avg": 0.0037013263441622256}
+{"step": 35450, "loss": 0.032, "learning_rate": 7.67228971396055e-05}
+{"step": 35450, "dynamics_loss_avg": 0.03992660706862807}
+{"step": 35450, "action_loss_avg": 0.003164175822166726}
+{"step": 35460, "dynamics_loss_avg": 0.023966932017356158}
+{"step": 35460, "action_loss_avg": 0.001961668685544282}
+{"step": 35470, "dynamics_loss_avg": 0.023808276280760765}
+{"step": 35470, "action_loss_avg": 0.002272474061464891}
+{"step": 35480, "dynamics_loss_avg": 0.030688642989844084}
+{"step": 35480, "action_loss_avg": 0.002698746442911215}
+{"step": 35490, "dynamics_loss_avg": 0.027020395360887052}
+{"step": 35490, "action_loss_avg": 0.0015016765450127424}
+{"step": 35500, "loss": 0.0292, "learning_rate": 7.665298541478932e-05}
+{"step": 35500, "dynamics_loss_avg": 0.031048797070980072}
+{"step": 35500, "action_loss_avg": 0.002617407392244786}
+{"step": 35510, "dynamics_loss_avg": 0.029033623263239862}
+{"step": 35510, "action_loss_avg": 0.002298474928829819}
+{"step": 35520, "dynamics_loss_avg": 0.03175963233225047}
+{"step": 35520, "action_loss_avg": 0.0023619865110958926}
+{"step": 35530, "dynamics_loss_avg": 0.03183957347646356}
+{"step": 35530, "action_loss_avg": 0.0024036977207288145}
+{"step": 35540, "dynamics_loss_avg": 0.035470084846019746}
+{"step": 35540, "action_loss_avg": 0.0023507997626438736}
+{"step": 35550, "loss": 0.0323, "learning_rate": 7.658300082172875e-05}
+{"step": 35550, "dynamics_loss_avg": 0.02830115519464016}
+{"step": 35550, "action_loss_avg": 0.0031413922319188715}
+{"step": 35560, "dynamics_loss_avg": 0.03290709368884563}
+{"step": 35560, "action_loss_avg": 0.0030715209431946278}
+{"step": 35570, "dynamics_loss_avg": 0.035758362431079146}
+{"step": 35570, "action_loss_avg": 0.003231239746673964}
+{"step": 35580, "dynamics_loss_avg": 0.03693363545462489}
+{"step": 35580, "action_loss_avg": 0.003080603654962033}
+{"step": 35590, "dynamics_loss_avg": 0.021568776480853556}
+{"step": 35590, "action_loss_avg": 0.0016782438557129352}
+{"step": 35600, "loss": 0.0335, "learning_rate": 7.6512943551759e-05}
+{"step": 35600, "dynamics_loss_avg": 0.03849467895925045}
+{"step": 35600, "action_loss_avg": 0.003649533726274967}
+{"step": 35610, "dynamics_loss_avg": 0.032884298078715804}
+{"step": 35610, "action_loss_avg": 0.0024663527961820363}
+{"step": 35620, "dynamics_loss_avg": 0.03680322580039501}
+{"step": 35620, "action_loss_avg": 0.0027096734032966197}
+{"step": 35630, "dynamics_loss_avg": 0.020640630275011063}
+{"step": 35630, "action_loss_avg": 0.0019123495207168163}
+{"step": 35640, "dynamics_loss_avg": 0.02854827232658863}
+{"step": 35640, "action_loss_avg": 0.002265782153699547}
+{"step": 35650, "loss": 0.033, "learning_rate": 7.644281379641396e-05}
+{"step": 35650, "dynamics_loss_avg": 0.026580275781452656}
+{"step": 35650, "action_loss_avg": 0.002198117860825732}
+{"step": 35660, "dynamics_loss_avg": 0.03433046238496899}
+{"step": 35660, "action_loss_avg": 0.002445441816234961}
+{"step": 35670, "dynamics_loss_avg": 0.025283844862133264}
+{"step": 35670, "action_loss_avg": 0.0021309115400072187}
+{"step": 35680, "dynamics_loss_avg": 0.03282988648861647}
+{"step": 35680, "action_loss_avg": 0.002437669725622982}
+{"step": 35690, "dynamics_loss_avg": 0.03973671672865749}
+{"step": 35690, "action_loss_avg": 0.0028877095377538354}
+{"step": 35700, "loss": 0.0326, "learning_rate": 7.637261174742574e-05}
+{"step": 35700, "dynamics_loss_avg": 0.03231162102892995}
+{"step": 35700, "action_loss_avg": 0.002088709594681859}
+{"step": 35710, "dynamics_loss_avg": 0.024522627424448728}
+{"step": 35710, "action_loss_avg": 0.00187296366202645}
+{"step": 35720, "dynamics_loss_avg": 0.02323097912594676}
+{"step": 35720, "action_loss_avg": 0.0021511178638320416}
+{"step": 35730, "dynamics_loss_avg": 0.025039776414632797}
+{"step": 35730, "action_loss_avg": 0.0018195876735262572}
+{"step": 35740, "dynamics_loss_avg": 0.032298218086361886}
+{"step": 35740, "action_loss_avg": 0.002942510409047827}
+{"step": 35750, "loss": 0.0293, "learning_rate": 7.630233759672403e-05}
+{"step": 35750, "dynamics_loss_avg": 0.03155249105766415}
+{"step": 35750, "action_loss_avg": 0.0022116754902526737}
+{"step": 35760, "dynamics_loss_avg": 0.03156489050015807}
+{"step": 35760, "action_loss_avg": 0.0028691914631053805}
+{"step": 35770, "dynamics_loss_avg": 0.027258133236318826}
+{"step": 35770, "action_loss_avg": 0.0021211266895988954}
+{"step": 35780, "dynamics_loss_avg": 0.028386318869888783}
+{"step": 35780, "action_loss_avg": 0.0025874808081425725}
+{"step": 35790, "dynamics_loss_avg": 0.03200533222407102}
+{"step": 35790, "action_loss_avg": 0.002297910302877426}
+{"step": 35800, "loss": 0.0313, "learning_rate": 7.623199153643569e-05}
+{"step": 35800, "dynamics_loss_avg": 0.03796542678028345}
+{"step": 35800, "action_loss_avg": 0.0023257786640897395}
+{"step": 35810, "dynamics_loss_avg": 0.031019253097474574}
+{"step": 35810, "action_loss_avg": 0.0023871219891589135}
+{"step": 35820, "dynamics_loss_avg": 0.03312530480325222}
+{"step": 35820, "action_loss_avg": 0.0023394607589580117}
+{"step": 35830, "dynamics_loss_avg": 0.02137389509007335}
+{"step": 35830, "action_loss_avg": 0.0017052493640221655}
+{"step": 35840, "dynamics_loss_avg": 0.03274853993207216}
+{"step": 35840, "action_loss_avg": 0.0023333309509325773}
+{"step": 35850, "loss": 0.0316, "learning_rate": 7.616157375888416e-05}
+{"step": 35850, "dynamics_loss_avg": 0.033656362630426886}
+{"step": 35850, "action_loss_avg": 0.002365999121684581}
+{"step": 35860, "dynamics_loss_avg": 0.029693237412720917}
+{"step": 35860, "action_loss_avg": 0.0017961446370463817}
+{"step": 35870, "dynamics_loss_avg": 0.0245992285432294}
+{"step": 35870, "action_loss_avg": 0.0019347417633980512}
+{"step": 35880, "dynamics_loss_avg": 0.033695012982934716}
+{"step": 35880, "action_loss_avg": 0.0036658269877079875}
+{"step": 35890, "dynamics_loss_avg": 0.03587058046832681}
+{"step": 35890, "action_loss_avg": 0.0033987008035182955}
+{"step": 35900, "loss": 0.0311, "learning_rate": 7.609108445658893e-05}
+{"step": 35900, "dynamics_loss_avg": 0.030527401342988016}
+{"step": 35900, "action_loss_avg": 0.002878526860149577}
+{"step": 35910, "dynamics_loss_avg": 0.03158825803548097}
+{"step": 35910, "action_loss_avg": 0.0021267308155074717}
+{"step": 35920, "dynamics_loss_avg": 0.03496177988126874}
+{"step": 35920, "action_loss_avg": 0.002068513672566041}
+{"step": 35930, "dynamics_loss_avg": 0.030041301250457765}
+{"step": 35930, "action_loss_avg": 0.0024756226659519596}
+{"step": 35940, "dynamics_loss_avg": 0.03407501308247447}
+{"step": 35940, "action_loss_avg": 0.002178511116653681}
+{"step": 35950, "loss": 0.0324, "learning_rate": 7.602052382226507e-05}
+{"step": 35950, "dynamics_loss_avg": 0.03626866154372692}
+{"step": 35950, "action_loss_avg": 0.002667844877578318}
+{"step": 35960, "dynamics_loss_avg": 0.03942236807197332}
+{"step": 35960, "action_loss_avg": 0.003254065534565598}
+{"step": 35970, "dynamics_loss_avg": 0.033304326515644786}
+{"step": 35970, "action_loss_avg": 0.0025314897939097136}
+{"step": 35980, "dynamics_loss_avg": 0.020077989320270717}
+{"step": 35980, "action_loss_avg": 0.001627916336292401}
+{"step": 35990, "dynamics_loss_avg": 0.025767262931913136}
+{"step": 35990, "action_loss_avg": 0.001824545778799802}
+{"step": 36000, "loss": 0.0313, "learning_rate": 7.59498920488227e-05}
+{"step": 36000, "dynamics_loss_avg": 0.029702647123485804}
+{"step": 36000, "action_loss_avg": 0.0023873664089478553}
+{"step": 36010, "dynamics_loss_avg": 0.02358050486072898}
+{"step": 36010, "action_loss_avg": 0.002552495343843475}
+{"step": 36020, "dynamics_loss_avg": 0.03217737395316363}
+{"step": 36020, "action_loss_avg": 0.002676032786257565}
+{"step": 36030, "dynamics_loss_avg": 0.029839976970106364}
+{"step": 36030, "action_loss_avg": 0.0018623474054038525}
+{"step": 36040, "dynamics_loss_avg": 0.022580994199961422}
+{"step": 36040, "action_loss_avg": 0.002276896158582531}
+{"step": 36050, "loss": 0.027, "learning_rate": 7.587918932936636e-05}
+{"step": 36050, "dynamics_loss_avg": 0.031450201757252216}
+{"step": 36050, "action_loss_avg": 0.002695740410126746}
+{"step": 36060, "dynamics_loss_avg": 0.03129438199102878}
+{"step": 36060, "action_loss_avg": 0.0020191671123029665}
+{"step": 36070, "dynamics_loss_avg": 0.026107408106327057}
+{"step": 36070, "action_loss_avg": 0.002070806312258355}
+{"step": 36080, "dynamics_loss_avg": 0.026950128097087144}
+{"step": 36080, "action_loss_avg": 0.001752523222239688}
+{"step": 36090, "dynamics_loss_avg": 0.03671758826822043}
+{"step": 36090, "action_loss_avg": 0.002344672987237573}
+{"step": 36100, "loss": 0.0313, "learning_rate": 7.580841585719458e-05}
+{"step": 36100, "dynamics_loss_avg": 0.03032692763954401}
+{"step": 36100, "action_loss_avg": 0.002071850234642625}
+{"step": 36110, "dynamics_loss_avg": 0.025385821936652064}
+{"step": 36110, "action_loss_avg": 0.0016072841885033996}
+{"step": 36120, "dynamics_loss_avg": 0.03321452541276813}
+{"step": 36120, "action_loss_avg": 0.002685960810049437}
+{"step": 36130, "dynamics_loss_avg": 0.026651880820281804}
+{"step": 36130, "action_loss_avg": 0.0015475468593649567}
+{"step": 36140, "dynamics_loss_avg": 0.0473031647503376}
+{"step": 36140, "action_loss_avg": 0.002952547755558044}
+{"step": 36150, "loss": 0.0295, "learning_rate": 7.573757182579934e-05}
+{"step": 36150, "dynamics_loss_avg": 0.025803957879543305}
+{"step": 36150, "action_loss_avg": 0.0017122171120718122}
+{"step": 36160, "dynamics_loss_avg": 0.0332094693556428}
+{"step": 36160, "action_loss_avg": 0.0033407628536224363}
+{"step": 36170, "dynamics_loss_avg": 0.032261171657592055}
+{"step": 36170, "action_loss_avg": 0.0023893911100458355}
+{"step": 36180, "dynamics_loss_avg": 0.027341606188565494}
+{"step": 36180, "action_loss_avg": 0.0018757547659333795}
+{"step": 36190, "dynamics_loss_avg": 0.02727544018998742}
+{"step": 36190, "action_loss_avg": 0.0019519317109370604}
+{"step": 36200, "loss": 0.0311, "learning_rate": 7.566665742886551e-05}
+{"step": 36200, "dynamics_loss_avg": 0.02457103058695793}
+{"step": 36200, "action_loss_avg": 0.0023238790570758285}
+{"step": 36210, "dynamics_loss_avg": 0.039745189156383275}
+{"step": 36210, "action_loss_avg": 0.0028644187026657165}
+{"step": 36220, "dynamics_loss_avg": 0.03708482524380088}
+{"step": 36220, "action_loss_avg": 0.0025865365343634037}
+{"step": 36230, "dynamics_loss_avg": 0.02774277310818434}
+{"step": 36230, "action_loss_avg": 0.0020165106863714753}
+{"step": 36240, "dynamics_loss_avg": 0.031206321343779563}
+{"step": 36240, "action_loss_avg": 0.002920835989061743}
+{"step": 36250, "loss": 0.033, "learning_rate": 7.559567286027036e-05}
+{"step": 36250, "dynamics_loss_avg": 0.03572109518572688}
+{"step": 36250, "action_loss_avg": 0.002409391518449411}
+{"step": 36260, "dynamics_loss_avg": 0.03742460543289781}
+{"step": 36260, "action_loss_avg": 0.0027868969365954397}
+{"step": 36270, "dynamics_loss_avg": 0.03362578493542969}
+{"step": 36270, "action_loss_avg": 0.0028555862023495137}
+{"step": 36280, "dynamics_loss_avg": 0.02969014151021838}
+{"step": 36280, "action_loss_avg": 0.00262673482648097}
+{"step": 36290, "dynamics_loss_avg": 0.03588435240089893}
+{"step": 36290, "action_loss_avg": 0.002701853454345837}
+{"step": 36300, "loss": 0.0335, "learning_rate": 7.552461831408298e-05}
+{"step": 36300, "dynamics_loss_avg": 0.03312176642939448}
+{"step": 36300, "action_loss_avg": 0.002850260236300528}
+{"step": 36310, "dynamics_loss_avg": 0.02909942828118801}
+{"step": 36310, "action_loss_avg": 0.0017978089832467957}
+{"step": 36320, "dynamics_loss_avg": 0.023383252881467344}
+{"step": 36320, "action_loss_avg": 0.0021800272399559615}
+{"step": 36330, "dynamics_loss_avg": 0.028097390290349723}
+{"step": 36330, "action_loss_avg": 0.001828307518735528}
+{"step": 36340, "dynamics_loss_avg": 0.025461111404001712}
+{"step": 36340, "action_loss_avg": 0.0020308856212068347}
+{"step": 36350, "loss": 0.0312, "learning_rate": 7.545349398456376e-05}
+{"step": 36350, "dynamics_loss_avg": 0.03496126057580114}
+{"step": 36350, "action_loss_avg": 0.003469794802367687}
+{"step": 36360, "dynamics_loss_avg": 0.03275176575407386}
+{"step": 36360, "action_loss_avg": 0.0029979609185829758}
+{"step": 36370, "dynamics_loss_avg": 0.033963725063949825}
+{"step": 36370, "action_loss_avg": 0.002519842388574034}
+{"step": 36380, "dynamics_loss_avg": 0.027660413645207882}
+{"step": 36380, "action_loss_avg": 0.0024748366558924317}
+{"step": 36390, "dynamics_loss_avg": 0.033751850575208665}
+{"step": 36390, "action_loss_avg": 0.0030762223061174153}
+{"step": 36400, "loss": 0.0331, "learning_rate": 7.538230006616395e-05}
+{"step": 36400, "dynamics_loss_avg": 0.03598414771258831}
+{"step": 36400, "action_loss_avg": 0.0026587439351715147}
+{"step": 36410, "dynamics_loss_avg": 0.02370211957022548}
+{"step": 36410, "action_loss_avg": 0.0020134584279730915}
+{"step": 36420, "dynamics_loss_avg": 0.0273780120536685}
+{"step": 36420, "action_loss_avg": 0.002417143536149524}
+{"step": 36430, "dynamics_loss_avg": 0.0334803419187665}
+{"step": 36430, "action_loss_avg": 0.0020374371146317572}
+{"step": 36440, "dynamics_loss_avg": 0.02910711457952857}
+{"step": 36440, "action_loss_avg": 0.0021666613291017713}
+{"step": 36450, "loss": 0.0293, "learning_rate": 7.531103675352497e-05}
+{"step": 36450, "dynamics_loss_avg": 0.02943405993282795}
+{"step": 36450, "action_loss_avg": 0.0022076975699746983}
+{"step": 36460, "dynamics_loss_avg": 0.029093257943168284}
+{"step": 36460, "action_loss_avg": 0.002806410187622532}
+{"step": 36470, "dynamics_loss_avg": 0.03601496927440166}
+{"step": 36470, "action_loss_avg": 0.00261330270441249}
+{"step": 36480, "dynamics_loss_avg": 0.030539506860077382}
+{"step": 36480, "action_loss_avg": 0.0022161279455758633}
+{"step": 36490, "dynamics_loss_avg": 0.02884670430794358}
+{"step": 36490, "action_loss_avg": 0.0021370398899307474}
+{"step": 36500, "loss": 0.0322, "learning_rate": 7.523970424147802e-05}
+{"step": 36500, "dynamics_loss_avg": 0.028656283486634494}
+{"step": 36500, "action_loss_avg": 0.0019425928476266563}
+{"step": 36510, "dynamics_loss_avg": 0.02532333815470338}
+{"step": 36510, "action_loss_avg": 0.0018052054103463889}
+{"step": 36520, "dynamics_loss_avg": 0.030832476634532213}
+{"step": 36520, "action_loss_avg": 0.002370719640748575}
+{"step": 36530, "dynamics_loss_avg": 0.04073888724669814}
+{"step": 36530, "action_loss_avg": 0.002926738641690463}
+{"step": 36540, "dynamics_loss_avg": 0.03199979588389397}
+{"step": 36540, "action_loss_avg": 0.0025359198509249834}
+{"step": 36550, "loss": 0.033, "learning_rate": 7.516830272504342e-05}
+{"step": 36550, "dynamics_loss_avg": 0.030455179093405605}
+{"step": 36550, "action_loss_avg": 0.002759604511084035}
+{"step": 36560, "dynamics_loss_avg": 0.039035544544458387}
+{"step": 36560, "action_loss_avg": 0.0026216294034384193}
+{"step": 36570, "dynamics_loss_avg": 0.029562607128173112}
+{"step": 36570, "action_loss_avg": 0.002105534775182605}
+{"step": 36580, "dynamics_loss_avg": 0.035531099792569874}
+{"step": 36580, "action_loss_avg": 0.002276136667933315}
+{"step": 36590, "dynamics_loss_avg": 0.02476935237646103}
+{"step": 36590, "action_loss_avg": 0.001559283840470016}
+{"step": 36600, "loss": 0.0355, "learning_rate": 7.509683239943024e-05}
+{"step": 36600, "dynamics_loss_avg": 0.03860599920153618}
+{"step": 36600, "action_loss_avg": 0.0024994891253300013}
+{"step": 36610, "dynamics_loss_avg": 0.025826194137334824}
+{"step": 36610, "action_loss_avg": 0.001794270920800045}
+{"step": 36620, "dynamics_loss_avg": 0.02119624288752675}
+{"step": 36620, "action_loss_avg": 0.0015379278134787454}
+{"step": 36630, "dynamics_loss_avg": 0.03326745508238673}
+{"step": 36630, "action_loss_avg": 0.0025367014546645804}
+{"step": 36640, "dynamics_loss_avg": 0.03691283753141761}
+{"step": 36640, "action_loss_avg": 0.002369147085119039}
+{"step": 36650, "loss": 0.0314, "learning_rate": 7.502529346003559e-05}
+{"step": 36650, "dynamics_loss_avg": 0.02955223936587572}
+{"step": 36650, "action_loss_avg": 0.0023264723015017806}
+{"step": 36660, "dynamics_loss_avg": 0.04139061886817217}
+{"step": 36660, "action_loss_avg": 0.002702034096000716}
+{"step": 36670, "dynamics_loss_avg": 0.026340738870203495}
+{"step": 36670, "action_loss_avg": 0.0017212870821822434}
+{"step": 36680, "dynamics_loss_avg": 0.0308914840221405}
+{"step": 36680, "action_loss_avg": 0.0024131308018695563}
+{"step": 36690, "dynamics_loss_avg": 0.022707324614748357}
+{"step": 36690, "action_loss_avg": 0.0012539246119558812}
+{"step": 36700, "loss": 0.0307, "learning_rate": 7.495368610244423e-05}
+{"step": 36700, "dynamics_loss_avg": 0.027037820499390363}
+{"step": 36700, "action_loss_avg": 0.0017907572910189629}
+{"step": 36710, "dynamics_loss_avg": 0.030163698084652423}
+{"step": 36710, "action_loss_avg": 0.0023281431291252374}
+{"step": 36720, "dynamics_loss_avg": 0.0361188143491745}
+{"step": 36720, "action_loss_avg": 0.0031183617771603166}
+{"step": 36730, "dynamics_loss_avg": 0.027437653951346876}
+{"step": 36730, "action_loss_avg": 0.001582352875266224}
+{"step": 36740, "dynamics_loss_avg": 0.026814953610301017}
+{"step": 36740, "action_loss_avg": 0.0025087191257625817}
+{"step": 36750, "loss": 0.0307, "learning_rate": 7.48820105224279e-05}
+{"step": 36750, "dynamics_loss_avg": 0.026160832680761813}
+{"step": 36750, "action_loss_avg": 0.0017591226845979691}
+{"step": 36760, "dynamics_loss_avg": 0.03235237523913383}
+{"step": 36760, "action_loss_avg": 0.0024239806458353995}
+{"step": 36770, "dynamics_loss_avg": 0.037311476469039914}
+{"step": 36770, "action_loss_avg": 0.003221660607960075}
+{"step": 36780, "dynamics_loss_avg": 0.03510056333616376}
+{"step": 36780, "action_loss_avg": 0.002555446431506425}
+{"step": 36790, "dynamics_loss_avg": 0.03361809221096337}
+{"step": 36790, "action_loss_avg": 0.0026625210710335525}
+{"step": 36800, "loss": 0.0327, "learning_rate": 7.481026691594492e-05}
+{"step": 36800, "dynamics_loss_avg": 0.02203869204968214}
+{"step": 36800, "action_loss_avg": 0.0016118570551043377}
+{"step": 36810, "dynamics_loss_avg": 0.034085437376052144}
+{"step": 36810, "action_loss_avg": 0.0022452440287452193}
+{"step": 36820, "dynamics_loss_avg": 0.03989813895896077}
+{"step": 36820, "action_loss_avg": 0.0024456998915411534}
+{"step": 36830, "dynamics_loss_avg": 0.02204290674999356}
+{"step": 36830, "action_loss_avg": 0.0021659833553712817}
+{"step": 36840, "dynamics_loss_avg": 0.033865591138601304}
+{"step": 36840, "action_loss_avg": 0.0029486459563486276}
+{"step": 36850, "loss": 0.033, "learning_rate": 7.473845547913957e-05}
+{"step": 36850, "dynamics_loss_avg": 0.02850727513432503}
+{"step": 36850, "action_loss_avg": 0.0027476949850097298}
+{"step": 36860, "dynamics_loss_avg": 0.024449417553842067}
+{"step": 36860, "action_loss_avg": 0.0015338843688368798}
+{"step": 36870, "dynamics_loss_avg": 0.030282122641801835}
+{"step": 36870, "action_loss_avg": 0.002224167948588729}
+{"step": 36880, "dynamics_loss_avg": 0.03401642628014088}
+{"step": 36880, "action_loss_avg": 0.003407510439865291}
+{"step": 36890, "dynamics_loss_avg": 0.02583031328395009}
+{"step": 36890, "action_loss_avg": 0.0021045303903520106}
+{"step": 36900, "loss": 0.0329, "learning_rate": 7.466657640834158e-05}
+{"step": 36900, "dynamics_loss_avg": 0.03432990722358227}
+{"step": 36900, "action_loss_avg": 0.002738520910497755}
+{"step": 36910, "dynamics_loss_avg": 0.02740932013839483}
+{"step": 36910, "action_loss_avg": 0.002511213388061151}
+{"step": 36920, "dynamics_loss_avg": 0.03461068840697408}
+{"step": 36920, "action_loss_avg": 0.0027533217798918486}
+{"step": 36930, "dynamics_loss_avg": 0.02600196492858231}
+{"step": 36930, "action_loss_avg": 0.0021507972152903674}
+{"step": 36940, "dynamics_loss_avg": 0.03293427499011159}
+{"step": 36940, "action_loss_avg": 0.0034451272222213447}
+{"step": 36950, "loss": 0.0299, "learning_rate": 7.459462990006558e-05}
+{"step": 36950, "dynamics_loss_avg": 0.026119033340364695}
+{"step": 36950, "action_loss_avg": 0.0017205983167514205}
+{"step": 36960, "dynamics_loss_avg": 0.026318805012851953}
+{"step": 36960, "action_loss_avg": 0.0024306886130943894}
+{"step": 36970, "dynamics_loss_avg": 0.023750706668943168}
+{"step": 36970, "action_loss_avg": 0.0018879924726206809}
+{"step": 36980, "dynamics_loss_avg": 0.04055024720728397}
+{"step": 36980, "action_loss_avg": 0.003348815214121714}
+{"step": 36990, "dynamics_loss_avg": 0.03122237930074334}
+{"step": 36990, "action_loss_avg": 0.0024159707012586296}
+{"step": 37000, "loss": 0.0294, "learning_rate": 7.452261615101057e-05}
+{"step": 37000, "dynamics_loss_avg": 0.03240815652534366}
+{"step": 37000, "action_loss_avg": 0.002421564213000238}
+{"step": 37010, "dynamics_loss_avg": 0.0238538833335042}
+{"step": 37010, "action_loss_avg": 0.0023481065523810684}
+{"step": 37020, "dynamics_loss_avg": 0.02994491709396243}
+{"step": 37020, "action_loss_avg": 0.0019735021982342006}
+{"step": 37030, "dynamics_loss_avg": 0.03867589645087719}
+{"step": 37030, "action_loss_avg": 0.0027573847299208866}
+{"step": 37040, "dynamics_loss_avg": 0.031748051987960935}
+{"step": 37040, "action_loss_avg": 0.002398507832549512}
+{"step": 37050, "loss": 0.0353, "learning_rate": 7.445053535805942e-05}
+{"step": 37050, "dynamics_loss_avg": 0.04318881910294294}
+{"step": 37050, "action_loss_avg": 0.00279431821545586}
+{"step": 37060, "dynamics_loss_avg": 0.022215374652296303}
+{"step": 37060, "action_loss_avg": 0.0013974317174870522}
+{"step": 37070, "dynamics_loss_avg": 0.034456480946391824}
+{"step": 37070, "action_loss_avg": 0.002649565110914409}
+{"step": 37080, "dynamics_loss_avg": 0.03925814656540751}
+{"step": 37080, "action_loss_avg": 0.0035686631221324206}
+{"step": 37090, "dynamics_loss_avg": 0.03363562459126115}
+{"step": 37090, "action_loss_avg": 0.0029669407347682865}
+{"step": 37100, "loss": 0.0361, "learning_rate": 7.43783877182782e-05}
+{"step": 37100, "dynamics_loss_avg": 0.03600873444229365}
+{"step": 37100, "action_loss_avg": 0.0036691354122012853}
+{"step": 37110, "dynamics_loss_avg": 0.035887766350060704}
+{"step": 37110, "action_loss_avg": 0.0032577097823377698}
+{"step": 37120, "dynamics_loss_avg": 0.02838641544803977}
+{"step": 37120, "action_loss_avg": 0.0018020727788098157}
+{"step": 37130, "dynamics_loss_avg": 0.028208430297672747}
+{"step": 37130, "action_loss_avg": 0.0024260976584628224}
+{"step": 37140, "dynamics_loss_avg": 0.033096562046557663}
+{"step": 37140, "action_loss_avg": 0.002772661205381155}
+{"step": 37150, "loss": 0.0313, "learning_rate": 7.430617342891588e-05}
+{"step": 37150, "dynamics_loss_avg": 0.023388382513076067}
+{"step": 37150, "action_loss_avg": 0.001944407296832651}
+{"step": 37160, "dynamics_loss_avg": 0.025901481602340938}
+{"step": 37160, "action_loss_avg": 0.0013476771535351872}
+{"step": 37170, "dynamics_loss_avg": 0.032765852846205236}
+{"step": 37170, "action_loss_avg": 0.0024552107992349193}
+{"step": 37180, "dynamics_loss_avg": 0.03515439759939909}
+{"step": 37180, "action_loss_avg": 0.0029465162369888276}
+{"step": 37190, "dynamics_loss_avg": 0.024833158263936637}
+{"step": 37190, "action_loss_avg": 0.0022446583257988094}
+{"step": 37200, "loss": 0.0311, "learning_rate": 7.423389268740352e-05}
+{"step": 37200, "dynamics_loss_avg": 0.02446195697411895}
+{"step": 37200, "action_loss_avg": 0.0022022776072844865}
+{"step": 37210, "dynamics_loss_avg": 0.021154154976829886}
+{"step": 37210, "action_loss_avg": 0.0014312955841887741}
+{"step": 37220, "dynamics_loss_avg": 0.02948265541344881}
+{"step": 37220, "action_loss_avg": 0.002385721087921411}
+{"step": 37230, "dynamics_loss_avg": 0.01974743213504553}
+{"step": 37230, "action_loss_avg": 0.0017458756687119604}
+{"step": 37240, "dynamics_loss_avg": 0.027421699929982425}
+{"step": 37240, "action_loss_avg": 0.0022564861457794903}
+{"step": 37250, "loss": 0.0269, "learning_rate": 7.416154569135393e-05}
+{"step": 37250, "dynamics_loss_avg": 0.02658045757561922}
+{"step": 37250, "action_loss_avg": 0.0023718643322354184}
+{"step": 37260, "dynamics_loss_avg": 0.035236210003495215}
+{"step": 37260, "action_loss_avg": 0.0022758855950087307}
+{"step": 37270, "dynamics_loss_avg": 0.04332944368943572}
+{"step": 37270, "action_loss_avg": 0.0033003027376253156}
+{"step": 37280, "dynamics_loss_avg": 0.0360337046906352}
+{"step": 37280, "action_loss_avg": 0.0033233880763873457}
+{"step": 37290, "dynamics_loss_avg": 0.029650506749749183}
+{"step": 37290, "action_loss_avg": 0.0019876406411640348}
+{"step": 37300, "loss": 0.0371, "learning_rate": 7.408913263856102e-05}
+{"step": 37300, "dynamics_loss_avg": 0.027299613412469625}
+{"step": 37300, "action_loss_avg": 0.002623795164981857}
+{"step": 37310, "dynamics_loss_avg": 0.032420076243579385}
+{"step": 37310, "action_loss_avg": 0.0026249764545354993}
+{"step": 37320, "dynamics_loss_avg": 0.03124456973746419}
+{"step": 37320, "action_loss_avg": 0.002544585900614038}
+{"step": 37330, "dynamics_loss_avg": 0.030248783901333808}
+{"step": 37330, "action_loss_avg": 0.0022701576235704124}
+{"step": 37340, "dynamics_loss_avg": 0.03197187846526504}
+{"step": 37340, "action_loss_avg": 0.0027488869469380005}
+{"step": 37350, "loss": 0.0308, "learning_rate": 7.401665372699932e-05}
+{"step": 37350, "dynamics_loss_avg": 0.026533628068864345}
+{"step": 37350, "action_loss_avg": 0.0017193614039570093}
+{"step": 37360, "dynamics_loss_avg": 0.029200320970267056}
+{"step": 37360, "action_loss_avg": 0.0020962599199265243}
+{"step": 37370, "dynamics_loss_avg": 0.027456104196608065}
+{"step": 37370, "action_loss_avg": 0.0021043895510956647}
+{"step": 37380, "dynamics_loss_avg": 0.028368614334613084}
+{"step": 37380, "action_loss_avg": 0.0018032628926448525}
+{"step": 37390, "dynamics_loss_avg": 0.025982708390802144}
+{"step": 37390, "action_loss_avg": 0.002259169641183689}
+{"step": 37400, "loss": 0.0315, "learning_rate": 7.394410915482341e-05}
+{"step": 37400, "dynamics_loss_avg": 0.03225322859361768}
+{"step": 37400, "action_loss_avg": 0.0028639873140491544}
+{"step": 37410, "dynamics_loss_avg": 0.035893157310783866}
+{"step": 37410, "action_loss_avg": 0.0023563792870845645}
+{"step": 37420, "dynamics_loss_avg": 0.03257918781600892}
+{"step": 37420, "action_loss_avg": 0.002576740027870983}
+{"step": 37430, "dynamics_loss_avg": 0.030088561493903397}
+{"step": 37430, "action_loss_avg": 0.0021941378130577506}
+{"step": 37440, "dynamics_loss_avg": 0.041111111827194693}
+{"step": 37440, "action_loss_avg": 0.002982758719008416}
+{"step": 37450, "loss": 0.0352, "learning_rate": 7.387149912036738e-05}
+{"step": 37450, "dynamics_loss_avg": 0.028164911456406115}
+{"step": 37450, "action_loss_avg": 0.0017110927205067129}
+{"step": 37460, "dynamics_loss_avg": 0.023108071833848953}
+{"step": 37460, "action_loss_avg": 0.0016289373830659314}
+{"step": 37470, "dynamics_loss_avg": 0.03405838152393699}
+{"step": 37470, "action_loss_avg": 0.0025045978254638612}
+{"step": 37480, "dynamics_loss_avg": 0.03315920336171985}
+{"step": 37480, "action_loss_avg": 0.003060724749229848}
+{"step": 37490, "dynamics_loss_avg": 0.038877942599356174}
+{"step": 37490, "action_loss_avg": 0.002409467249526642}
+{"step": 37500, "loss": 0.0322, "learning_rate": 7.379882382214426e-05}
+{"step": 37500, "dynamics_loss_avg": 0.0209568296559155}
+{"step": 37500, "action_loss_avg": 0.001889548238250427}
+{"step": 37510, "dynamics_loss_avg": 0.032319204229861495}
+{"step": 37510, "action_loss_avg": 0.002230325888376683}
+{"step": 37520, "dynamics_loss_avg": 0.03827689234167338}
+{"step": 37520, "action_loss_avg": 0.0028400199313182383}
+{"step": 37530, "dynamics_loss_avg": 0.03882467914372682}
+{"step": 37530, "action_loss_avg": 0.0021966900618281215}
+{"step": 37540, "dynamics_loss_avg": 0.027416280889883637}
+{"step": 37540, "action_loss_avg": 0.002132679586065933}
+{"step": 37550, "loss": 0.0344, "learning_rate": 7.372608345884558e-05}
+{"step": 37550, "dynamics_loss_avg": 0.030092457216233014}
+{"step": 37550, "action_loss_avg": 0.0025708535860758273}
+{"step": 37560, "dynamics_loss_avg": 0.02876987960189581}
+{"step": 37560, "action_loss_avg": 0.002076784009113908}
+{"step": 37570, "dynamics_loss_avg": 0.03750517833977938}
+{"step": 37570, "action_loss_avg": 0.0029150048503652215}
+{"step": 37580, "dynamics_loss_avg": 0.029281875398010016}
+{"step": 37580, "action_loss_avg": 0.0018731085408944636}
+{"step": 37590, "dynamics_loss_avg": 0.029040556401014328}
+{"step": 37590, "action_loss_avg": 0.002344039914896712}
+{"step": 37600, "loss": 0.0327, "learning_rate": 7.36532782293407e-05}
+{"step": 37600, "dynamics_loss_avg": 0.027212530560791492}
+{"step": 37600, "action_loss_avg": 0.002180355560267344}
+{"step": 37610, "dynamics_loss_avg": 0.027361467760056258}
+{"step": 37610, "action_loss_avg": 0.0023562528600450604}
+{"step": 37620, "dynamics_loss_avg": 0.034673776291310784}
+{"step": 37620, "action_loss_avg": 0.0024296746181789786}
+{"step": 37630, "dynamics_loss_avg": 0.03359855338931084}
+{"step": 37630, "action_loss_avg": 0.002625448681646958}
+{"step": 37640, "dynamics_loss_avg": 0.035332987643778326}
+{"step": 37640, "action_loss_avg": 0.0031942980713211}
+{"step": 37650, "loss": 0.034, "learning_rate": 7.358040833267634e-05}
+{"step": 37650, "dynamics_loss_avg": 0.03995720390230417}
+{"step": 37650, "action_loss_avg": 0.0033187362249009313}
+{"step": 37660, "dynamics_loss_avg": 0.03151537552475929}
+{"step": 37660, "action_loss_avg": 0.002287860756041482}
+{"step": 37670, "dynamics_loss_avg": 0.033629908226430416}
+{"step": 37670, "action_loss_avg": 0.0028024374041706324}
+{"step": 37680, "dynamics_loss_avg": 0.02963437419384718}
+{"step": 37680, "action_loss_avg": 0.002558308036532253}
+{"step": 37690, "dynamics_loss_avg": 0.027190638054162265}
+{"step": 37690, "action_loss_avg": 0.002437057753559202}
+{"step": 37700, "loss": 0.0337, "learning_rate": 7.350747396807601e-05}
+{"step": 37700, "dynamics_loss_avg": 0.02854810105636716}
+{"step": 37700, "action_loss_avg": 0.0023573197482619434}
+{"step": 37710, "dynamics_loss_avg": 0.02954180762171745}
+{"step": 37710, "action_loss_avg": 0.0023855402891058476}
+{"step": 37720, "dynamics_loss_avg": 0.03652888825163245}
+{"step": 37720, "action_loss_avg": 0.002774270763620734}
+{"step": 37730, "dynamics_loss_avg": 0.025917544681578874}
+{"step": 37730, "action_loss_avg": 0.002305459976196289}
+{"step": 37740, "dynamics_loss_avg": 0.023303322680294513}
+{"step": 37740, "action_loss_avg": 0.001366666893591173}
+{"step": 37750, "loss": 0.0308, "learning_rate": 7.343447533493947e-05}
+{"step": 37750, "dynamics_loss_avg": 0.02889928026124835}
+{"step": 37750, "action_loss_avg": 0.0028063098958227783}
+{"step": 37760, "dynamics_loss_avg": 0.039615561719983816}
+{"step": 37760, "action_loss_avg": 0.0028869270288851114}
+{"step": 37770, "dynamics_loss_avg": 0.03714675363153219}
+{"step": 37770, "action_loss_avg": 0.0029426661087200044}
+{"step": 37780, "dynamics_loss_avg": 0.03759961798787117}
+{"step": 37780, "action_loss_avg": 0.0031625998904928564}
+{"step": 37790, "dynamics_loss_avg": 0.027210712991654874}
+{"step": 37790, "action_loss_avg": 0.0024827040324453264}
+{"step": 37800, "loss": 0.0363, "learning_rate": 7.336141263284225e-05}
+{"step": 37800, "dynamics_loss_avg": 0.03387658766005188}
+{"step": 37800, "action_loss_avg": 0.002398772301967256}
+{"step": 37810, "dynamics_loss_avg": 0.039249046333134176}
+{"step": 37810, "action_loss_avg": 0.0032240002299658956}
+{"step": 37820, "dynamics_loss_avg": 0.025522300321608783}
+{"step": 37820, "action_loss_avg": 0.0020689416443929074}
+{"step": 37830, "dynamics_loss_avg": 0.03306085518561304}
+{"step": 37830, "action_loss_avg": 0.002247482066741213}
+{"step": 37840, "dynamics_loss_avg": 0.02214856883510947}
+{"step": 37840, "action_loss_avg": 0.0017614403157494962}
+{"step": 37850, "loss": 0.0322, "learning_rate": 7.32882860615349e-05}
+{"step": 37850, "dynamics_loss_avg": 0.025014621764421464}
+{"step": 37850, "action_loss_avg": 0.0025017022620886565}
+{"step": 37860, "dynamics_loss_avg": 0.025435830745846034}
+{"step": 37860, "action_loss_avg": 0.0013737198198214174}
+{"step": 37870, "dynamics_loss_avg": 0.033625906147062776}
+{"step": 37870, "action_loss_avg": 0.002816333743976429}
+{"step": 37880, "dynamics_loss_avg": 0.03351618610322475}
+{"step": 37880, "action_loss_avg": 0.00316161445225589}
+{"step": 37890, "dynamics_loss_avg": 0.029695127811282872}
+{"step": 37890, "action_loss_avg": 0.002461550006410107}
+{"step": 37900, "loss": 0.0326, "learning_rate": 7.321509582094274e-05}
+{"step": 37900, "dynamics_loss_avg": 0.02948997709900141}
+{"step": 37900, "action_loss_avg": 0.0021287938550813125}
+{"step": 37910, "dynamics_loss_avg": 0.02716282531619072}
+{"step": 37910, "action_loss_avg": 0.0018795697949826717}
+{"step": 37920, "dynamics_loss_avg": 0.023516989313066006}
+{"step": 37920, "action_loss_avg": 0.0014358484710101037}
+{"step": 37930, "dynamics_loss_avg": 0.03177927737124264}
+{"step": 37930, "action_loss_avg": 0.002820089159649797}
+{"step": 37940, "dynamics_loss_avg": 0.023769231140613557}
+{"step": 37940, "action_loss_avg": 0.00171208901447244}
+{"step": 37950, "loss": 0.0293, "learning_rate": 7.314184211116507e-05}
+{"step": 37950, "dynamics_loss_avg": 0.02201880612410605}
+{"step": 37950, "action_loss_avg": 0.0017058490717317908}
+{"step": 37960, "dynamics_loss_avg": 0.026626015454530715}
+{"step": 37960, "action_loss_avg": 0.0015928796259686352}
+{"step": 37970, "dynamics_loss_avg": 0.0347016048617661}
+{"step": 37970, "action_loss_avg": 0.00285344248986803}
+{"step": 37980, "dynamics_loss_avg": 0.023748002573847772}
+{"step": 37980, "action_loss_avg": 0.0017668283893726767}
+{"step": 37990, "dynamics_loss_avg": 0.02174092479981482}
+{"step": 37990, "action_loss_avg": 0.0017429704719688743}
+{"step": 38000, "loss": 0.0312, "learning_rate": 7.306852513247474e-05}
+{"step": 38000, "dynamics_loss_avg": 0.04185075089335442}
+{"step": 38000, "action_loss_avg": 0.0026194117264822124}
+{"step": 38010, "dynamics_loss_avg": 0.027936762012541295}
+{"step": 38010, "action_loss_avg": 0.0020352698746137323}
+{"step": 38020, "dynamics_loss_avg": 0.037351562455296514}
+{"step": 38020, "action_loss_avg": 0.002254854654893279}
+{"step": 38030, "dynamics_loss_avg": 0.024364080093801022}
+{"step": 38030, "action_loss_avg": 0.001649787899805233}
+{"step": 38040, "dynamics_loss_avg": 0.025748449191451073}
+{"step": 38040, "action_loss_avg": 0.0022823898354545234}
+{"step": 38050, "loss": 0.0301, "learning_rate": 7.299514508531757e-05}
+{"step": 38050, "dynamics_loss_avg": 0.028284472040832044}
+{"step": 38050, "action_loss_avg": 0.002316142822382972}
+{"step": 38060, "dynamics_loss_avg": 0.030543785076588392}
+{"step": 38060, "action_loss_avg": 0.0021664083935320376}
+{"step": 38070, "dynamics_loss_avg": 0.03868812071159482}
+{"step": 38070, "action_loss_avg": 0.002375276677776128}
+{"step": 38080, "dynamics_loss_avg": 0.02798789767548442}
+{"step": 38080, "action_loss_avg": 0.002143874013563618}
+{"step": 38090, "dynamics_loss_avg": 0.026419177884235978}
+{"step": 38090, "action_loss_avg": 0.0018103012116625905}
+{"step": 38100, "loss": 0.0332, "learning_rate": 7.292170217031179e-05}
+{"step": 38100, "dynamics_loss_avg": 0.03415203187614679}
+{"step": 38100, "action_loss_avg": 0.0034640147583559155}
+{"step": 38110, "dynamics_loss_avg": 0.026775583857670426}
+{"step": 38110, "action_loss_avg": 0.00211983673798386}
+{"step": 38120, "dynamics_loss_avg": 0.032677224930375816}
+{"step": 38120, "action_loss_avg": 0.0023692060145549475}
+{"step": 38130, "dynamics_loss_avg": 0.03165212096646428}
+{"step": 38130, "action_loss_avg": 0.002441426506265998}
+{"step": 38140, "dynamics_loss_avg": 0.02856343239545822}
+{"step": 38140, "action_loss_avg": 0.002271952212322503}
+{"step": 38150, "loss": 0.0319, "learning_rate": 7.284819658824756e-05}
+{"step": 38150, "dynamics_loss_avg": 0.03506459146738052}
+{"step": 38150, "action_loss_avg": 0.0030820698011666536}
+{"step": 38160, "dynamics_loss_avg": 0.02980861850082874}
+{"step": 38160, "action_loss_avg": 0.002009266201639548}
+{"step": 38170, "dynamics_loss_avg": 0.03719576075673103}
+{"step": 38170, "action_loss_avg": 0.003162453754339367}
+{"step": 38180, "dynamics_loss_avg": 0.0331539686769247}
+{"step": 38180, "action_loss_avg": 0.002627559844404459}
+{"step": 38190, "dynamics_loss_avg": 0.021566084958612917}
+{"step": 38190, "action_loss_avg": 0.002474551944760606}
+{"step": 38200, "loss": 0.0317, "learning_rate": 7.277462854008629e-05}
+{"step": 38200, "dynamics_loss_avg": 0.02340631475672126}
+{"step": 38200, "action_loss_avg": 0.002486834168666974}
+{"step": 38210, "dynamics_loss_avg": 0.029050207696855068}
+{"step": 38210, "action_loss_avg": 0.0027992303599603473}
+{"step": 38220, "dynamics_loss_avg": 0.021339762164279817}
+{"step": 38220, "action_loss_avg": 0.0015508329030126332}
+{"step": 38230, "dynamics_loss_avg": 0.031776202656328675}
+{"step": 38230, "action_loss_avg": 0.002130803733598441}
+{"step": 38240, "dynamics_loss_avg": 0.028933168575167655}
+{"step": 38240, "action_loss_avg": 0.00220823516137898}
+{"step": 38250, "loss": 0.0331, "learning_rate": 7.270099822696024e-05}
+{"step": 38250, "dynamics_loss_avg": 0.03729845630005002}
+{"step": 38250, "action_loss_avg": 0.0028039381955750286}
+{"step": 38260, "dynamics_loss_avg": 0.028172490140423178}
+{"step": 38260, "action_loss_avg": 0.0025218375376425683}
+{"step": 38270, "dynamics_loss_avg": 0.039196261763572694}
+{"step": 38270, "action_loss_avg": 0.0032653929200023414}
+{"step": 38280, "dynamics_loss_avg": 0.027114474773406984}
+{"step": 38280, "action_loss_avg": 0.002132534561678767}
+{"step": 38290, "dynamics_loss_avg": 0.025501300860196353}
+{"step": 38290, "action_loss_avg": 0.002488526614615694}
+{"step": 38300, "loss": 0.0325, "learning_rate": 7.262730585017188e-05}
+{"step": 38300, "dynamics_loss_avg": 0.027541038114577532}
+{"step": 38300, "action_loss_avg": 0.002295327905449085}
+{"step": 38310, "dynamics_loss_avg": 0.025237324740737678}
+{"step": 38310, "action_loss_avg": 0.0015045050415210426}
+{"step": 38320, "dynamics_loss_avg": 0.03284417102113366}
+{"step": 38320, "action_loss_avg": 0.0021399538090918213}
+{"step": 38330, "dynamics_loss_avg": 0.034826023736968637}
+{"step": 38330, "action_loss_avg": 0.003456960921175778}
+{"step": 38340, "dynamics_loss_avg": 0.021866004448384047}
+{"step": 38340, "action_loss_avg": 0.0016639282403048128}
+{"step": 38350, "loss": 0.0299, "learning_rate": 7.255355161119336e-05}
+{"step": 38350, "dynamics_loss_avg": 0.02877188688144088}
+{"step": 38350, "action_loss_avg": 0.0021805346535984428}
+{"step": 38360, "dynamics_loss_avg": 0.02986991573125124}
+{"step": 38360, "action_loss_avg": 0.0020527543500065805}
+{"step": 38370, "dynamics_loss_avg": 0.025963276531547307}
+{"step": 38370, "action_loss_avg": 0.0016980176093056797}
+{"step": 38380, "dynamics_loss_avg": 0.03414535447955132}
+{"step": 38380, "action_loss_avg": 0.00285351105267182}
+{"step": 38390, "dynamics_loss_avg": 0.02354764621704817}
+{"step": 38390, "action_loss_avg": 0.001697972189867869}
+{"step": 38400, "loss": 0.0307, "learning_rate": 7.247973571166593e-05}
+{"step": 38400, "dynamics_loss_avg": 0.03800488645210862}
+{"step": 38400, "action_loss_avg": 0.0025502276374027135}
+{"step": 38410, "dynamics_loss_avg": 0.036638643406331536}
+{"step": 38410, "action_loss_avg": 0.002408347767777741}
+{"step": 38420, "dynamics_loss_avg": 0.023489779653027655}
+{"step": 38420, "action_loss_avg": 0.0018331712984945626}
+{"step": 38430, "dynamics_loss_avg": 0.02721939580515027}
+{"step": 38430, "action_loss_avg": 0.0022204783163033426}
+{"step": 38440, "dynamics_loss_avg": 0.032238253578543666}
+{"step": 38440, "action_loss_avg": 0.003418056550435722}
+{"step": 38450, "loss": 0.0341, "learning_rate": 7.240585835339946e-05}
+{"step": 38450, "dynamics_loss_avg": 0.03697035107761622}
+{"step": 38450, "action_loss_avg": 0.0027088871924206615}
+{"step": 38460, "dynamics_loss_avg": 0.028913072869181634}
+{"step": 38460, "action_loss_avg": 0.0021415011578937992}
+{"step": 38470, "dynamics_loss_avg": 0.03979395180940628}
+{"step": 38470, "action_loss_avg": 0.002921924728434533}
+{"step": 38480, "dynamics_loss_avg": 0.03469039974734187}
+{"step": 38480, "action_loss_avg": 0.0023601783672347666}
+{"step": 38490, "dynamics_loss_avg": 0.02841929383575916}
+{"step": 38490, "action_loss_avg": 0.0023150713241193444}
+{"step": 38500, "loss": 0.034, "learning_rate": 7.233191973837179e-05}
+{"step": 38500, "dynamics_loss_avg": 0.025596783310174943}
+{"step": 38500, "action_loss_avg": 0.0014428620925173163}
+{"step": 38510, "dynamics_loss_avg": 0.0333813794888556}
+{"step": 38510, "action_loss_avg": 0.0021360140410251914}
+{"step": 38520, "dynamics_loss_avg": 0.026320493035018443}
+{"step": 38520, "action_loss_avg": 0.002091921149985865}
+{"step": 38530, "dynamics_loss_avg": 0.030620702914893626}
+{"step": 38530, "action_loss_avg": 0.00211003536824137}
+{"step": 38540, "dynamics_loss_avg": 0.03224499449133873}
+{"step": 38540, "action_loss_avg": 0.0018777387682348489}
+{"step": 38550, "loss": 0.0307, "learning_rate": 7.225792006872831e-05}
+{"step": 38550, "dynamics_loss_avg": 0.0319486303254962}
+{"step": 38550, "action_loss_avg": 0.002335757378023118}
+{"step": 38560, "dynamics_loss_avg": 0.0301682123914361}
+{"step": 38560, "action_loss_avg": 0.0019817519380012525}
+{"step": 38570, "dynamics_loss_avg": 0.028937239572405814}
+{"step": 38570, "action_loss_avg": 0.0019698714022524655}
+{"step": 38580, "dynamics_loss_avg": 0.03326783487573266}
+{"step": 38580, "action_loss_avg": 0.0027845217555295676}
+{"step": 38590, "dynamics_loss_avg": 0.03165197502821684}
+{"step": 38590, "action_loss_avg": 0.0030974823050200937}
+{"step": 38600, "loss": 0.0335, "learning_rate": 7.21838595467813e-05}
+{"step": 38600, "dynamics_loss_avg": 0.03571848561987281}
+{"step": 38600, "action_loss_avg": 0.0027518485323525963}
+{"step": 38610, "dynamics_loss_avg": 0.027518591657280923}
+{"step": 38610, "action_loss_avg": 0.001801161258481443}
+{"step": 38620, "dynamics_loss_avg": 0.03535388158634305}
+{"step": 38620, "action_loss_avg": 0.002892578300088644}
+{"step": 38630, "dynamics_loss_avg": 0.034882262162864205}
+{"step": 38630, "action_loss_avg": 0.002839762583607808}
+{"step": 38640, "dynamics_loss_avg": 0.03603704357519746}
+{"step": 38640, "action_loss_avg": 0.002856189070735127}
+{"step": 38650, "loss": 0.0338, "learning_rate": 7.210973837500937e-05}
+{"step": 38650, "dynamics_loss_avg": 0.03463324159383774}
+{"step": 38650, "action_loss_avg": 0.0029961225955048576}
+{"step": 38660, "dynamics_loss_avg": 0.02001042841002345}
+{"step": 38660, "action_loss_avg": 0.002174622658640146}
+{"step": 38670, "dynamics_loss_avg": 0.03433813359588385}
+{"step": 38670, "action_loss_avg": 0.0024219770100899042}
+{"step": 38680, "dynamics_loss_avg": 0.03129193624481559}
+{"step": 38680, "action_loss_avg": 0.002816595934564248}
+{"step": 38690, "dynamics_loss_avg": 0.0261481499299407}
+{"step": 38690, "action_loss_avg": 0.002049176907166839}
+{"step": 38700, "loss": 0.03, "learning_rate": 7.203555675605697e-05}
+{"step": 38700, "dynamics_loss_avg": 0.03315414544194937}
+{"step": 38700, "action_loss_avg": 0.0018704897549469024}
+{"step": 38710, "dynamics_loss_avg": 0.028533886279910804}
+{"step": 38710, "action_loss_avg": 0.0018446926085744053}
+{"step": 38720, "dynamics_loss_avg": 0.029718878865242004}
+{"step": 38720, "action_loss_avg": 0.001717868319246918}
+{"step": 38730, "dynamics_loss_avg": 0.028715291060507298}
+{"step": 38730, "action_loss_avg": 0.002357048384146765}
+{"step": 38740, "dynamics_loss_avg": 0.03300934750586748}
+{"step": 38740, "action_loss_avg": 0.00233637624187395}
+{"step": 38750, "loss": 0.033, "learning_rate": 7.196131489273381e-05}
+{"step": 38750, "dynamics_loss_avg": 0.02547932700254023}
+{"step": 38750, "action_loss_avg": 0.002161649888148531}
+{"step": 38760, "dynamics_loss_avg": 0.029964206274598837}
+{"step": 38760, "action_loss_avg": 0.0017664660408627242}
+{"step": 38770, "dynamics_loss_avg": 0.029410389252007008}
+{"step": 38770, "action_loss_avg": 0.001504237181507051}
+{"step": 38780, "dynamics_loss_avg": 0.03743946105241776}
+{"step": 38780, "action_loss_avg": 0.002127623313572258}
+{"step": 38790, "dynamics_loss_avg": 0.026685677748173476}
+{"step": 38790, "action_loss_avg": 0.0016772959323134273}
+{"step": 38800, "loss": 0.032, "learning_rate": 7.188701298801435e-05}
+{"step": 38800, "dynamics_loss_avg": 0.025174579303711652}
+{"step": 38800, "action_loss_avg": 0.001557775554829277}
+{"step": 38810, "dynamics_loss_avg": 0.036336070485413076}
+{"step": 38810, "action_loss_avg": 0.0018356718297582119}
+{"step": 38820, "dynamics_loss_avg": 0.024224428366869687}
+{"step": 38820, "action_loss_avg": 0.0018205475294962525}
+{"step": 38830, "dynamics_loss_avg": 0.03230369659140706}
+{"step": 38830, "action_loss_avg": 0.002953282301314175}
+{"step": 38840, "dynamics_loss_avg": 0.02864789143204689}
+{"step": 38840, "action_loss_avg": 0.0016921672271564604}
+{"step": 38850, "loss": 0.0339, "learning_rate": 7.181265124503711e-05}
+{"step": 38850, "dynamics_loss_avg": 0.02843665312975645}
+{"step": 38850, "action_loss_avg": 0.0018971107550896705}
+{"step": 38860, "dynamics_loss_avg": 0.025159404240548612}
+{"step": 38860, "action_loss_avg": 0.0019657981407362967}
+{"step": 38870, "dynamics_loss_avg": 0.029508015606552362}
+{"step": 38870, "action_loss_avg": 0.0020709880132926627}
+{"step": 38880, "dynamics_loss_avg": 0.017973051639273763}
+{"step": 38880, "action_loss_avg": 0.0018058386776829138}
+{"step": 38890, "dynamics_loss_avg": 0.028000747971236705}
+{"step": 38890, "action_loss_avg": 0.002412383782211691}
+{"step": 38900, "loss": 0.0295, "learning_rate": 7.17382298671043e-05}
+{"step": 38900, "dynamics_loss_avg": 0.032652972545474765}
+{"step": 38900, "action_loss_avg": 0.0023013747995719314}
+{"step": 38910, "dynamics_loss_avg": 0.030672933161258697}
+{"step": 38910, "action_loss_avg": 0.0017165003577247263}
+{"step": 38920, "dynamics_loss_avg": 0.02914590509608388}
+{"step": 38920, "action_loss_avg": 0.002213613817002624}
+{"step": 38930, "dynamics_loss_avg": 0.02737465314567089}
+{"step": 38930, "action_loss_avg": 0.0024636117450427264}
+{"step": 38940, "dynamics_loss_avg": 0.031548143224790694}
+{"step": 38940, "action_loss_avg": 0.002418726251926273}
+{"step": 38950, "loss": 0.0313, "learning_rate": 7.166374905768111e-05}
+{"step": 38950, "dynamics_loss_avg": 0.03329592142254114}
+{"step": 38950, "action_loss_avg": 0.002581561094848439}
+{"step": 38960, "dynamics_loss_avg": 0.031517579592764376}
+{"step": 38960, "action_loss_avg": 0.0025606871058698744}
+{"step": 38970, "dynamics_loss_avg": 0.029971363581717016}
+{"step": 38970, "action_loss_avg": 0.002082075137877837}
+{"step": 38980, "dynamics_loss_avg": 0.02628899421542883}
+{"step": 38980, "action_loss_avg": 0.001498639365308918}
+{"step": 38990, "dynamics_loss_avg": 0.023320090118795635}
+{"step": 38990, "action_loss_avg": 0.0015394923335406928}
+{"step": 39000, "loss": 0.0307, "learning_rate": 7.158920902039521e-05}
+{"step": 39000, "dynamics_loss_avg": 0.02713296813890338}
+{"step": 39000, "action_loss_avg": 0.0016251520777586848}
+{"step": 39010, "dynamics_loss_avg": 0.027519177366048097}
+{"step": 39010, "action_loss_avg": 0.001959317555883899}
+{"step": 39020, "dynamics_loss_avg": 0.03782834932208061}
+{"step": 39020, "action_loss_avg": 0.00260096705169417}
+{"step": 39030, "dynamics_loss_avg": 0.02346269879490137}
+{"step": 39030, "action_loss_avg": 0.001599151943810284}
+{"step": 39040, "dynamics_loss_avg": 0.03297191532328725}
+{"step": 39040, "action_loss_avg": 0.0022370912542100997}
+{"step": 39050, "loss": 0.0308, "learning_rate": 7.151460995903624e-05}
+{"step": 39050, "dynamics_loss_avg": 0.03422185778617859}
+{"step": 39050, "action_loss_avg": 0.0024720526242163034}
+{"step": 39060, "dynamics_loss_avg": 0.03242050474509597}
+{"step": 39060, "action_loss_avg": 0.0021113961818628015}
+{"step": 39070, "dynamics_loss_avg": 0.03353689219802618}
+{"step": 39070, "action_loss_avg": 0.0027347253751941027}
+{"step": 39080, "dynamics_loss_avg": 0.021530287619680167}
+{"step": 39080, "action_loss_avg": 0.001676497934386134}
+{"step": 39090, "dynamics_loss_avg": 0.03239154196344316}
+{"step": 39090, "action_loss_avg": 0.002945224041468464}
+{"step": 39100, "loss": 0.0329, "learning_rate": 7.143995207755517e-05}
+{"step": 39100, "dynamics_loss_avg": 0.03512070034630597}
+{"step": 39100, "action_loss_avg": 0.002624541157274507}
+{"step": 39110, "dynamics_loss_avg": 0.03080836432054639}
+{"step": 39110, "action_loss_avg": 0.0023197940608952194}
+{"step": 39120, "dynamics_loss_avg": 0.030250664427876474}
+{"step": 39120, "action_loss_avg": 0.002280111762229353}
+{"step": 39130, "dynamics_loss_avg": 0.03397632790729403}
+{"step": 39130, "action_loss_avg": 0.002461309969658032}
+{"step": 39140, "dynamics_loss_avg": 0.029406259348616005}
+{"step": 39140, "action_loss_avg": 0.0018769181857351213}
+{"step": 39150, "loss": 0.0323, "learning_rate": 7.13652355800638e-05}
+{"step": 39150, "dynamics_loss_avg": 0.022594897262752055}
+{"step": 39150, "action_loss_avg": 0.0015783314069267363}
+{"step": 39160, "dynamics_loss_avg": 0.020471085095778108}
+{"step": 39160, "action_loss_avg": 0.0018048365251161157}
+{"step": 39170, "dynamics_loss_avg": 0.0380221426486969}
+{"step": 39170, "action_loss_avg": 0.003015785978641361}
+{"step": 39180, "dynamics_loss_avg": 0.03574844691902399}
+{"step": 39180, "action_loss_avg": 0.0026732525671832263}
+{"step": 39190, "dynamics_loss_avg": 0.025427510030567646}
+{"step": 39190, "action_loss_avg": 0.0017170837963931262}
+{"step": 39200, "loss": 0.0303, "learning_rate": 7.12904606708342e-05}
+{"step": 39200, "dynamics_loss_avg": 0.025768333114683628}
+{"step": 39200, "action_loss_avg": 0.0024273842573165894}
+{"step": 39210, "dynamics_loss_avg": 0.025822540558874608}
+{"step": 39210, "action_loss_avg": 0.002157894108677283}
+{"step": 39220, "dynamics_loss_avg": 0.035042524617165324}
+{"step": 39220, "action_loss_avg": 0.0026127830380573867}
+{"step": 39230, "dynamics_loss_avg": 0.03070351146161556}
+{"step": 39230, "action_loss_avg": 0.002466586508671753}
+{"step": 39240, "dynamics_loss_avg": 0.03197469003498554}
+{"step": 39240, "action_loss_avg": 0.0027661478845402597}
+{"step": 39250, "loss": 0.0304, "learning_rate": 7.121562755429807e-05}
+{"step": 39250, "dynamics_loss_avg": 0.02871410744264722}
+{"step": 39250, "action_loss_avg": 0.0020175335579551757}
+{"step": 39260, "dynamics_loss_avg": 0.027870708703994752}
+{"step": 39260, "action_loss_avg": 0.001893410342745483}
+{"step": 39270, "dynamics_loss_avg": 0.029927604459226133}
+{"step": 39270, "action_loss_avg": 0.0020591285545378925}
+{"step": 39280, "dynamics_loss_avg": 0.0316429303959012}
+{"step": 39280, "action_loss_avg": 0.002049132093088701}
+{"step": 39290, "dynamics_loss_avg": 0.020999759202823043}
+{"step": 39290, "action_loss_avg": 0.0015867716370848938}
+{"step": 39300, "loss": 0.0346, "learning_rate": 7.114073643504635e-05}
+{"step": 39300, "dynamics_loss_avg": 0.023324800375849008}
+{"step": 39300, "action_loss_avg": 0.0013765774259809405}
+{"step": 39310, "dynamics_loss_avg": 0.027630349947139622}
+{"step": 39310, "action_loss_avg": 0.002318204537732527}
+{"step": 39320, "dynamics_loss_avg": 0.02888588421046734}
+{"step": 39320, "action_loss_avg": 0.0016714220633730291}
+{"step": 39330, "dynamics_loss_avg": 0.028748121950775384}
+{"step": 39330, "action_loss_avg": 0.002026354891131632}
+{"step": 39340, "dynamics_loss_avg": 0.02235384830273688}
+{"step": 39340, "action_loss_avg": 0.0015071500500198453}
+{"step": 39350, "loss": 0.0284, "learning_rate": 7.106578751782847e-05}
+{"step": 39350, "dynamics_loss_avg": 0.025692834192886947}
+{"step": 39350, "action_loss_avg": 0.002423102845204994}
+{"step": 39360, "dynamics_loss_avg": 0.031824857275933024}
+{"step": 39360, "action_loss_avg": 0.002678963134530932}
+{"step": 39370, "dynamics_loss_avg": 0.03257622122764588}
+{"step": 39370, "action_loss_avg": 0.002648427471285686}
+{"step": 39380, "dynamics_loss_avg": 0.02913713827729225}
+{"step": 39380, "action_loss_avg": 0.0021095948992297052}
+{"step": 39390, "dynamics_loss_avg": 0.02680628830567002}
+{"step": 39390, "action_loss_avg": 0.0018565863720141351}
+{"step": 39400, "loss": 0.0329, "learning_rate": 7.09907810075519e-05}
+{"step": 39400, "dynamics_loss_avg": 0.036121001653373244}
+{"step": 39400, "action_loss_avg": 0.002036601334111765}
+{"step": 39410, "dynamics_loss_avg": 0.03307637539692223}
+{"step": 39410, "action_loss_avg": 0.0022899704170413317}
+{"step": 39420, "dynamics_loss_avg": 0.02363115190528333}
+{"step": 39420, "action_loss_avg": 0.001742476230720058}
+{"step": 39430, "dynamics_loss_avg": 0.034757102467119695}
+{"step": 39430, "action_loss_avg": 0.002926408115308732}
+{"step": 39440, "dynamics_loss_avg": 0.039758076798170804}
+{"step": 39440, "action_loss_avg": 0.0032167133409529924}
+{"step": 39450, "loss": 0.0327, "learning_rate": 7.09157171092816e-05}
+{"step": 39450, "dynamics_loss_avg": 0.034936237055808304}
+{"step": 39450, "action_loss_avg": 0.002692510443739593}
+{"step": 39460, "dynamics_loss_avg": 0.03284676633775234}
+{"step": 39460, "action_loss_avg": 0.00227681371034123}
+{"step": 39470, "dynamics_loss_avg": 0.034279315080493686}
+{"step": 39470, "action_loss_avg": 0.0028376369853504004}
+{"step": 39480, "dynamics_loss_avg": 0.025903784763067962}
+{"step": 39480, "action_loss_avg": 0.0022289642482064666}
+{"step": 39490, "dynamics_loss_avg": 0.043379973992705344}
+{"step": 39490, "action_loss_avg": 0.0031436297809705137}
+{"step": 39500, "loss": 0.0373, "learning_rate": 7.084059602823937e-05}
+{"step": 39500, "dynamics_loss_avg": 0.0354763675481081}
+{"step": 39500, "action_loss_avg": 0.0028176136896945537}
+{"step": 39510, "dynamics_loss_avg": 0.036558893695473674}
+{"step": 39510, "action_loss_avg": 0.0021899768966250122}
+{"step": 39520, "dynamics_loss_avg": 0.023648171871900558}
+{"step": 39520, "action_loss_avg": 0.0017009385570418089}
+{"step": 39530, "dynamics_loss_avg": 0.025826860405504703}
+{"step": 39530, "action_loss_avg": 0.0022366711986251176}
+{"step": 39540, "dynamics_loss_avg": 0.03282509557902813}
+{"step": 39540, "action_loss_avg": 0.002491396138793789}
+{"step": 39550, "loss": 0.0318, "learning_rate": 7.07654179698034e-05}
+{"step": 39550, "dynamics_loss_avg": 0.022190316952764987}
+{"step": 39550, "action_loss_avg": 0.001768350158818066}
+{"step": 39560, "dynamics_loss_avg": 0.02828837875276804}
+{"step": 39560, "action_loss_avg": 0.0029440745594911276}
+{"step": 39570, "dynamics_loss_avg": 0.042066512443125245}
+{"step": 39570, "action_loss_avg": 0.003056243777973577}
+{"step": 39580, "dynamics_loss_avg": 0.026013063825666906}
+{"step": 39580, "action_loss_avg": 0.0014114149613305925}
+{"step": 39590, "dynamics_loss_avg": 0.030801620241254567}
+{"step": 39590, "action_loss_avg": 0.002564337314106524}
+{"step": 39600, "loss": 0.0312, "learning_rate": 7.069018313950763e-05}
+{"step": 39600, "dynamics_loss_avg": 0.016968448646366596}
+{"step": 39600, "action_loss_avg": 0.001078360494284425}
+{"step": 39610, "dynamics_loss_avg": 0.027817367855459452}
+{"step": 39610, "action_loss_avg": 0.001790530764264986}
+{"step": 39620, "dynamics_loss_avg": 0.029369560442864893}
+{"step": 39620, "action_loss_avg": 0.0015543727204203606}
+{"step": 39630, "dynamics_loss_avg": 0.030340043269097804}
+{"step": 39630, "action_loss_avg": 0.0025449735810980203}
+{"step": 39640, "dynamics_loss_avg": 0.01927635851316154}
+{"step": 39640, "action_loss_avg": 0.001464117071009241}
+{"step": 39650, "loss": 0.0291, "learning_rate": 7.061489174304121e-05}
+{"step": 39650, "dynamics_loss_avg": 0.0332660005427897}
+{"step": 39650, "action_loss_avg": 0.0029351753531955183}
+{"step": 39660, "dynamics_loss_avg": 0.027887523453682662}
+{"step": 39660, "action_loss_avg": 0.0024549654161091896}
+{"step": 39670, "dynamics_loss_avg": 0.034661118686199185}
+{"step": 39670, "action_loss_avg": 0.0019689200853463262}
+{"step": 39680, "dynamics_loss_avg": 0.02209284184500575}
+{"step": 39680, "action_loss_avg": 0.0020835433970205486}
+{"step": 39690, "dynamics_loss_avg": 0.030386875849217176}
+{"step": 39690, "action_loss_avg": 0.0019530834862962366}
+{"step": 39700, "loss": 0.031, "learning_rate": 7.053954398624794e-05}
+{"step": 39700, "dynamics_loss_avg": 0.03425018833950162}
+{"step": 39700, "action_loss_avg": 0.001977310422807932}
+{"step": 39710, "dynamics_loss_avg": 0.030620906222611665}
+{"step": 39710, "action_loss_avg": 0.0024636892834678293}
+{"step": 39720, "dynamics_loss_avg": 0.02573546152561903}
+{"step": 39720, "action_loss_avg": 0.0018447513284627348}
+{"step": 39730, "dynamics_loss_avg": 0.02788738515228033}
+{"step": 39730, "action_loss_avg": 0.0019698837655596434}
+{"step": 39740, "dynamics_loss_avg": 0.02252825452014804}
+{"step": 39740, "action_loss_avg": 0.001977205439470708}
+{"step": 39750, "loss": 0.0301, "learning_rate": 7.046414007512571e-05}
+{"step": 39750, "dynamics_loss_avg": 0.028664782643318176}
+{"step": 39750, "action_loss_avg": 0.0019134759146254509}
+{"step": 39760, "dynamics_loss_avg": 0.029443877190351485}
+{"step": 39760, "action_loss_avg": 0.002121987717691809}
+{"step": 39770, "dynamics_loss_avg": 0.032044168654829265}
+{"step": 39770, "action_loss_avg": 0.001849739416502416}
+{"step": 39780, "dynamics_loss_avg": 0.03245972227305174}
+{"step": 39780, "action_loss_avg": 0.002396206010598689}
+{"step": 39790, "dynamics_loss_avg": 0.02986074211075902}
+{"step": 39790, "action_loss_avg": 0.0018748229369521141}
+{"step": 39800, "loss": 0.0325, "learning_rate": 7.038868021582594e-05}
+{"step": 39800, "dynamics_loss_avg": 0.03107187794521451}
+{"step": 39800, "action_loss_avg": 0.001819558721035719}
+{"step": 39810, "dynamics_loss_avg": 0.032024689763784406}
+{"step": 39810, "action_loss_avg": 0.0018830777029506863}
+{"step": 39820, "dynamics_loss_avg": 0.029051877558231354}
+{"step": 39820, "action_loss_avg": 0.0015496029402129353}
+{"step": 39830, "dynamics_loss_avg": 0.028940398804843427}
+{"step": 39830, "action_loss_avg": 0.002006384322885424}
+{"step": 39840, "dynamics_loss_avg": 0.03959255563095212}
+{"step": 39840, "action_loss_avg": 0.002465038577793166}
+{"step": 39850, "loss": 0.0314, "learning_rate": 7.031316461465302e-05}
+{"step": 39850, "dynamics_loss_avg": 0.026568584702908994}
+{"step": 39850, "action_loss_avg": 0.0023106147535145284}
+{"step": 39860, "dynamics_loss_avg": 0.021101532969623804}
+{"step": 39860, "action_loss_avg": 0.0014668511168565602}
+{"step": 39870, "dynamics_loss_avg": 0.027310297824442387}
+{"step": 39870, "action_loss_avg": 0.0017230392433702946}
+{"step": 39880, "dynamics_loss_avg": 0.02328351903706789}
+{"step": 39880, "action_loss_avg": 0.0017756070068571717}
+{"step": 39890, "dynamics_loss_avg": 0.038617128506302834}
+{"step": 39890, "action_loss_avg": 0.0024168483330868186}
+{"step": 39900, "loss": 0.0306, "learning_rate": 7.023759347806366e-05}
+{"step": 39900, "dynamics_loss_avg": 0.035037494357675315}
+{"step": 39900, "action_loss_avg": 0.0019969796121586114}
+{"step": 39910, "dynamics_loss_avg": 0.029176918882876636}
+{"step": 39910, "action_loss_avg": 0.0020768642716575414}
+{"step": 39920, "dynamics_loss_avg": 0.033804013812914493}
+{"step": 39920, "action_loss_avg": 0.0025708176399348304}
+{"step": 39930, "dynamics_loss_avg": 0.03528977204114199}
+{"step": 39930, "action_loss_avg": 0.0019269063137471675}
+{"step": 39940, "dynamics_loss_avg": 0.02509358450770378}
+{"step": 39940, "action_loss_avg": 0.0019692099594976753}
+{"step": 39950, "loss": 0.0337, "learning_rate": 7.016196701266652e-05}
+{"step": 39950, "dynamics_loss_avg": 0.040155944786965846}
+{"step": 39950, "action_loss_avg": 0.0031564158678520473}
+{"step": 39960, "dynamics_loss_avg": 0.03393818084150553}
+{"step": 39960, "action_loss_avg": 0.002943175006657839}
+{"step": 39970, "dynamics_loss_avg": 0.023691251873970032}
+{"step": 39970, "action_loss_avg": 0.0014717555575771257}
+{"step": 39980, "dynamics_loss_avg": 0.03141043307259679}
+{"step": 39980, "action_loss_avg": 0.001975868083536625}
+{"step": 39990, "dynamics_loss_avg": 0.03038095636293292}
+{"step": 39990, "action_loss_avg": 0.0019549365126295013}
+{"step": 40000, "loss": 0.03, "learning_rate": 7.008628542522147e-05}
+{"step": 40000, "dynamics_loss_avg": 0.029942812211811543}
+{"step": 40000, "action_loss_avg": 0.0016610489197773858}
+{"step": 40010, "dynamics_loss_avg": 0.031740144174546}
+{"step": 40010, "action_loss_avg": 0.0025447406515013427}
+{"step": 40020, "dynamics_loss_avg": 0.02787829553708434}
+{"step": 40020, "action_loss_avg": 0.002558243309613317}
+{"step": 40030, "dynamics_loss_avg": 0.031973663810640575}
+{"step": 40030, "action_loss_avg": 0.003132243931759149}
+{"step": 40040, "dynamics_loss_avg": 0.03162045693024993}
+{"step": 40040, "action_loss_avg": 0.0025251347688026726}
+{"step": 40050, "loss": 0.0322, "learning_rate": 7.001054892263903e-05}
+{"step": 40050, "dynamics_loss_avg": 0.027200277848169207}
+{"step": 40050, "action_loss_avg": 0.002015991837834008}
+{"step": 40060, "dynamics_loss_avg": 0.029320785589516164}
+{"step": 40060, "action_loss_avg": 0.0022985418851021676}
+{"step": 40070, "dynamics_loss_avg": 0.027261530235409736}
+{"step": 40070, "action_loss_avg": 0.002079051302280277}
+{"step": 40080, "dynamics_loss_avg": 0.028479477390646935}
+{"step": 40080, "action_loss_avg": 0.0016369701421353965}
+{"step": 40090, "dynamics_loss_avg": 0.021949460823088886}
+{"step": 40090, "action_loss_avg": 0.0013084936130326242}
+{"step": 40100, "loss": 0.0309, "learning_rate": 6.993475771197995e-05}
+{"step": 40100, "dynamics_loss_avg": 0.041281793359667064}
+{"step": 40100, "action_loss_avg": 0.003991969669004902}
+{"step": 40110, "dynamics_loss_avg": 0.028514710254967213}
+{"step": 40110, "action_loss_avg": 0.0025557250250130893}
+{"step": 40120, "dynamics_loss_avg": 0.027544503565877676}
+{"step": 40120, "action_loss_avg": 0.0025550741818733515}
+{"step": 40130, "dynamics_loss_avg": 0.02348724608309567}
+{"step": 40130, "action_loss_avg": 0.001924163370858878}
+{"step": 40140, "dynamics_loss_avg": 0.022612028010189533}
+{"step": 40140, "action_loss_avg": 0.002164501533843577}
+{"step": 40150, "loss": 0.0298, "learning_rate": 6.985891200045449e-05}
+{"step": 40150, "dynamics_loss_avg": 0.028494236804544926}
+{"step": 40150, "action_loss_avg": 0.002066221710992977}
+{"step": 40160, "dynamics_loss_avg": 0.023141510179266335}
+{"step": 40160, "action_loss_avg": 0.0019121291086776182}
+{"step": 40170, "dynamics_loss_avg": 0.03608528040349483}
+{"step": 40170, "action_loss_avg": 0.002950214268639684}
+{"step": 40180, "dynamics_loss_avg": 0.036071297340095045}
+{"step": 40180, "action_loss_avg": 0.002294210938271135}
+{"step": 40190, "dynamics_loss_avg": 0.03168384116142988}
+{"step": 40190, "action_loss_avg": 0.002704732120037079}
+{"step": 40200, "loss": 0.0354, "learning_rate": 6.978301199542193e-05}
+{"step": 40200, "dynamics_loss_avg": 0.03417248371988535}
+{"step": 40200, "action_loss_avg": 0.002912226121407002}
+{"step": 40210, "dynamics_loss_avg": 0.025151456985622645}
+{"step": 40210, "action_loss_avg": 0.0023199666349682955}
+{"step": 40220, "dynamics_loss_avg": 0.025346083799377084}
+{"step": 40220, "action_loss_avg": 0.0020979627792257816}
+{"step": 40230, "dynamics_loss_avg": 0.03546233410015702}
+{"step": 40230, "action_loss_avg": 0.0029856675828341395}
+{"step": 40240, "dynamics_loss_avg": 0.02274927911348641}
+{"step": 40240, "action_loss_avg": 0.0017238648870261386}
+{"step": 40250, "loss": 0.0311, "learning_rate": 6.970705790438998e-05}
+{"step": 40250, "dynamics_loss_avg": 0.03824104256927967}
+{"step": 40250, "action_loss_avg": 0.0033284408506006}
+{"step": 40260, "dynamics_loss_avg": 0.02807420352473855}
+{"step": 40260, "action_loss_avg": 0.002215622304356657}
+{"step": 40270, "dynamics_loss_avg": 0.024862431269139052}
+{"step": 40270, "action_loss_avg": 0.0017998993513174354}
+{"step": 40280, "dynamics_loss_avg": 0.030981309339404108}
+{"step": 40280, "action_loss_avg": 0.003271589963696897}
+{"step": 40290, "dynamics_loss_avg": 0.030684177577495576}
+{"step": 40290, "action_loss_avg": 0.0027198334224522113}
+{"step": 40300, "loss": 0.0329, "learning_rate": 6.963104993501425e-05}
+{"step": 40300, "dynamics_loss_avg": 0.033874735608696936}
+{"step": 40300, "action_loss_avg": 0.002370113367214799}
+{"step": 40310, "dynamics_loss_avg": 0.03455963246524334}
+{"step": 40310, "action_loss_avg": 0.001957944693276659}
+{"step": 40320, "dynamics_loss_avg": 0.03633531434461475}
+{"step": 40320, "action_loss_avg": 0.0029174676281400027}
+{"step": 40330, "dynamics_loss_avg": 0.03222028380259871}
+{"step": 40330, "action_loss_avg": 0.0021710074855946005}
+{"step": 40340, "dynamics_loss_avg": 0.028926205728203057}
+{"step": 40340, "action_loss_avg": 0.0029875585227273405}
+{"step": 40350, "loss": 0.035, "learning_rate": 6.95549882950976e-05}
+{"step": 40350, "dynamics_loss_avg": 0.029769782535731794}
+{"step": 40350, "action_loss_avg": 0.0027460489014629274}
+{"step": 40360, "dynamics_loss_avg": 0.027921461034566164}
+{"step": 40360, "action_loss_avg": 0.002168445198913105}
+{"step": 40370, "dynamics_loss_avg": 0.03323327777907252}
+{"step": 40370, "action_loss_avg": 0.0028646354679949582}
+{"step": 40380, "dynamics_loss_avg": 0.021743241511285306}
+{"step": 40380, "action_loss_avg": 0.002040367864537984}
+{"step": 40390, "dynamics_loss_avg": 0.025000823382288217}
+{"step": 40390, "action_loss_avg": 0.001907571816991549}
+{"step": 40400, "loss": 0.0295, "learning_rate": 6.947887319258966e-05}
+{"step": 40400, "dynamics_loss_avg": 0.033883136324584485}
+{"step": 40400, "action_loss_avg": 0.0020121812005527316}
+{"step": 40410, "dynamics_loss_avg": 0.02844478553161025}
+{"step": 40410, "action_loss_avg": 0.002544071860029362}
+{"step": 40420, "dynamics_loss_avg": 0.025843761395663023}
+{"step": 40420, "action_loss_avg": 0.002224513265537098}
+{"step": 40430, "dynamics_loss_avg": 0.033139266259968284}
+{"step": 40430, "action_loss_avg": 0.0023395328200422226}
+{"step": 40440, "dynamics_loss_avg": 0.030282121151685715}
+{"step": 40440, "action_loss_avg": 0.0020896414353046566}
+{"step": 40450, "loss": 0.0329, "learning_rate": 6.94027048355862e-05}
+{"step": 40450, "dynamics_loss_avg": 0.04226202107965946}
+{"step": 40450, "action_loss_avg": 0.0034940399462357165}
+{"step": 40460, "dynamics_loss_avg": 0.0359227105975151}
+{"step": 40460, "action_loss_avg": 0.0028712551400531085}
+{"step": 40470, "dynamics_loss_avg": 0.031211927207186817}
+{"step": 40470, "action_loss_avg": 0.0015318028017645702}
+{"step": 40480, "dynamics_loss_avg": 0.022838421631604433}
+{"step": 40480, "action_loss_avg": 0.002269775641616434}
+{"step": 40490, "dynamics_loss_avg": 0.03129104217514396}
+{"step": 40490, "action_loss_avg": 0.0025206309393979607}
+{"step": 40500, "loss": 0.032, "learning_rate": 6.93264834323286e-05}
+{"step": 40500, "dynamics_loss_avg": 0.034117473755031824}
+{"step": 40500, "action_loss_avg": 0.0023563251830637454}
+{"step": 40510, "dynamics_loss_avg": 0.024504298996180295}
+{"step": 40510, "action_loss_avg": 0.002468638529535383}
+{"step": 40520, "dynamics_loss_avg": 0.03627724498510361}
+{"step": 40520, "action_loss_avg": 0.003565019747475162}
+{"step": 40530, "dynamics_loss_avg": 0.028727479465305805}
+{"step": 40530, "action_loss_avg": 0.0018218949029687793}
+{"step": 40540, "dynamics_loss_avg": 0.02727271746844053}
+{"step": 40540, "action_loss_avg": 0.0020108137978240848}
+{"step": 40550, "loss": 0.0303, "learning_rate": 6.92502091912033e-05}
+{"step": 40550, "dynamics_loss_avg": 0.02640614830888808}
+{"step": 40550, "action_loss_avg": 0.002539243607316166}
+{"step": 40560, "dynamics_loss_avg": 0.025551610998809336}
+{"step": 40560, "action_loss_avg": 0.002179227682063356}
+{"step": 40570, "dynamics_loss_avg": 0.03487209966406226}
+{"step": 40570, "action_loss_avg": 0.003360160056035966}
+{"step": 40580, "dynamics_loss_avg": 0.027788393758237363}
+{"step": 40580, "action_loss_avg": 0.002236867172177881}
+{"step": 40590, "dynamics_loss_avg": 0.03172915084287524}
+{"step": 40590, "action_loss_avg": 0.0021284999151248486}
+{"step": 40600, "loss": 0.0306, "learning_rate": 6.917388232074114e-05}
+{"step": 40600, "dynamics_loss_avg": 0.027810738934203983}
+{"step": 40600, "action_loss_avg": 0.002785648507415317}
+{"step": 40610, "dynamics_loss_avg": 0.033032322814688084}
+{"step": 40610, "action_loss_avg": 0.002619323364342563}
+{"step": 40620, "dynamics_loss_avg": 0.029764914698898793}
+{"step": 40620, "action_loss_avg": 0.002461483352817595}
+{"step": 40630, "dynamics_loss_avg": 0.0251019855029881}
+{"step": 40630, "action_loss_avg": 0.0020982698304578664}
+{"step": 40640, "dynamics_loss_avg": 0.028327284287661313}
+{"step": 40640, "action_loss_avg": 0.002439063595375046}
+{"step": 40650, "loss": 0.0303, "learning_rate": 6.909750302961684e-05}
+{"step": 40650, "dynamics_loss_avg": 0.028269901825115084}
+{"step": 40650, "action_loss_avg": 0.0022997613734332843}
+{"step": 40660, "dynamics_loss_avg": 0.03042209753766656}
+{"step": 40660, "action_loss_avg": 0.0028805395413655788}
+{"step": 40670, "dynamics_loss_avg": 0.03518286375328898}
+{"step": 40670, "action_loss_avg": 0.002696902200113982}
+{"step": 40680, "dynamics_loss_avg": 0.027577419579029084}
+{"step": 40680, "action_loss_avg": 0.002268920070491731}
+{"step": 40690, "dynamics_loss_avg": 0.03786971541121602}
+{"step": 40690, "action_loss_avg": 0.003384685330092907}
+{"step": 40700, "loss": 0.0309, "learning_rate": 6.902107152664851e-05}
+{"step": 40700, "dynamics_loss_avg": 0.02814446510747075}
+{"step": 40700, "action_loss_avg": 0.0023918280843645335}
+{"step": 40710, "dynamics_loss_avg": 0.03372014220803976}
+{"step": 40710, "action_loss_avg": 0.0029586960445158184}
+{"step": 40720, "dynamics_loss_avg": 0.04140883516520262}
+{"step": 40720, "action_loss_avg": 0.0034504751150961966}
+{"step": 40730, "dynamics_loss_avg": 0.03178884480148554}
+{"step": 40730, "action_loss_avg": 0.0023111314920242878}
+{"step": 40740, "dynamics_loss_avg": 0.02300410782918334}
+{"step": 40740, "action_loss_avg": 0.0014751490409253166}
+{"step": 40750, "loss": 0.0338, "learning_rate": 6.894458802079694e-05}
+{"step": 40750, "dynamics_loss_avg": 0.03361468389630318}
+{"step": 40750, "action_loss_avg": 0.002990278508514166}
+{"step": 40760, "dynamics_loss_avg": 0.026701629534363745}
+{"step": 40760, "action_loss_avg": 0.0016845606558490544}
+{"step": 40770, "dynamics_loss_avg": 0.030127038434147834}
+{"step": 40770, "action_loss_avg": 0.0021543919923715294}
+{"step": 40780, "dynamics_loss_avg": 0.031695915199816224}
+{"step": 40780, "action_loss_avg": 0.0024812491377815605}
+{"step": 40790, "dynamics_loss_avg": 0.024126585153862835}
+{"step": 40790, "action_loss_avg": 0.0013382167147938163}
+{"step": 40800, "loss": 0.032, "learning_rate": 6.886805272116513e-05}
+{"step": 40800, "dynamics_loss_avg": 0.03085029365029186}
+{"step": 40800, "action_loss_avg": 0.002079453901387751}
+{"step": 40810, "dynamics_loss_avg": 0.02376464419066906}
+{"step": 40810, "action_loss_avg": 0.0016905234137084336}
+{"step": 40820, "dynamics_loss_avg": 0.030114178825169802}
+{"step": 40820, "action_loss_avg": 0.0026769026182591913}
+{"step": 40830, "dynamics_loss_avg": 0.025850246660411358}
+{"step": 40830, "action_loss_avg": 0.0016577912319917232}
+{"step": 40840, "dynamics_loss_avg": 0.033859254559502006}
+{"step": 40840, "action_loss_avg": 0.002927837264724076}
+{"step": 40850, "loss": 0.0302, "learning_rate": 6.879146583699765e-05}
+{"step": 40850, "dynamics_loss_avg": 0.029663752019405364}
+{"step": 40850, "action_loss_avg": 0.0023833524785004554}
+{"step": 40860, "dynamics_loss_avg": 0.03210288211703301}
+{"step": 40860, "action_loss_avg": 0.0025612608413212003}
+{"step": 40870, "dynamics_loss_avg": 0.028248030343092978}
+{"step": 40870, "action_loss_avg": 0.001936421191203408}
+{"step": 40880, "dynamics_loss_avg": 0.03215443803928793}
+{"step": 40880, "action_loss_avg": 0.003012418618891388}
+{"step": 40890, "dynamics_loss_avg": 0.036739370319992304}
+{"step": 40890, "action_loss_avg": 0.0023617755330633374}
+{"step": 40900, "loss": 0.0313, "learning_rate": 6.871482757768012e-05}
+{"step": 40900, "dynamics_loss_avg": 0.023486915836110712}
+{"step": 40900, "action_loss_avg": 0.0014663865615148098}
+{"step": 40910, "dynamics_loss_avg": 0.030673061963170767}
+{"step": 40910, "action_loss_avg": 0.001726614500512369}
+{"step": 40920, "dynamics_loss_avg": 0.03068467266857624}
+{"step": 40920, "action_loss_avg": 0.0024865363229764625}
+{"step": 40930, "dynamics_loss_avg": 0.02954517649486661}
+{"step": 40930, "action_loss_avg": 0.0018580939387902618}
+{"step": 40940, "dynamics_loss_avg": 0.02841779701411724}
+{"step": 40940, "action_loss_avg": 0.00180747474078089}
+{"step": 40950, "loss": 0.0336, "learning_rate": 6.86381381527386e-05}
+{"step": 40950, "dynamics_loss_avg": 0.03514348538592458}
+{"step": 40950, "action_loss_avg": 0.0022475981269963084}
+{"step": 40960, "dynamics_loss_avg": 0.0276684008538723}
+{"step": 40960, "action_loss_avg": 0.002256984740961343}
+{"step": 40970, "dynamics_loss_avg": 0.029574311338365078}
+{"step": 40970, "action_loss_avg": 0.002676445338875055}
+{"step": 40980, "dynamics_loss_avg": 0.031011230871081354}
+{"step": 40980, "action_loss_avg": 0.0026086854981258512}
+{"step": 40990, "dynamics_loss_avg": 0.035072367265820505}
+{"step": 40990, "action_loss_avg": 0.0026729413686553015}
+{"step": 41000, "loss": 0.0322, "learning_rate": 6.85613977718391e-05}
+{"step": 41000, "dynamics_loss_avg": 0.037380419299006463}
+{"step": 41000, "action_loss_avg": 0.002858257747720927}
+{"step": 41010, "dynamics_loss_avg": 0.034077949542552236}
+{"step": 41010, "action_loss_avg": 0.0027941627078689633}
+{"step": 41020, "dynamics_loss_avg": 0.024753717146813868}
+{"step": 41020, "action_loss_avg": 0.0017752845189534128}
+{"step": 41030, "dynamics_loss_avg": 0.03312416383996606}
+{"step": 41030, "action_loss_avg": 0.0025020150060299784}
+{"step": 41040, "dynamics_loss_avg": 0.035766570502892135}
+{"step": 41040, "action_loss_avg": 0.0034934416180476546}
+{"step": 41050, "loss": 0.0357, "learning_rate": 6.848460664478684e-05}
+{"step": 41050, "dynamics_loss_avg": 0.027940089255571364}
+{"step": 41050, "action_loss_avg": 0.0030733234656509013}
+{"step": 41060, "dynamics_loss_avg": 0.025692439544945954}
+{"step": 41060, "action_loss_avg": 0.0019524388830177487}
+{"step": 41070, "dynamics_loss_avg": 0.033019528817385436}
+{"step": 41070, "action_loss_avg": 0.0032169583340873943}
+{"step": 41080, "dynamics_loss_avg": 0.029292003344744445}
+{"step": 41080, "action_loss_avg": 0.0020529374756733886}
+{"step": 41090, "dynamics_loss_avg": 0.021336817182600498}
+{"step": 41090, "action_loss_avg": 0.001721567678032443}
+{"step": 41100, "loss": 0.0305, "learning_rate": 6.840776498152584e-05}
+{"step": 41100, "dynamics_loss_avg": 0.03125989306718111}
+{"step": 41100, "action_loss_avg": 0.002355292270658538}
+{"step": 41110, "dynamics_loss_avg": 0.025205754674971104}
+{"step": 41110, "action_loss_avg": 0.0017954850220121444}
+{"step": 41120, "dynamics_loss_avg": 0.03392413100227713}
+{"step": 41120, "action_loss_avg": 0.0019932828901801257}
+{"step": 41130, "dynamics_loss_avg": 0.026154414052143693}
+{"step": 41130, "action_loss_avg": 0.002171990048373118}
+{"step": 41140, "dynamics_loss_avg": 0.03494001468643546}
+{"step": 41140, "action_loss_avg": 0.002695146860787645}
+{"step": 41150, "loss": 0.0322, "learning_rate": 6.833087299213829e-05}
+{"step": 41150, "dynamics_loss_avg": 0.02966462024487555}
+{"step": 41150, "action_loss_avg": 0.0026222686166875063}
+{"step": 41160, "dynamics_loss_avg": 0.02486538579687476}
+{"step": 41160, "action_loss_avg": 0.0016865846526343375}
+{"step": 41170, "dynamics_loss_avg": 0.033150567952543494}
+{"step": 41170, "action_loss_avg": 0.0025346038688439875}
+{"step": 41180, "dynamics_loss_avg": 0.03172991443425417}
+{"step": 41180, "action_loss_avg": 0.0022565639344975354}
+{"step": 41190, "dynamics_loss_avg": 0.02353691589087248}
+{"step": 41190, "action_loss_avg": 0.0014721361279953272}
+{"step": 41200, "loss": 0.0289, "learning_rate": 6.825393088684393e-05}
+{"step": 41200, "dynamics_loss_avg": 0.02661406621336937}
+{"step": 41200, "action_loss_avg": 0.001685925293713808}
+{"step": 41210, "dynamics_loss_avg": 0.02358994632959366}
+{"step": 41210, "action_loss_avg": 0.0014999064209405334}
+{"step": 41220, "dynamics_loss_avg": 0.0333556953817606}
+{"step": 41220, "action_loss_avg": 0.0025520052062347532}
+{"step": 41230, "dynamics_loss_avg": 0.033253414742648604}
+{"step": 41230, "action_loss_avg": 0.0021690122957807034}
+{"step": 41240, "dynamics_loss_avg": 0.03228994207456708}
+{"step": 41240, "action_loss_avg": 0.0028093169734347613}
+{"step": 41250, "loss": 0.0314, "learning_rate": 6.817693887599956e-05}
+{"step": 41250, "dynamics_loss_avg": 0.028868219628930093}
+{"step": 41250, "action_loss_avg": 0.0025152105838060377}
+{"step": 41260, "dynamics_loss_avg": 0.029376299818977714}
+{"step": 41260, "action_loss_avg": 0.0029872387705836443}
+{"step": 41270, "dynamics_loss_avg": 0.029443826247006654}
+{"step": 41270, "action_loss_avg": 0.0021955523639917373}
+{"step": 41280, "dynamics_loss_avg": 0.04097948931157589}
+{"step": 41280, "action_loss_avg": 0.0030133545282296837}
+{"step": 41290, "dynamics_loss_avg": 0.03466687705367803}
+{"step": 41290, "action_loss_avg": 0.0031615806336048992}
+{"step": 41300, "loss": 0.0347, "learning_rate": 6.809989717009839e-05}
+{"step": 41300, "dynamics_loss_avg": 0.025487521756440402}
+{"step": 41300, "action_loss_avg": 0.0019178749003913253}
+{"step": 41310, "dynamics_loss_avg": 0.03643752248026431}
+{"step": 41310, "action_loss_avg": 0.0029854782857000827}
+{"step": 41320, "dynamics_loss_avg": 0.028283851500600577}
+{"step": 41320, "action_loss_avg": 0.0019462638127151876}
+{"step": 41330, "dynamics_loss_avg": 0.033459519408643244}
+{"step": 41330, "action_loss_avg": 0.0026757228362839667}
+{"step": 41340, "dynamics_loss_avg": 0.031462193839251994}
+{"step": 41340, "action_loss_avg": 0.002047474286518991}
+{"step": 41350, "loss": 0.0323, "learning_rate": 6.802280597976949e-05}
+{"step": 41350, "dynamics_loss_avg": 0.019802534859627484}
+{"step": 41350, "action_loss_avg": 0.0018303669290617107}
+{"step": 41360, "dynamics_loss_avg": 0.03154317974112928}
+{"step": 41360, "action_loss_avg": 0.0025675575569039212}
+{"step": 41370, "dynamics_loss_avg": 0.03200683193281293}
+{"step": 41370, "action_loss_avg": 0.002514224927290343}
+{"step": 41380, "dynamics_loss_avg": 0.024678287748247384}
+{"step": 41380, "action_loss_avg": 0.0019230824895203114}
+{"step": 41390, "dynamics_loss_avg": 0.034397728927433494}
+{"step": 41390, "action_loss_avg": 0.002969961753115058}
+{"step": 41400, "loss": 0.0335, "learning_rate": 6.794566551577724e-05}
+{"step": 41400, "dynamics_loss_avg": 0.035964589565992355}
+{"step": 41400, "action_loss_avg": 0.00293309073895216}
+{"step": 41410, "dynamics_loss_avg": 0.034400084614753725}
+{"step": 41410, "action_loss_avg": 0.002380226121749729}
+{"step": 41420, "dynamics_loss_avg": 0.027693954482674598}
+{"step": 41420, "action_loss_avg": 0.0023766612750478087}
+{"step": 41430, "dynamics_loss_avg": 0.04066754635423422}
+{"step": 41430, "action_loss_avg": 0.003994283976498991}
+{"step": 41440, "dynamics_loss_avg": 0.030559994094073773}
+{"step": 41440, "action_loss_avg": 0.0029353683930821717}
+{"step": 41450, "loss": 0.034, "learning_rate": 6.786847598902072e-05}
+{"step": 41450, "dynamics_loss_avg": 0.036085971258580686}
+{"step": 41450, "action_loss_avg": 0.0038186595076695083}
+{"step": 41460, "dynamics_loss_avg": 0.037957677710801364}
+{"step": 41460, "action_loss_avg": 0.0037755646859295665}
+{"step": 41470, "dynamics_loss_avg": 0.02739944774657488}
+{"step": 41470, "action_loss_avg": 0.0020217965240590273}
+{"step": 41480, "dynamics_loss_avg": 0.03417164850980044}
+{"step": 41480, "action_loss_avg": 0.002949116553645581}
+{"step": 41490, "dynamics_loss_avg": 0.027245652209967375}
+{"step": 41490, "action_loss_avg": 0.0018792860850226135}
+{"step": 41500, "loss": 0.0316, "learning_rate": 6.779123761053317e-05}
+{"step": 41500, "dynamics_loss_avg": 0.024305428192019463}
+{"step": 41500, "action_loss_avg": 0.001623938197735697}
+{"step": 41510, "dynamics_loss_avg": 0.022990871174260973}
+{"step": 41510, "action_loss_avg": 0.0015428276179591193}
+{"step": 41520, "dynamics_loss_avg": 0.030675786919891833}
+{"step": 41520, "action_loss_avg": 0.002401015174109489}
+{"step": 41530, "dynamics_loss_avg": 0.03318981379270554}
+{"step": 41530, "action_loss_avg": 0.002816090133273974}
+{"step": 41540, "dynamics_loss_avg": 0.02977907769382}
+{"step": 41540, "action_loss_avg": 0.002369630697648972}
+{"step": 41550, "loss": 0.0314, "learning_rate": 6.771395059148134e-05}
+{"step": 41550, "dynamics_loss_avg": 0.03669546954333782}
+{"step": 41550, "action_loss_avg": 0.0021206659148447216}
+{"step": 41560, "dynamics_loss_avg": 0.03343623499386013}
+{"step": 41560, "action_loss_avg": 0.002488203241955489}
+{"step": 41570, "dynamics_loss_avg": 0.028536824230104684}
+{"step": 41570, "action_loss_avg": 0.0021295554586686196}
+{"step": 41580, "dynamics_loss_avg": 0.026297135278582573}
+{"step": 41580, "action_loss_avg": 0.0014872486382955686}
+{"step": 41590, "dynamics_loss_avg": 0.026460770098492504}
+{"step": 41590, "action_loss_avg": 0.0017686292121652514}
+{"step": 41600, "loss": 0.0326, "learning_rate": 6.763661514316499e-05}
+{"step": 41600, "dynamics_loss_avg": 0.03053345615044236}
+{"step": 41600, "action_loss_avg": 0.002109242929145694}
+{"step": 41610, "dynamics_loss_avg": 0.03729603532701731}
+{"step": 41610, "action_loss_avg": 0.002381327806506306}
+{"step": 41620, "dynamics_loss_avg": 0.031052571069449187}
+{"step": 41620, "action_loss_avg": 0.002805251986137591}
+{"step": 41630, "dynamics_loss_avg": 0.034835619106888774}
+{"step": 41630, "action_loss_avg": 0.00284741468494758}
+{"step": 41640, "dynamics_loss_avg": 0.0309238126501441}
+{"step": 41640, "action_loss_avg": 0.0021491726627573373}
+{"step": 41650, "loss": 0.0323, "learning_rate": 6.75592314770163e-05}
+{"step": 41650, "dynamics_loss_avg": 0.02461367561481893}
+{"step": 41650, "action_loss_avg": 0.0017999475850956515}
+{"step": 41660, "dynamics_loss_avg": 0.02778958426788449}
+{"step": 41660, "action_loss_avg": 0.001904799573821947}
+{"step": 41670, "dynamics_loss_avg": 0.025641832128167154}
+{"step": 41670, "action_loss_avg": 0.0015647767286282033}
+{"step": 41680, "dynamics_loss_avg": 0.02614136002957821}
+{"step": 41680, "action_loss_avg": 0.0020225091255269946}
+{"step": 41690, "dynamics_loss_avg": 0.02821946134790778}
+{"step": 41690, "action_loss_avg": 0.0022880626085679976}
+{"step": 41700, "loss": 0.0288, "learning_rate": 6.748179980459924e-05}
+{"step": 41700, "dynamics_loss_avg": 0.026979747600853442}
+{"step": 41700, "action_loss_avg": 0.0019287813222035766}
+{"step": 41710, "dynamics_loss_avg": 0.030615625623613595}
+{"step": 41710, "action_loss_avg": 0.001932975312229246}
+{"step": 41720, "dynamics_loss_avg": 0.024895171727985145}
+{"step": 41720, "action_loss_avg": 0.0014195495867170393}
+{"step": 41730, "dynamics_loss_avg": 0.03703737612813711}
+{"step": 41730, "action_loss_avg": 0.002670324023347348}
+{"step": 41740, "dynamics_loss_avg": 0.040755401458591224}
+{"step": 41740, "action_loss_avg": 0.0034775962471030653}
+{"step": 41750, "loss": 0.0316, "learning_rate": 6.740432033760907e-05}
+{"step": 41750, "dynamics_loss_avg": 0.02394952466711402}
+{"step": 41750, "action_loss_avg": 0.0017308331065578387}
+{"step": 41760, "dynamics_loss_avg": 0.030029228515923025}
+{"step": 41760, "action_loss_avg": 0.0024224378721555695}
+{"step": 41770, "dynamics_loss_avg": 0.030118029098957777}
+{"step": 41770, "action_loss_avg": 0.002114532527048141}
+{"step": 41780, "dynamics_loss_avg": 0.032357413740828636}
+{"step": 41780, "action_loss_avg": 0.002450960880378261}
+{"step": 41790, "dynamics_loss_avg": 0.03135566329583526}
+{"step": 41790, "action_loss_avg": 0.0026760431355796754}
+{"step": 41800, "loss": 0.032, "learning_rate": 6.732679328787168e-05}
+{"step": 41800, "dynamics_loss_avg": 0.026939203171059488}
+{"step": 41800, "action_loss_avg": 0.0020631786959711463}
+{"step": 41810, "dynamics_loss_avg": 0.04316570144146681}
+{"step": 41810, "action_loss_avg": 0.0031363536487333476}
+{"step": 41820, "dynamics_loss_avg": 0.02003201860934496}
+{"step": 41820, "action_loss_avg": 0.0014402505184989423}
+{"step": 41830, "dynamics_loss_avg": 0.027650811639614404}
+{"step": 41830, "action_loss_avg": 0.001787040213821456}
+{"step": 41840, "dynamics_loss_avg": 0.034129415173083544}
+{"step": 41840, "action_loss_avg": 0.0032780729117803274}
+{"step": 41850, "loss": 0.0341, "learning_rate": 6.724921886734305e-05}
+{"step": 41850, "dynamics_loss_avg": 0.02773540373891592}
+{"step": 41850, "action_loss_avg": 0.0018040838884189724}
+{"step": 41860, "dynamics_loss_avg": 0.036395139340311286}
+{"step": 41860, "action_loss_avg": 0.0034764195559546353}
+{"step": 41870, "dynamics_loss_avg": 0.03454082915559411}
+{"step": 41870, "action_loss_avg": 0.0026123133953660726}
+{"step": 41880, "dynamics_loss_avg": 0.02781744918320328}
+{"step": 41880, "action_loss_avg": 0.0026299600925995038}
+{"step": 41890, "dynamics_loss_avg": 0.022537758434191348}
+{"step": 41890, "action_loss_avg": 0.0020240369914972687}
+{"step": 41900, "loss": 0.0322, "learning_rate": 6.71715972881087e-05}
+{"step": 41900, "dynamics_loss_avg": 0.030225861910730602}
+{"step": 41900, "action_loss_avg": 0.0019802734110271557}
+{"step": 41910, "dynamics_loss_avg": 0.027378623280674218}
+{"step": 41910, "action_loss_avg": 0.002255465294001624}
+{"step": 41920, "dynamics_loss_avg": 0.032053332217037676}
+{"step": 41920, "action_loss_avg": 0.003317110042553395}
+{"step": 41930, "dynamics_loss_avg": 0.031047170888632535}
+{"step": 41930, "action_loss_avg": 0.0027332906029187143}
+{"step": 41940, "dynamics_loss_avg": 0.026917429734021427}
+{"step": 41940, "action_loss_avg": 0.0016012591600883751}
+{"step": 41950, "loss": 0.0304, "learning_rate": 6.709392876238307e-05}
+{"step": 41950, "dynamics_loss_avg": 0.030786975845694543}
+{"step": 41950, "action_loss_avg": 0.0020482261606957763}
+{"step": 41960, "dynamics_loss_avg": 0.03400934133678675}
+{"step": 41960, "action_loss_avg": 0.003138832253171131}
+{"step": 41970, "dynamics_loss_avg": 0.03197711147367954}
+{"step": 41970, "action_loss_avg": 0.0021290000237058847}
+{"step": 41980, "dynamics_loss_avg": 0.029930344596505166}
+{"step": 41980, "action_loss_avg": 0.0023605750495335085}
+{"step": 41990, "dynamics_loss_avg": 0.04081691424362362}
+{"step": 41990, "action_loss_avg": 0.0024170950113330037}
+{"step": 42000, "loss": 0.0317, "learning_rate": 6.701621350250892e-05}
+{"step": 42000, "dynamics_loss_avg": 0.026621239259839058}
+{"step": 42000, "action_loss_avg": 0.002400905080139637}
+{"step": 42010, "dynamics_loss_avg": 0.026615146640688182}
+{"step": 42010, "action_loss_avg": 0.0014283853233791888}
+{"step": 42020, "dynamics_loss_avg": 0.029088824149221183}
+{"step": 42020, "action_loss_avg": 0.002144422405399382}
+{"step": 42030, "dynamics_loss_avg": 0.025762462988495827}
+{"step": 42030, "action_loss_avg": 0.0014055106323212386}
+{"step": 42040, "dynamics_loss_avg": 0.03325787391513586}
+{"step": 42040, "action_loss_avg": 0.0025466227263677864}
+{"step": 42050, "loss": 0.031, "learning_rate": 6.693845172095683e-05}
+{"step": 42050, "dynamics_loss_avg": 0.029342773463577033}
+{"step": 42050, "action_loss_avg": 0.0018250991823151707}
+{"step": 42060, "dynamics_loss_avg": 0.020385470427572727}
+{"step": 42060, "action_loss_avg": 0.0022972580802161245}
+{"step": 42070, "dynamics_loss_avg": 0.04557338645681739}
+{"step": 42070, "action_loss_avg": 0.0027787752100266517}
+{"step": 42080, "dynamics_loss_avg": 0.03647134294733405}
+{"step": 42080, "action_loss_avg": 0.003659473330480978}
+{"step": 42090, "dynamics_loss_avg": 0.030348327197134494}
+{"step": 42090, "action_loss_avg": 0.002556519734207541}
+{"step": 42100, "loss": 0.0338, "learning_rate": 6.686064363032451e-05}
+{"step": 42100, "dynamics_loss_avg": 0.023589204391464592}
+{"step": 42100, "action_loss_avg": 0.002001175354234874}
+{"step": 42110, "dynamics_loss_avg": 0.031049647135660052}
+{"step": 42110, "action_loss_avg": 0.0016809584951261059}
+{"step": 42120, "dynamics_loss_avg": 0.02671732138842344}
+{"step": 42120, "action_loss_avg": 0.0022991220437688755}
+{"step": 42130, "dynamics_loss_avg": 0.030851264111697675}
+{"step": 42130, "action_loss_avg": 0.0020063890260644257}
+{"step": 42140, "dynamics_loss_avg": 0.03188589233905077}
+{"step": 42140, "action_loss_avg": 0.002437858533812687}
+{"step": 42150, "loss": 0.0289, "learning_rate": 6.678278944333633e-05}
+{"step": 42150, "dynamics_loss_avg": 0.02724064067006111}
+{"step": 42150, "action_loss_avg": 0.0021852912614122033}
+{"step": 42160, "dynamics_loss_avg": 0.03486199481412768}
+{"step": 42160, "action_loss_avg": 0.0020789761969354005}
+{"step": 42170, "dynamics_loss_avg": 0.0317252797074616}
+{"step": 42170, "action_loss_avg": 0.0026239709986839443}
+{"step": 42180, "dynamics_loss_avg": 0.02518515894189477}
+{"step": 42180, "action_loss_avg": 0.0018814935814589263}
+{"step": 42190, "dynamics_loss_avg": 0.026060756016522645}
+{"step": 42190, "action_loss_avg": 0.001811460603494197}
+{"step": 42200, "loss": 0.031, "learning_rate": 6.670488937284268e-05}
+{"step": 42200, "dynamics_loss_avg": 0.03255025586113334}
+{"step": 42200, "action_loss_avg": 0.0022747219540178777}
+{"step": 42210, "dynamics_loss_avg": 0.029167364165186883}
+{"step": 42210, "action_loss_avg": 0.0024858474615029992}
+{"step": 42220, "dynamics_loss_avg": 0.03386083897203207}
+{"step": 42220, "action_loss_avg": 0.0029615212755743415}
+{"step": 42230, "dynamics_loss_avg": 0.03431700114160776}
+{"step": 42230, "action_loss_avg": 0.0024951828876510263}
+{"step": 42240, "dynamics_loss_avg": 0.032766487821936606}
+{"step": 42240, "action_loss_avg": 0.0020470721588935702}
+{"step": 42250, "loss": 0.0332, "learning_rate": 6.662694363181935e-05}
+{"step": 42250, "dynamics_loss_avg": 0.03776824586093426}
+{"step": 42250, "action_loss_avg": 0.002925049373880029}
+{"step": 42260, "dynamics_loss_avg": 0.030486689414829016}
+{"step": 42260, "action_loss_avg": 0.0020222745079081506}
+{"step": 42270, "dynamics_loss_avg": 0.02637874986976385}
+{"step": 42270, "action_loss_avg": 0.0017904137726873159}
+{"step": 42280, "dynamics_loss_avg": 0.03366738837212324}
+{"step": 42280, "action_loss_avg": 0.0022879748838022353}
+{"step": 42290, "dynamics_loss_avg": 0.027107786480337383}
+{"step": 42290, "action_loss_avg": 0.001364521897630766}
+{"step": 42300, "loss": 0.0315, "learning_rate": 6.654895243336702e-05}
+{"step": 42300, "dynamics_loss_avg": 0.02498043905943632}
+{"step": 42300, "action_loss_avg": 0.0013520026695914567}
+{"step": 42310, "dynamics_loss_avg": 0.032861874997615816}
+{"step": 42310, "action_loss_avg": 0.0019917727913707495}
+{"step": 42320, "dynamics_loss_avg": 0.030333946086466314}
+{"step": 42320, "action_loss_avg": 0.002015773655148223}
+{"step": 42330, "dynamics_loss_avg": 0.022668350581079723}
+{"step": 42330, "action_loss_avg": 0.0018508429231587798}
+{"step": 42340, "dynamics_loss_avg": 0.0370801345910877}
+{"step": 42340, "action_loss_avg": 0.003165077493758872}
+{"step": 42350, "loss": 0.0317, "learning_rate": 6.647091599071066e-05}
+{"step": 42350, "dynamics_loss_avg": 0.03514656238257885}
+{"step": 42350, "action_loss_avg": 0.002838306606281549}
+{"step": 42360, "dynamics_loss_avg": 0.03016888638958335}
+{"step": 42360, "action_loss_avg": 0.002633399044862017}
+{"step": 42370, "dynamics_loss_avg": 0.034483343921601774}
+{"step": 42370, "action_loss_avg": 0.0018231157562695443}
+{"step": 42380, "dynamics_loss_avg": 0.025006321910768747}
+{"step": 42380, "action_loss_avg": 0.002188994234893471}
+{"step": 42390, "dynamics_loss_avg": 0.03352040462195873}
+{"step": 42390, "action_loss_avg": 0.002504006144590676}
+{"step": 42400, "loss": 0.0309, "learning_rate": 6.639283451719893e-05}
+{"step": 42400, "dynamics_loss_avg": 0.028075504954904316}
+{"step": 42400, "action_loss_avg": 0.0024402721464866772}
+{"step": 42410, "dynamics_loss_avg": 0.03157114554196596}
+{"step": 42410, "action_loss_avg": 0.0022293879330391063}
+{"step": 42420, "dynamics_loss_avg": 0.029477291647344826}
+{"step": 42420, "action_loss_avg": 0.001916073402389884}
+{"step": 42430, "dynamics_loss_avg": 0.03760367501527071}
+{"step": 42430, "action_loss_avg": 0.003026783658424392}
+{"step": 42440, "dynamics_loss_avg": 0.0338642256334424}
+{"step": 42440, "action_loss_avg": 0.002942449878901243}
+{"step": 42450, "loss": 0.0326, "learning_rate": 6.631470822630359e-05}
+{"step": 42450, "dynamics_loss_avg": 0.03532206490635872}
+{"step": 42450, "action_loss_avg": 0.002359958703164011}
+{"step": 42460, "dynamics_loss_avg": 0.024155478551983835}
+{"step": 42460, "action_loss_avg": 0.0019730800049728714}
+{"step": 42470, "dynamics_loss_avg": 0.03566669607535004}
+{"step": 42470, "action_loss_avg": 0.0025197114737238735}
+{"step": 42480, "dynamics_loss_avg": 0.026466703275218606}
+{"step": 42480, "action_loss_avg": 0.0019209364589187316}
+{"step": 42490, "dynamics_loss_avg": 0.035561791015788914}
+{"step": 42490, "action_loss_avg": 0.0025079170940443874}
+{"step": 42500, "loss": 0.0316, "learning_rate": 6.623653733161892e-05}
+{"step": 42500, "dynamics_loss_avg": 0.03277480429969728}
+{"step": 42500, "action_loss_avg": 0.001886399762588553}
+{"step": 42510, "dynamics_loss_avg": 0.028624858427792787}
+{"step": 42510, "action_loss_avg": 0.0019053876225370915}
+{"step": 42520, "dynamics_loss_avg": 0.029171339608728884}
+{"step": 42520, "action_loss_avg": 0.0028908825130201875}
+{"step": 42530, "dynamics_loss_avg": 0.02795255295932293}
+{"step": 42530, "action_loss_avg": 0.0018430860480293631}
+{"step": 42540, "dynamics_loss_avg": 0.024001612793654203}
+{"step": 42540, "action_loss_avg": 0.0016809401917271317}
+{"step": 42550, "loss": 0.032, "learning_rate": 6.61583220468612e-05}
+{"step": 42550, "dynamics_loss_avg": 0.029833358991891146}
+{"step": 42550, "action_loss_avg": 0.001864437118638307}
+{"step": 42560, "dynamics_loss_avg": 0.030111821461468936}
+{"step": 42560, "action_loss_avg": 0.0018030522507615388}
+{"step": 42570, "dynamics_loss_avg": 0.02834037342108786}
+{"step": 42570, "action_loss_avg": 0.0021755792608018965}
+{"step": 42580, "dynamics_loss_avg": 0.030636510928161442}
+{"step": 42580, "action_loss_avg": 0.00211728434660472}
+{"step": 42590, "dynamics_loss_avg": 0.028303070832043885}
+{"step": 42590, "action_loss_avg": 0.002305823948699981}
+{"step": 42600, "loss": 0.0314, "learning_rate": 6.608006258586797e-05}
+{"step": 42600, "dynamics_loss_avg": 0.030565925873816013}
+{"step": 42600, "action_loss_avg": 0.002310215623583645}
+{"step": 42610, "dynamics_loss_avg": 0.03526747850701213}
+{"step": 42610, "action_loss_avg": 0.002390495024155825}
+{"step": 42620, "dynamics_loss_avg": 0.038225149549543855}
+{"step": 42620, "action_loss_avg": 0.00231974886264652}
+{"step": 42630, "dynamics_loss_avg": 0.03689231816679239}
+{"step": 42630, "action_loss_avg": 0.0025935321813449264}
+{"step": 42640, "dynamics_loss_avg": 0.02318192683160305}
+{"step": 42640, "action_loss_avg": 0.001651599968317896}
+{"step": 42650, "loss": 0.0336, "learning_rate": 6.600175916259769e-05}
+{"step": 42650, "dynamics_loss_avg": 0.02199386330321431}
+{"step": 42650, "action_loss_avg": 0.002321717794984579}
+{"step": 42660, "dynamics_loss_avg": 0.028169088577851654}
+{"step": 42660, "action_loss_avg": 0.0022730361903086304}
+{"step": 42670, "dynamics_loss_avg": 0.028931154496967794}
+{"step": 42670, "action_loss_avg": 0.0015097985975444316}
+{"step": 42680, "dynamics_loss_avg": 0.02880252609029412}
+{"step": 42680, "action_loss_avg": 0.0021242760703898966}
+{"step": 42690, "dynamics_loss_avg": 0.03382858708500862}
+{"step": 42690, "action_loss_avg": 0.002151489333482459}
+{"step": 42700, "loss": 0.0289, "learning_rate": 6.592341199112886e-05}
+{"step": 42700, "dynamics_loss_avg": 0.029379981383681298}
+{"step": 42700, "action_loss_avg": 0.002968517586123198}
+{"step": 42710, "dynamics_loss_avg": 0.033466399367898705}
+{"step": 42710, "action_loss_avg": 0.0027065051370300354}
+{"step": 42720, "dynamics_loss_avg": 0.03855597451329231}
+{"step": 42720, "action_loss_avg": 0.0036149374092929063}
+{"step": 42730, "dynamics_loss_avg": 0.03427484259009361}
+{"step": 42730, "action_loss_avg": 0.0022097598528489472}
+{"step": 42740, "dynamics_loss_avg": 0.025964858755469323}
+{"step": 42740, "action_loss_avg": 0.0019227776560001076}
+{"step": 42750, "loss": 0.0335, "learning_rate": 6.584502128565968e-05}
+{"step": 42750, "dynamics_loss_avg": 0.03504048082977533}
+{"step": 42750, "action_loss_avg": 0.002586667926516384}
+{"step": 42760, "dynamics_loss_avg": 0.025938513223081827}
+{"step": 42760, "action_loss_avg": 0.002120206115068868}
+{"step": 42770, "dynamics_loss_avg": 0.022567289881408215}
+{"step": 42770, "action_loss_avg": 0.0016690677031874657}
+{"step": 42780, "dynamics_loss_avg": 0.03333871085196734}
+{"step": 42780, "action_loss_avg": 0.002445959870237857}
+{"step": 42790, "dynamics_loss_avg": 0.02892651129513979}
+{"step": 42790, "action_loss_avg": 0.0019901622901670633}
+{"step": 42800, "loss": 0.0309, "learning_rate": 6.576658726050735e-05}
+{"step": 42800, "dynamics_loss_avg": 0.03134205406531691}
+{"step": 42800, "action_loss_avg": 0.0025987696717493236}
+{"step": 42810, "dynamics_loss_avg": 0.02907034568488598}
+{"step": 42810, "action_loss_avg": 0.002778124320320785}
+{"step": 42820, "dynamics_loss_avg": 0.032228187378495934}
+{"step": 42820, "action_loss_avg": 0.0019313398632220923}
+{"step": 42830, "dynamics_loss_avg": 0.028867645561695097}
+{"step": 42830, "action_loss_avg": 0.002576092997333035}
+{"step": 42840, "dynamics_loss_avg": 0.03769194651395082}
+{"step": 42840, "action_loss_avg": 0.003332286688964814}
+{"step": 42850, "loss": 0.0325, "learning_rate": 6.568811013010749e-05}
+{"step": 42850, "dynamics_loss_avg": 0.02876539947465062}
+{"step": 42850, "action_loss_avg": 0.0019146659004036337}
+{"step": 42860, "dynamics_loss_avg": 0.03516785586252809}
+{"step": 42860, "action_loss_avg": 0.0023414232971845196}
+{"step": 42870, "dynamics_loss_avg": 0.030284520890563726}
+{"step": 42870, "action_loss_avg": 0.002250370813999325}
+{"step": 42880, "dynamics_loss_avg": 0.031377528235316275}
+{"step": 42880, "action_loss_avg": 0.002141152590047568}
+{"step": 42890, "dynamics_loss_avg": 0.03365780534222722}
+{"step": 42890, "action_loss_avg": 0.0022751820855773986}
+{"step": 42900, "loss": 0.0338, "learning_rate": 6.56095901090136e-05}
+{"step": 42900, "dynamics_loss_avg": 0.033913588430732486}
+{"step": 42900, "action_loss_avg": 0.003455208020750433}
+{"step": 42910, "dynamics_loss_avg": 0.03900486137717962}
+{"step": 42910, "action_loss_avg": 0.0040822147857397795}
+{"step": 42920, "dynamics_loss_avg": 0.03329412303864956}
+{"step": 42920, "action_loss_avg": 0.0024572204682044687}
+{"step": 42930, "dynamics_loss_avg": 0.026531179528683425}
+{"step": 42930, "action_loss_avg": 0.0023355147161055355}
+{"step": 42940, "dynamics_loss_avg": 0.025047344248741867}
+{"step": 42940, "action_loss_avg": 0.002156182168982923}
+{"step": 42950, "loss": 0.0327, "learning_rate": 6.553102741189638e-05}
+{"step": 42950, "dynamics_loss_avg": 0.033387179113924505}
+{"step": 42950, "action_loss_avg": 0.0030881706974469126}
+{"step": 42960, "dynamics_loss_avg": 0.028841081913560628}
+{"step": 42960, "action_loss_avg": 0.003039690101286396}
+{"step": 42970, "dynamics_loss_avg": 0.032386841345578433}
+{"step": 42970, "action_loss_avg": 0.002054961542307865}
+{"step": 42980, "dynamics_loss_avg": 0.035413517989218234}
+{"step": 42980, "action_loss_avg": 0.0028579473204445095}
+{"step": 42990, "dynamics_loss_avg": 0.02870554933324456}
+{"step": 42990, "action_loss_avg": 0.0022183027816936375}
+{"step": 43000, "loss": 0.0313, "learning_rate": 6.545242225354328e-05}
+{"step": 43000, "dynamics_loss_avg": 0.026430328935384752}
+{"step": 43000, "action_loss_avg": 0.002087424276396632}
+{"step": 43010, "dynamics_loss_avg": 0.03214697395451367}
+{"step": 43010, "action_loss_avg": 0.002387974623707123}
+{"step": 43020, "dynamics_loss_avg": 0.030655009858310222}
+{"step": 43020, "action_loss_avg": 0.0018465619126800449}
+{"step": 43030, "dynamics_loss_avg": 0.020027974573895335}
+{"step": 43030, "action_loss_avg": 0.001294334832346067}
+{"step": 43040, "dynamics_loss_avg": 0.021680273208767177}
+{"step": 43040, "action_loss_avg": 0.0016747619665693492}
+{"step": 43050, "loss": 0.0298, "learning_rate": 6.537377484885779e-05}
+{"step": 43050, "dynamics_loss_avg": 0.03384505799040198}
+{"step": 43050, "action_loss_avg": 0.0027555087901419027}
+{"step": 43060, "dynamics_loss_avg": 0.0302241001278162}
+{"step": 43060, "action_loss_avg": 0.0024927917897002772}
+{"step": 43070, "dynamics_loss_avg": 0.021202129498124122}
+{"step": 43070, "action_loss_avg": 0.001185183209599927}
+{"step": 43080, "dynamics_loss_avg": 0.03408139236271381}
+{"step": 43080, "action_loss_avg": 0.003047117334790528}
+{"step": 43090, "dynamics_loss_avg": 0.02961094481870532}
+{"step": 43090, "action_loss_avg": 0.0021076768840430304}
+{"step": 43100, "loss": 0.0325, "learning_rate": 6.529508541285889e-05}
+{"step": 43100, "dynamics_loss_avg": 0.03612416991963983}
+{"step": 43100, "action_loss_avg": 0.0026690941595006734}
+{"step": 43110, "dynamics_loss_avg": 0.03360116283874959}
+{"step": 43110, "action_loss_avg": 0.0019070469119469636}
+{"step": 43120, "dynamics_loss_avg": 0.02698981948196888}
+{"step": 43120, "action_loss_avg": 0.002060064009856433}
+{"step": 43130, "dynamics_loss_avg": 0.02853363733738661}
+{"step": 43130, "action_loss_avg": 0.001743302762042731}
+{"step": 43140, "dynamics_loss_avg": 0.031128612579777837}
+{"step": 43140, "action_loss_avg": 0.0023163162462878973}
+{"step": 43150, "loss": 0.0329, "learning_rate": 6.521635416068054e-05}
+{"step": 43150, "dynamics_loss_avg": 0.03016577996313572}
+{"step": 43150, "action_loss_avg": 0.001997940638102591}
+{"step": 43160, "dynamics_loss_avg": 0.030448908917605877}
+{"step": 43160, "action_loss_avg": 0.0023821081267669797}
+{"step": 43170, "dynamics_loss_avg": 0.026249883137643336}
+{"step": 43170, "action_loss_avg": 0.0023011982761090622}
+{"step": 43180, "dynamics_loss_avg": 0.020028478186577558}
+{"step": 43180, "action_loss_avg": 0.0010513207962503657}
+{"step": 43190, "dynamics_loss_avg": 0.03689393028616905}
+{"step": 43190, "action_loss_avg": 0.002186544775031507}
+{"step": 43200, "loss": 0.03, "learning_rate": 6.513758130757094e-05}
+{"step": 43200, "dynamics_loss_avg": 0.030843055341392756}
+{"step": 43200, "action_loss_avg": 0.0030665970756672324}
+{"step": 43210, "dynamics_loss_avg": 0.03292199252173304}
+{"step": 43210, "action_loss_avg": 0.0024916006077546626}
+{"step": 43220, "dynamics_loss_avg": 0.025613746792078017}
+{"step": 43220, "action_loss_avg": 0.0017706396465655416}
+{"step": 43230, "dynamics_loss_avg": 0.02859833841212094}
+{"step": 43230, "action_loss_avg": 0.0022956648652325386}
+{"step": 43240, "dynamics_loss_avg": 0.029919788893312215}
+{"step": 43240, "action_loss_avg": 0.0019758937938604503}
+{"step": 43250, "loss": 0.0302, "learning_rate": 6.505876706889207e-05}
+{"step": 43250, "dynamics_loss_avg": 0.034556682128459214}
+{"step": 43250, "action_loss_avg": 0.002273589780088514}
+{"step": 43260, "dynamics_loss_avg": 0.03232544921338558}
+{"step": 43260, "action_loss_avg": 0.002981162571813911}
+{"step": 43270, "dynamics_loss_avg": 0.030480467528104783}
+{"step": 43270, "action_loss_avg": 0.0017806460557039828}
+{"step": 43280, "dynamics_loss_avg": 0.02521833973005414}
+{"step": 43280, "action_loss_avg": 0.0022612740169279276}
+{"step": 43290, "dynamics_loss_avg": 0.02494742553681135}
+{"step": 43290, "action_loss_avg": 0.0015310072980355472}
+{"step": 43300, "loss": 0.0319, "learning_rate": 6.497991166011903e-05}
+{"step": 43300, "dynamics_loss_avg": 0.04070512317121029}
+{"step": 43300, "action_loss_avg": 0.0021724726888351143}
+{"step": 43310, "dynamics_loss_avg": 0.033394073508679865}
+{"step": 43310, "action_loss_avg": 0.0021523113711737095}
+{"step": 43320, "dynamics_loss_avg": 0.03234622348099947}
+{"step": 43320, "action_loss_avg": 0.002042197663104162}
+{"step": 43330, "dynamics_loss_avg": 0.02310002576559782}
+{"step": 43330, "action_loss_avg": 0.0016012337116990238}
+{"step": 43340, "dynamics_loss_avg": 0.028493566997349264}
+{"step": 43340, "action_loss_avg": 0.002046928944764659}
+{"step": 43350, "loss": 0.0295, "learning_rate": 6.490101529683957e-05}
+{"step": 43350, "dynamics_loss_avg": 0.027056990098208188}
+{"step": 43350, "action_loss_avg": 0.0015286987472791225}
+{"step": 43360, "dynamics_loss_avg": 0.0324518877081573}
+{"step": 43360, "action_loss_avg": 0.0023403558705467732}
+{"step": 43370, "dynamics_loss_avg": 0.03647745847702026}
+{"step": 43370, "action_loss_avg": 0.002363815950229764}
+{"step": 43380, "dynamics_loss_avg": 0.028769783955067397}
+{"step": 43380, "action_loss_avg": 0.001771352149080485}
+{"step": 43390, "dynamics_loss_avg": 0.028001117007806896}
+{"step": 43390, "action_loss_avg": 0.0022803039726568388}
+{"step": 43400, "loss": 0.0314, "learning_rate": 6.482207819475323e-05}
+{"step": 43400, "dynamics_loss_avg": 0.028426698874682188}
+{"step": 43400, "action_loss_avg": 0.001699594996171072}
+{"step": 43410, "dynamics_loss_avg": 0.03257693536579609}
+{"step": 43410, "action_loss_avg": 0.0027161044854437932}
+{"step": 43420, "dynamics_loss_avg": 0.03582866601645947}
+{"step": 43420, "action_loss_avg": 0.002176083857193589}
+{"step": 43430, "dynamics_loss_avg": 0.029390554875135422}
+{"step": 43430, "action_loss_avg": 0.0021368209738284348}
+{"step": 43440, "dynamics_loss_avg": 0.032443194277584554}
+{"step": 43440, "action_loss_avg": 0.0021215990418568254}
+{"step": 43450, "loss": 0.0322, "learning_rate": 6.474310056967111e-05}
+{"step": 43450, "dynamics_loss_avg": 0.021574958600103854}
+{"step": 43450, "action_loss_avg": 0.001523434987757355}
+{"step": 43460, "dynamics_loss_avg": 0.03356260834261775}
+{"step": 43460, "action_loss_avg": 0.002362758060917258}
+{"step": 43470, "dynamics_loss_avg": 0.03150621210224926}
+{"step": 43470, "action_loss_avg": 0.003402425581589341}
+{"step": 43480, "dynamics_loss_avg": 0.03362192707136273}
+{"step": 43480, "action_loss_avg": 0.002329387643840164}
+{"step": 43490, "dynamics_loss_avg": 0.025668823532760142}
+{"step": 43490, "action_loss_avg": 0.0014284016622696071}
+{"step": 43500, "loss": 0.0325, "learning_rate": 6.4664082637515e-05}
+{"step": 43500, "dynamics_loss_avg": 0.028472619876265527}
+{"step": 43500, "action_loss_avg": 0.0016792496317066252}
+{"step": 43510, "dynamics_loss_avg": 0.023523045424371957}
+{"step": 43510, "action_loss_avg": 0.0016732849413529038}
+{"step": 43520, "dynamics_loss_avg": 0.03052194882184267}
+{"step": 43520, "action_loss_avg": 0.002149608376203105}
+{"step": 43530, "dynamics_loss_avg": 0.020683813840150833}
+{"step": 43530, "action_loss_avg": 0.0016240517230471595}
+{"step": 43540, "dynamics_loss_avg": 0.02361288294196129}
+{"step": 43540, "action_loss_avg": 0.0013504923495929687}
+{"step": 43550, "loss": 0.0268, "learning_rate": 6.45850246143169e-05}
+{"step": 43550, "dynamics_loss_avg": 0.02492760503664613}
+{"step": 43550, "action_loss_avg": 0.0015911197857349179}
+{"step": 43560, "dynamics_loss_avg": 0.03311508381739259}
+{"step": 43560, "action_loss_avg": 0.0017817733256379142}
+{"step": 43570, "dynamics_loss_avg": 0.03602359052747488}
+{"step": 43570, "action_loss_avg": 0.0023158422496635466}
+{"step": 43580, "dynamics_loss_avg": 0.035710065718740226}
+{"step": 43580, "action_loss_avg": 0.0028227899310877547}
+{"step": 43590, "dynamics_loss_avg": 0.02827941137365997}
+{"step": 43590, "action_loss_avg": 0.002006197132868692}
+{"step": 43600, "loss": 0.034, "learning_rate": 6.450592671621842e-05}
+{"step": 43600, "dynamics_loss_avg": 0.03535042172297835}
+{"step": 43600, "action_loss_avg": 0.002470311790239066}
+{"step": 43610, "dynamics_loss_avg": 0.019949132995679974}
+{"step": 43610, "action_loss_avg": 0.001141350861871615}
+{"step": 43620, "dynamics_loss_avg": 0.034411756321787834}
+{"step": 43620, "action_loss_avg": 0.0019167943566571922}
+{"step": 43630, "dynamics_loss_avg": 0.036578791309148075}
+{"step": 43630, "action_loss_avg": 0.002033913627383299}
+{"step": 43640, "dynamics_loss_avg": 0.026768973888829352}
+{"step": 43640, "action_loss_avg": 0.001732773066032678}
+{"step": 43650, "loss": 0.0316, "learning_rate": 6.442678915947023e-05}
+{"step": 43650, "dynamics_loss_avg": 0.02995433546602726}
+{"step": 43650, "action_loss_avg": 0.0017697467876132578}
+{"step": 43660, "dynamics_loss_avg": 0.038361409679055214}
+{"step": 43660, "action_loss_avg": 0.003309190372237936}
+{"step": 43670, "dynamics_loss_avg": 0.03145046355202794}
+{"step": 43670, "action_loss_avg": 0.002295446291100234}
+{"step": 43680, "dynamics_loss_avg": 0.02260423367843032}
+{"step": 43680, "action_loss_avg": 0.0012170152680482716}
+{"step": 43690, "dynamics_loss_avg": 0.03240633672103286}
+{"step": 43690, "action_loss_avg": 0.002301235741470009}
+{"step": 43700, "loss": 0.0318, "learning_rate": 6.434761216043135e-05}
+{"step": 43700, "dynamics_loss_avg": 0.032391364499926564}
+{"step": 43700, "action_loss_avg": 0.001951043662847951}
+{"step": 43710, "dynamics_loss_avg": 0.03379729092121124}
+{"step": 43710, "action_loss_avg": 0.002175554138375446}
+{"step": 43720, "dynamics_loss_avg": 0.030031308904290198}
+{"step": 43720, "action_loss_avg": 0.002300053770886734}
+{"step": 43730, "dynamics_loss_avg": 0.03292709039524198}
+{"step": 43730, "action_loss_avg": 0.0015818477317225189}
+{"step": 43740, "dynamics_loss_avg": 0.02742136213928461}
+{"step": 43740, "action_loss_avg": 0.0019231116748414934}
+{"step": 43750, "loss": 0.0309, "learning_rate": 6.426839593556868e-05}
+{"step": 43750, "dynamics_loss_avg": 0.027428590785712005}
+{"step": 43750, "action_loss_avg": 0.0022922407428268344}
+{"step": 43760, "dynamics_loss_avg": 0.03240322824567556}
+{"step": 43760, "action_loss_avg": 0.0025334433070383967}
+{"step": 43770, "dynamics_loss_avg": 0.036424610484391454}
+{"step": 43770, "action_loss_avg": 0.002794359321705997}
+{"step": 43780, "dynamics_loss_avg": 0.030133961141109465}
+{"step": 43780, "action_loss_avg": 0.0029683934757485987}
+{"step": 43790, "dynamics_loss_avg": 0.025580176152288914}
+{"step": 43790, "action_loss_avg": 0.0014372030913364143}
+{"step": 43800, "loss": 0.0344, "learning_rate": 6.418914070145636e-05}
+{"step": 43800, "dynamics_loss_avg": 0.02496667797677219}
+{"step": 43800, "action_loss_avg": 0.0019402056117542089}
+{"step": 43810, "dynamics_loss_avg": 0.030245473701506854}
+{"step": 43810, "action_loss_avg": 0.0027752151887398212}
+{"step": 43820, "dynamics_loss_avg": 0.02462350851856172}
+{"step": 43820, "action_loss_avg": 0.0017212632694281638}
+{"step": 43830, "dynamics_loss_avg": 0.026132481079548596}
+{"step": 43830, "action_loss_avg": 0.0013694800611119718}
+{"step": 43840, "dynamics_loss_avg": 0.03222797205671668}
+{"step": 43840, "action_loss_avg": 0.0023424106941092758}
+{"step": 43850, "loss": 0.0293, "learning_rate": 6.410984667477518e-05}
+{"step": 43850, "dynamics_loss_avg": 0.030208498425781726}
+{"step": 43850, "action_loss_avg": 0.0019914783479180187}
+{"step": 43860, "dynamics_loss_avg": 0.03912955317646265}
+{"step": 43860, "action_loss_avg": 0.002130299003329128}
+{"step": 43870, "dynamics_loss_avg": 0.023024207074195148}
+{"step": 43870, "action_loss_avg": 0.0015760022070026025}
+{"step": 43880, "dynamics_loss_avg": 0.03054740568622947}
+{"step": 43880, "action_loss_avg": 0.002635822969023138}
+{"step": 43890, "dynamics_loss_avg": 0.027069004811346532}
+{"step": 43890, "action_loss_avg": 0.0019383681821636856}
+{"step": 43900, "loss": 0.0315, "learning_rate": 6.403051407231196e-05}
+{"step": 43900, "dynamics_loss_avg": 0.023927190341055393}
+{"step": 43900, "action_loss_avg": 0.0017264582158531994}
+{"step": 43910, "dynamics_loss_avg": 0.028947891760617496}
+{"step": 43910, "action_loss_avg": 0.0017728748673107475}
+{"step": 43920, "dynamics_loss_avg": 0.03525222688913345}
+{"step": 43920, "action_loss_avg": 0.002053373621311039}
+{"step": 43930, "dynamics_loss_avg": 0.03521792986430228}
+{"step": 43930, "action_loss_avg": 0.00300723955151625}
+{"step": 43940, "dynamics_loss_avg": 0.03519103433936834}
+{"step": 43940, "action_loss_avg": 0.002709930867422372}
+{"step": 43950, "loss": 0.0322, "learning_rate": 6.395114311095905e-05}
+{"step": 43950, "dynamics_loss_avg": 0.02226474448107183}
+{"step": 43950, "action_loss_avg": 0.0013386184233240782}
+{"step": 43960, "dynamics_loss_avg": 0.026312265451997517}
+{"step": 43960, "action_loss_avg": 0.001806273279362358}
+{"step": 43970, "dynamics_loss_avg": 0.034376044664531945}
+{"step": 43970, "action_loss_avg": 0.0026954811939503996}
+{"step": 43980, "dynamics_loss_avg": 0.025149223022162916}
+{"step": 43980, "action_loss_avg": 0.0013175543979741633}
+{"step": 43990, "dynamics_loss_avg": 0.03039422333240509}
+{"step": 43990, "action_loss_avg": 0.0011877814831677824}
+{"step": 44000, "loss": 0.0307, "learning_rate": 6.387173400771358e-05}
+{"step": 44000, "dynamics_loss_avg": 0.02741283653303981}
+{"step": 44000, "action_loss_avg": 0.0016166974121006206}
+{"step": 44010, "dynamics_loss_avg": 0.03448984771966934}
+{"step": 44010, "action_loss_avg": 0.0020056593348272145}
+{"step": 44020, "dynamics_loss_avg": 0.03909591631963849}
+{"step": 44020, "action_loss_avg": 0.0023531595652457327}
+{"step": 44030, "dynamics_loss_avg": 0.0301304348744452}
+{"step": 44030, "action_loss_avg": 0.0019521193520631642}
+{"step": 44040, "dynamics_loss_avg": 0.026028782688081266}
+{"step": 44040, "action_loss_avg": 0.0016619933099718764}
+{"step": 44050, "loss": 0.0323, "learning_rate": 6.379228697967702e-05}
+{"step": 44050, "dynamics_loss_avg": 0.02110099485144019}
+{"step": 44050, "action_loss_avg": 0.0019705262267962096}
+{"step": 44060, "dynamics_loss_avg": 0.026721013803035022}
+{"step": 44060, "action_loss_avg": 0.0019016681180801243}
+{"step": 44070, "dynamics_loss_avg": 0.03036454217508435}
+{"step": 44070, "action_loss_avg": 0.0021030970849096773}
+{"step": 44080, "dynamics_loss_avg": 0.038042095769196746}
+{"step": 44080, "action_loss_avg": 0.0031912047998048365}
+{"step": 44090, "dynamics_loss_avg": 0.040175208915025}
+{"step": 44090, "action_loss_avg": 0.002809411787893623}
+{"step": 44100, "loss": 0.0333, "learning_rate": 6.371280224405452e-05}
+{"step": 44100, "dynamics_loss_avg": 0.03538941740989685}
+{"step": 44100, "action_loss_avg": 0.002625132747925818}
+{"step": 44110, "dynamics_loss_avg": 0.023665463412180544}
+{"step": 44110, "action_loss_avg": 0.0016996578138787299}
+{"step": 44120, "dynamics_loss_avg": 0.02876364588737488}
+{"step": 44120, "action_loss_avg": 0.0019987304985988885}
+{"step": 44130, "dynamics_loss_avg": 0.021731834672391415}
+{"step": 44130, "action_loss_avg": 0.0016156008816324175}
+{"step": 44140, "dynamics_loss_avg": 0.030236713495105504}
+{"step": 44140, "action_loss_avg": 0.0021739181771408766}
+{"step": 44150, "loss": 0.0309, "learning_rate": 6.363328001815431e-05}
+{"step": 44150, "dynamics_loss_avg": 0.04121391586959362}
+{"step": 44150, "action_loss_avg": 0.002475026063621044}
+{"step": 44160, "dynamics_loss_avg": 0.03648358685895801}
+{"step": 44160, "action_loss_avg": 0.002466029970673844}
+{"step": 44170, "dynamics_loss_avg": 0.027402378059923647}
+{"step": 44170, "action_loss_avg": 0.0018844484991859644}
+{"step": 44180, "dynamics_loss_avg": 0.024369804281741382}
+{"step": 44180, "action_loss_avg": 0.0014583463955204934}
+{"step": 44190, "dynamics_loss_avg": 0.03242063373327255}
+{"step": 44190, "action_loss_avg": 0.0024629559891764076}
+{"step": 44200, "loss": 0.0324, "learning_rate": 6.355372051938711e-05}
+{"step": 44200, "dynamics_loss_avg": 0.03405200615525246}
+{"step": 44200, "action_loss_avg": 0.002842780199716799}
+{"step": 44210, "dynamics_loss_avg": 0.02764737857505679}
+{"step": 44210, "action_loss_avg": 0.0016229729517363012}
+{"step": 44220, "dynamics_loss_avg": 0.03512901249341667}
+{"step": 44220, "action_loss_avg": 0.0024898768926504998}
+{"step": 44230, "dynamics_loss_avg": 0.03051114287227392}
+{"step": 44230, "action_loss_avg": 0.0026810818759258836}
+{"step": 44240, "dynamics_loss_avg": 0.023286661272868513}
+{"step": 44240, "action_loss_avg": 0.0018568600993603469}
+{"step": 44250, "loss": 0.0298, "learning_rate": 6.347412396526555e-05}
+{"step": 44250, "dynamics_loss_avg": 0.021389297489076853}
+{"step": 44250, "action_loss_avg": 0.0017013868549838663}
+{"step": 44260, "dynamics_loss_avg": 0.02998344795778394}
+{"step": 44260, "action_loss_avg": 0.002568844734923914}
+{"step": 44270, "dynamics_loss_avg": 0.03444740325212479}
+{"step": 44270, "action_loss_avg": 0.0030433416133746503}
+{"step": 44280, "dynamics_loss_avg": 0.02557723643258214}
+{"step": 44280, "action_loss_avg": 0.001420393050648272}
+{"step": 44290, "dynamics_loss_avg": 0.02759755477309227}
+{"step": 44290, "action_loss_avg": 0.0015983881894499063}
+{"step": 44300, "loss": 0.0327, "learning_rate": 6.339449057340359e-05}
+{"step": 44300, "dynamics_loss_avg": 0.04656995609402657}
+{"step": 44300, "action_loss_avg": 0.003478862752672285}
+{"step": 44310, "dynamics_loss_avg": 0.029252356034703553}
+{"step": 44310, "action_loss_avg": 0.0020003954239655288}
+{"step": 44320, "dynamics_loss_avg": 0.03064855239354074}
+{"step": 44320, "action_loss_avg": 0.0032818603503983468}
+{"step": 44330, "dynamics_loss_avg": 0.033284506760537624}
+{"step": 44330, "action_loss_avg": 0.0019624549633590503}
+{"step": 44340, "dynamics_loss_avg": 0.028790033422410488}
+{"step": 44340, "action_loss_avg": 0.0015912211849354208}
+{"step": 44350, "loss": 0.0316, "learning_rate": 6.331482056151585e-05}
+{"step": 44350, "dynamics_loss_avg": 0.02625899072736502}
+{"step": 44350, "action_loss_avg": 0.0014774052222492173}
+{"step": 44360, "dynamics_loss_avg": 0.024311869498342277}
+{"step": 44360, "action_loss_avg": 0.0018909507809439674}
+{"step": 44370, "dynamics_loss_avg": 0.03318249862641096}
+{"step": 44370, "action_loss_avg": 0.002944017911795527}
+{"step": 44380, "dynamics_loss_avg": 0.030702825728803874}
+{"step": 44380, "action_loss_avg": 0.003069310146383941}
+{"step": 44390, "dynamics_loss_avg": 0.03202962363138795}
+{"step": 44390, "action_loss_avg": 0.0023890240758191795}
+{"step": 44400, "loss": 0.0323, "learning_rate": 6.323511414741715e-05}
+{"step": 44400, "dynamics_loss_avg": 0.030535014113411307}
+{"step": 44400, "action_loss_avg": 0.002382621372817084}
+{"step": 44410, "dynamics_loss_avg": 0.03683092328719795}
+{"step": 44410, "action_loss_avg": 0.003333507249772083}
+{"step": 44420, "dynamics_loss_avg": 0.03193221101537347}
+{"step": 44420, "action_loss_avg": 0.0031093845173018053}
+{"step": 44430, "dynamics_loss_avg": 0.02510126167908311}
+{"step": 44430, "action_loss_avg": 0.002070942975115031}
+{"step": 44440, "dynamics_loss_avg": 0.02643861956894398}
+{"step": 44440, "action_loss_avg": 0.002081075287424028}
+{"step": 44450, "loss": 0.0326, "learning_rate": 6.315537154902173e-05}
+{"step": 44450, "dynamics_loss_avg": 0.02531977379694581}
+{"step": 44450, "action_loss_avg": 0.0014984204433858394}
+{"step": 44460, "dynamics_loss_avg": 0.041827094927430156}
+{"step": 44460, "action_loss_avg": 0.002509860589634627}
+{"step": 44470, "dynamics_loss_avg": 0.029591672588139772}
+{"step": 44470, "action_loss_avg": 0.0025313530524726955}
+{"step": 44480, "dynamics_loss_avg": 0.029364688228815793}
+{"step": 44480, "action_loss_avg": 0.0021235526277450846}
+{"step": 44490, "dynamics_loss_avg": 0.03364275004714727}
+{"step": 44490, "action_loss_avg": 0.0022011140128597615}
+{"step": 44500, "loss": 0.0327, "learning_rate": 6.307559298434284e-05}
+{"step": 44500, "dynamics_loss_avg": 0.019850783236324786}
+{"step": 44500, "action_loss_avg": 0.0013147893347195349}
+{"step": 44510, "dynamics_loss_avg": 0.025798480864614247}
+{"step": 44510, "action_loss_avg": 0.002320715386304073}
+{"step": 44520, "dynamics_loss_avg": 0.0211957891471684}
+{"step": 44520, "action_loss_avg": 0.0017159140959847718}
+{"step": 44530, "dynamics_loss_avg": 0.02704096371307969}
+{"step": 44530, "action_loss_avg": 0.0023964770254679022}
+{"step": 44540, "dynamics_loss_avg": 0.03333613993600011}
+{"step": 44540, "action_loss_avg": 0.0020881039439700545}
+{"step": 44550, "loss": 0.0285, "learning_rate": 6.299577867149202e-05}
+{"step": 44550, "dynamics_loss_avg": 0.03330805115401745}
+{"step": 44550, "action_loss_avg": 0.0023121993872337043}
+{"step": 44560, "dynamics_loss_avg": 0.02763382256962359}
+{"step": 44560, "action_loss_avg": 0.0019588022900279612}
+{"step": 44570, "dynamics_loss_avg": 0.03629098208621144}
+{"step": 44570, "action_loss_avg": 0.0032035130832809957}
+{"step": 44580, "dynamics_loss_avg": 0.022818650444969536}
+{"step": 44580, "action_loss_avg": 0.001542645477456972}
+{"step": 44590, "dynamics_loss_avg": 0.02802296681329608}
+{"step": 44590, "action_loss_avg": 0.002992362284567207}
+{"step": 44600, "loss": 0.0313, "learning_rate": 6.291592882867855e-05}
+{"step": 44600, "dynamics_loss_avg": 0.027797811850905418}
+{"step": 44600, "action_loss_avg": 0.0018565662670880557}
+{"step": 44610, "dynamics_loss_avg": 0.03615380004048348}
+{"step": 44610, "action_loss_avg": 0.001767378713702783}
+{"step": 44620, "dynamics_loss_avg": 0.026631534658372404}
+{"step": 44620, "action_loss_avg": 0.002411292085889727}
+{"step": 44630, "dynamics_loss_avg": 0.03196779442951083}
+{"step": 44630, "action_loss_avg": 0.0030393532710149885}
+{"step": 44640, "dynamics_loss_avg": 0.0305547496303916}
+{"step": 44640, "action_loss_avg": 0.0020904962497297675}
+{"step": 44650, "loss": 0.0317, "learning_rate": 6.283604367420887e-05}
+{"step": 44650, "dynamics_loss_avg": 0.02855583904311061}
+{"step": 44650, "action_loss_avg": 0.0019243556482251734}
+{"step": 44660, "dynamics_loss_avg": 0.02284908974543214}
+{"step": 44660, "action_loss_avg": 0.002312711253762245}
+{"step": 44670, "dynamics_loss_avg": 0.03276629811152816}
+{"step": 44670, "action_loss_avg": 0.002349601505557075}
+{"step": 44680, "dynamics_loss_avg": 0.0343618618324399}
+{"step": 44680, "action_loss_avg": 0.0018774742493405938}
+{"step": 44690, "dynamics_loss_avg": 0.02839055424556136}
+{"step": 44690, "action_loss_avg": 0.0026710442267358302}
+{"step": 44700, "loss": 0.0321, "learning_rate": 6.275612342648592e-05}
+{"step": 44700, "dynamics_loss_avg": 0.026353277545422316}
+{"step": 44700, "action_loss_avg": 0.001663488708436489}
+{"step": 44710, "dynamics_loss_avg": 0.03449863493442536}
+{"step": 44710, "action_loss_avg": 0.002961396751925349}
+{"step": 44720, "dynamics_loss_avg": 0.03136499710381031}
+{"step": 44720, "action_loss_avg": 0.0021632268268149345}
+{"step": 44730, "dynamics_loss_avg": 0.026693340763449667}
+{"step": 44730, "action_loss_avg": 0.0021998610813170672}
+{"step": 44740, "dynamics_loss_avg": 0.025536105781793595}
+{"step": 44740, "action_loss_avg": 0.0015634382958523928}
+{"step": 44750, "loss": 0.0298, "learning_rate": 6.26761683040086e-05}
+{"step": 44750, "dynamics_loss_avg": 0.032506410498172045}
+{"step": 44750, "action_loss_avg": 0.002010710662580095}
+{"step": 44760, "dynamics_loss_avg": 0.03094813812058419}
+{"step": 44760, "action_loss_avg": 0.0027035577630158516}
+{"step": 44770, "dynamics_loss_avg": 0.03598386850208044}
+{"step": 44770, "action_loss_avg": 0.0018243743106722832}
+{"step": 44780, "dynamics_loss_avg": 0.029671125346794724}
+{"step": 44780, "action_loss_avg": 0.0025550917911459693}
+{"step": 44790, "dynamics_loss_avg": 0.03977008797228336}
+{"step": 44790, "action_loss_avg": 0.0022794160526245833}
+{"step": 44800, "loss": 0.0345, "learning_rate": 6.259617852537118e-05}
+{"step": 44800, "dynamics_loss_avg": 0.024576550349593163}
+{"step": 44800, "action_loss_avg": 0.0016138556879013778}
+{"step": 44810, "dynamics_loss_avg": 0.03660689201205969}
+{"step": 44810, "action_loss_avg": 0.0024882991216145455}
+{"step": 44820, "dynamics_loss_avg": 0.04035032205283642}
+{"step": 44820, "action_loss_avg": 0.0027137742610648273}
+{"step": 44830, "dynamics_loss_avg": 0.025679806619882582}
+{"step": 44830, "action_loss_avg": 0.0014754873001948}
+{"step": 44840, "dynamics_loss_avg": 0.03418288775719702}
+{"step": 44840, "action_loss_avg": 0.0023375423610559666}
+{"step": 44850, "loss": 0.0327, "learning_rate": 6.251615430926267e-05}
+{"step": 44850, "dynamics_loss_avg": 0.029267391096800564}
+{"step": 44850, "action_loss_avg": 0.0019068079680437222}
+{"step": 44860, "dynamics_loss_avg": 0.033871700847521426}
+{"step": 44860, "action_loss_avg": 0.0031851001374889167}
+{"step": 44870, "dynamics_loss_avg": 0.03397190123796463}
+{"step": 44870, "action_loss_avg": 0.002860765962395817}
+{"step": 44880, "dynamics_loss_avg": 0.03262436147779226}
+{"step": 44880, "action_loss_avg": 0.0022708683216478677}
+{"step": 44890, "dynamics_loss_avg": 0.03389733210206032}
+{"step": 44890, "action_loss_avg": 0.0026887440821155907}
+{"step": 44900, "loss": 0.0331, "learning_rate": 6.24360958744662e-05}
+{"step": 44900, "dynamics_loss_avg": 0.026484628627076744}
+{"step": 44900, "action_loss_avg": 0.0020542065263725816}
+{"step": 44910, "dynamics_loss_avg": 0.03370766965672374}
+{"step": 44910, "action_loss_avg": 0.0021343509666621684}
+{"step": 44920, "dynamics_loss_avg": 0.017903031781315804}
+{"step": 44920, "action_loss_avg": 0.0012704653549008072}
+{"step": 44930, "dynamics_loss_avg": 0.034360071457922456}
+{"step": 44930, "action_loss_avg": 0.002467614458873868}
+{"step": 44940, "dynamics_loss_avg": 0.033354646526277065}
+{"step": 44940, "action_loss_avg": 0.0025702315993839874}
+{"step": 44950, "loss": 0.0315, "learning_rate": 6.235600343985848e-05}
+{"step": 44950, "dynamics_loss_avg": 0.029329870454967023}
+{"step": 44950, "action_loss_avg": 0.0017435783869586886}
+{"step": 44960, "dynamics_loss_avg": 0.029043219052255154}
+{"step": 44960, "action_loss_avg": 0.0022096253756899386}
+{"step": 44970, "dynamics_loss_avg": 0.029094522027298807}
+{"step": 44970, "action_loss_avg": 0.0018347696401178836}
+{"step": 44980, "dynamics_loss_avg": 0.03374036867171526}
+{"step": 44980, "action_loss_avg": 0.002791629743296653}
+{"step": 44990, "dynamics_loss_avg": 0.0262114567682147}
+{"step": 44990, "action_loss_avg": 0.0018227396649308503}
+{"step": 45000, "loss": 0.0311, "learning_rate": 6.227587722440917e-05}
+{"step": 45000, "dynamics_loss_avg": 0.031331640761345626}
+{"step": 45000, "action_loss_avg": 0.001969169738003984}
+{"step": 45010, "dynamics_loss_avg": 0.032191119901835916}
+{"step": 45010, "action_loss_avg": 0.001889323873911053}
+{"step": 45020, "dynamics_loss_avg": 0.03161860322579742}
+{"step": 45020, "action_loss_avg": 0.0022552929527591913}
+{"step": 45030, "dynamics_loss_avg": 0.03319414034485817}
+{"step": 45030, "action_loss_avg": 0.0019725557474885138}
+{"step": 45040, "dynamics_loss_avg": 0.026830153353512288}
+{"step": 45040, "action_loss_avg": 0.002211131656076759}
+{"step": 45050, "loss": 0.0325, "learning_rate": 6.219571744718027e-05}
+{"step": 45050, "dynamics_loss_avg": 0.024823052622377873}
+{"step": 45050, "action_loss_avg": 0.0019081625796388835}
+{"step": 45060, "dynamics_loss_avg": 0.02495712460950017}
+{"step": 45060, "action_loss_avg": 0.0012402915337588639}
+{"step": 45070, "dynamics_loss_avg": 0.022451164294034244}
+{"step": 45070, "action_loss_avg": 0.0012718678219243885}
+{"step": 45080, "dynamics_loss_avg": 0.027176368329674006}
+{"step": 45080, "action_loss_avg": 0.0017610635055461898}
+{"step": 45090, "dynamics_loss_avg": 0.03468952113762498}
+{"step": 45090, "action_loss_avg": 0.0021030621486715973}
+{"step": 45100, "loss": 0.0281, "learning_rate": 6.211552432732559e-05}
+{"step": 45100, "dynamics_loss_avg": 0.03024393431842327}
+{"step": 45100, "action_loss_avg": 0.00304154132027179}
+{"step": 45110, "dynamics_loss_avg": 0.036564350686967374}
+{"step": 45110, "action_loss_avg": 0.002558935293927789}
+{"step": 45120, "dynamics_loss_avg": 0.021827579755336047}
+{"step": 45120, "action_loss_avg": 0.0014852993306703865}
+{"step": 45130, "dynamics_loss_avg": 0.022602211125195025}
+{"step": 45130, "action_loss_avg": 0.0017750424391124397}
+{"step": 45140, "dynamics_loss_avg": 0.03424943825230002}
+{"step": 45140, "action_loss_avg": 0.0019578317645937205}
+{"step": 45150, "loss": 0.0307, "learning_rate": 6.203529808409e-05}
+{"step": 45150, "dynamics_loss_avg": 0.02963279765099287}
+{"step": 45150, "action_loss_avg": 0.001852392323780805}
+{"step": 45160, "dynamics_loss_avg": 0.02451158072799444}
+{"step": 45160, "action_loss_avg": 0.0014259888004744426}
+{"step": 45170, "dynamics_loss_avg": 0.027087279316037893}
+{"step": 45170, "action_loss_avg": 0.0015115739370230585}
+{"step": 45180, "dynamics_loss_avg": 0.03140381062403321}
+{"step": 45180, "action_loss_avg": 0.0023683643667027354}
+{"step": 45190, "dynamics_loss_avg": 0.028128362167626618}
+{"step": 45190, "action_loss_avg": 0.0017136514419689775}
+{"step": 45200, "loss": 0.0301, "learning_rate": 6.195503893680903e-05}
+{"step": 45200, "dynamics_loss_avg": 0.031202804669737814}
+{"step": 45200, "action_loss_avg": 0.002069658861728385}
+{"step": 45210, "dynamics_loss_avg": 0.025981631595641375}
+{"step": 45210, "action_loss_avg": 0.0017441599920857698}
+{"step": 45220, "dynamics_loss_avg": 0.03189875967800617}
+{"step": 45220, "action_loss_avg": 0.0025626148766605184}
+{"step": 45230, "dynamics_loss_avg": 0.02742648022249341}
+{"step": 45230, "action_loss_avg": 0.0018344334210269153}
+{"step": 45240, "dynamics_loss_avg": 0.03656657543033361}
+{"step": 45240, "action_loss_avg": 0.0026602325262501834}
+{"step": 45250, "loss": 0.0308, "learning_rate": 6.187474710490809e-05}
+{"step": 45250, "dynamics_loss_avg": 0.026043538516387344}
+{"step": 45250, "action_loss_avg": 0.001440758618991822}
+{"step": 45260, "dynamics_loss_avg": 0.02472837995737791}
+{"step": 45260, "action_loss_avg": 0.001517922175116837}
+{"step": 45270, "dynamics_loss_avg": 0.033574433717876676}
+{"step": 45270, "action_loss_avg": 0.00214946826454252}
+{"step": 45280, "dynamics_loss_avg": 0.028358539938926695}
+{"step": 45280, "action_loss_avg": 0.0023495443630963562}
+{"step": 45290, "dynamics_loss_avg": 0.022627826500684022}
+{"step": 45290, "action_loss_avg": 0.0018223854072857647}
+{"step": 45300, "loss": 0.0288, "learning_rate": 6.179442280790202e-05}
+{"step": 45300, "dynamics_loss_avg": 0.03036317229270935}
+{"step": 45300, "action_loss_avg": 0.003259774053003639}
+{"step": 45310, "dynamics_loss_avg": 0.028926376812160016}
+{"step": 45310, "action_loss_avg": 0.0015708886494394392}
+{"step": 45320, "dynamics_loss_avg": 0.03447173610329628}
+{"step": 45320, "action_loss_avg": 0.002312749915290624}
+{"step": 45330, "dynamics_loss_avg": 0.026188800437375905}
+{"step": 45330, "action_loss_avg": 0.0018763815198326484}
+{"step": 45340, "dynamics_loss_avg": 0.040032816026359795}
+{"step": 45340, "action_loss_avg": 0.0028798507642932235}
+{"step": 45350, "loss": 0.0337, "learning_rate": 6.171406626539436e-05}
+{"step": 45350, "dynamics_loss_avg": 0.037080276478081944}
+{"step": 45350, "action_loss_avg": 0.002926022442989051}
+{"step": 45360, "dynamics_loss_avg": 0.03842580430209637}
+{"step": 45360, "action_loss_avg": 0.0029520497424528}
+{"step": 45370, "dynamics_loss_avg": 0.022288241516798736}
+{"step": 45370, "action_loss_avg": 0.0014156293822452427}
+{"step": 45380, "dynamics_loss_avg": 0.02509219227358699}
+{"step": 45380, "action_loss_avg": 0.001730676827719435}
+{"step": 45390, "dynamics_loss_avg": 0.030387144163250925}
+{"step": 45390, "action_loss_avg": 0.002358177973655984}
+{"step": 45400, "loss": 0.0301, "learning_rate": 6.163367769707683e-05}
+{"step": 45400, "dynamics_loss_avg": 0.026929739397019148}
+{"step": 45400, "action_loss_avg": 0.0016272199922241271}
+{"step": 45410, "dynamics_loss_avg": 0.028863776149228214}
+{"step": 45410, "action_loss_avg": 0.0015573136683087797}
+{"step": 45420, "dynamics_loss_avg": 0.03179775318130851}
+{"step": 45420, "action_loss_avg": 0.002048539405222982}
+{"step": 45430, "dynamics_loss_avg": 0.025867872685194016}
+{"step": 45430, "action_loss_avg": 0.002255654882173985}
+{"step": 45440, "dynamics_loss_avg": 0.03395484294742346}
+{"step": 45440, "action_loss_avg": 0.0024006862193346025}
+{"step": 45450, "loss": 0.0312, "learning_rate": 6.15532573227287e-05}
+{"step": 45450, "dynamics_loss_avg": 0.034075970947742465}
+{"step": 45450, "action_loss_avg": 0.0022583879181183875}
+{"step": 45460, "dynamics_loss_avg": 0.025468684220686554}
+{"step": 45460, "action_loss_avg": 0.0019592189346440136}
+{"step": 45470, "dynamics_loss_avg": 0.029906717920675875}
+{"step": 45470, "action_loss_avg": 0.0024901018012315037}
+{"step": 45480, "dynamics_loss_avg": 0.036554324068129064}
+{"step": 45480, "action_loss_avg": 0.0021061445178929715}
+{"step": 45490, "dynamics_loss_avg": 0.03944020764902234}
+{"step": 45490, "action_loss_avg": 0.002171083475695923}
+{"step": 45500, "loss": 0.0331, "learning_rate": 6.147280536221622e-05}
+{"step": 45500, "dynamics_loss_avg": 0.03250924851745367}
+{"step": 45500, "action_loss_avg": 0.0018797054537571967}
+{"step": 45510, "dynamics_loss_avg": 0.04039775533601642}
+{"step": 45510, "action_loss_avg": 0.002798997540958226}
+{"step": 45520, "dynamics_loss_avg": 0.032662765588611364}
+{"step": 45520, "action_loss_avg": 0.0023555236984975636}
+{"step": 45530, "dynamics_loss_avg": 0.03044601702131331}
+{"step": 45530, "action_loss_avg": 0.002054303721524775}
+{"step": 45540, "dynamics_loss_avg": 0.02362911282107234}
+{"step": 45540, "action_loss_avg": 0.0013379078736761585}
+{"step": 45550, "loss": 0.0346, "learning_rate": 6.139232203549197e-05}
+{"step": 45550, "dynamics_loss_avg": 0.034674117155373094}
+{"step": 45550, "action_loss_avg": 0.0025362288462929426}
+{"step": 45560, "dynamics_loss_avg": 0.027869491931051017}
+{"step": 45560, "action_loss_avg": 0.002291360800154507}
+{"step": 45570, "dynamics_loss_avg": 0.03406300200149417}
+{"step": 45570, "action_loss_avg": 0.0026153483428061008}
+{"step": 45580, "dynamics_loss_avg": 0.025049785152077675}
+{"step": 45580, "action_loss_avg": 0.0013642958860145883}
+{"step": 45590, "dynamics_loss_avg": 0.030937728472054005}
+{"step": 45590, "action_loss_avg": 0.0016707874718122184}
+{"step": 45600, "loss": 0.0312, "learning_rate": 6.131180756259428e-05}
+{"step": 45600, "dynamics_loss_avg": 0.030606273002922534}
+{"step": 45600, "action_loss_avg": 0.002749026456149295}
+{"step": 45610, "dynamics_loss_avg": 0.03466637218371034}
+{"step": 45610, "action_loss_avg": 0.00252291327342391}
+{"step": 45620, "dynamics_loss_avg": 0.036799104791134594}
+{"step": 45620, "action_loss_avg": 0.002473011630354449}
+{"step": 45630, "dynamics_loss_avg": 0.03404397200793028}
+{"step": 45630, "action_loss_avg": 0.0016602849180344492}
+{"step": 45640, "dynamics_loss_avg": 0.036172359995543954}
+{"step": 45640, "action_loss_avg": 0.0028110193205066027}
+{"step": 45650, "loss": 0.033, "learning_rate": 6.123126216364665e-05}
+{"step": 45650, "dynamics_loss_avg": 0.04006569348275661}
+{"step": 45650, "action_loss_avg": 0.002482559927739203}
+{"step": 45660, "dynamics_loss_avg": 0.02226831577718258}
+{"step": 45660, "action_loss_avg": 0.001767151732929051}
+{"step": 45670, "dynamics_loss_avg": 0.03535843603312969}
+{"step": 45670, "action_loss_avg": 0.0023232252453453837}
+{"step": 45680, "dynamics_loss_avg": 0.02328981747850776}
+{"step": 45680, "action_loss_avg": 0.0017538276500999928}
+{"step": 45690, "dynamics_loss_avg": 0.03223391929641366}
+{"step": 45690, "action_loss_avg": 0.0021962417406029998}
+{"step": 45700, "loss": 0.03, "learning_rate": 6.115068605885713e-05}
+{"step": 45700, "dynamics_loss_avg": 0.02910951217636466}
+{"step": 45700, "action_loss_avg": 0.0019480917253531516}
+{"step": 45710, "dynamics_loss_avg": 0.030411898717284204}
+{"step": 45710, "action_loss_avg": 0.0014756394230062142}
+{"step": 45720, "dynamics_loss_avg": 0.040792434476315975}
+{"step": 45720, "action_loss_avg": 0.002551083150319755}
+{"step": 45730, "dynamics_loss_avg": 0.02963034980930388}
+{"step": 45730, "action_loss_avg": 0.0022018290357664226}
+{"step": 45740, "dynamics_loss_avg": 0.0368249736726284}
+{"step": 45740, "action_loss_avg": 0.0030164686031639576}
+{"step": 45750, "loss": 0.0354, "learning_rate": 6.107007946851773e-05}
+{"step": 45750, "dynamics_loss_avg": 0.03821840649470687}
+{"step": 45750, "action_loss_avg": 0.0033399579697288573}
+{"step": 45760, "dynamics_loss_avg": 0.027375012077391146}
+{"step": 45760, "action_loss_avg": 0.0013042424398008734}
+{"step": 45770, "dynamics_loss_avg": 0.04261611197143793}
+{"step": 45770, "action_loss_avg": 0.0023136577452532946}
+{"step": 45780, "dynamics_loss_avg": 0.0323893966153264}
+{"step": 45780, "action_loss_avg": 0.0026252025505527853}
+{"step": 45790, "dynamics_loss_avg": 0.04011735823005438}
+{"step": 45790, "action_loss_avg": 0.002457134413998574}
+{"step": 45800, "loss": 0.036, "learning_rate": 6.0989442613003765e-05}
+{"step": 45800, "dynamics_loss_avg": 0.022428660141304135}
+{"step": 45800, "action_loss_avg": 0.001999616844113916}
+{"step": 45810, "dynamics_loss_avg": 0.024704067688435315}
+{"step": 45810, "action_loss_avg": 0.0014374135236721486}
+{"step": 45820, "dynamics_loss_avg": 0.03590493844822049}
+{"step": 45820, "action_loss_avg": 0.00297666591941379}
+{"step": 45830, "dynamics_loss_avg": 0.04056018069386482}
+{"step": 45830, "action_loss_avg": 0.0027143007260747253}
+{"step": 45840, "dynamics_loss_avg": 0.035039616469293836}
+{"step": 45840, "action_loss_avg": 0.001982935192063451}
+{"step": 45850, "loss": 0.0336, "learning_rate": 6.090877571277331e-05}
+{"step": 45850, "dynamics_loss_avg": 0.028297988045960665}
+{"step": 45850, "action_loss_avg": 0.0020950621517840775}
+{"step": 45860, "dynamics_loss_avg": 0.0293204047717154}
+{"step": 45860, "action_loss_avg": 0.0019231284619309007}
+{"step": 45870, "dynamics_loss_avg": 0.02746481546200812}
+{"step": 45870, "action_loss_avg": 0.0020736915001180025}
+{"step": 45880, "dynamics_loss_avg": 0.04100982509553432}
+{"step": 45880, "action_loss_avg": 0.002306010923348367}
+{"step": 45890, "dynamics_loss_avg": 0.034272771794348955}
+{"step": 45890, "action_loss_avg": 0.00283680934808217}
+{"step": 45900, "loss": 0.0348, "learning_rate": 6.082807898836663e-05}
+{"step": 45900, "dynamics_loss_avg": 0.038335103634744884}
+{"step": 45900, "action_loss_avg": 0.003106861482956447}
+{"step": 45910, "dynamics_loss_avg": 0.03031761698657647}
+{"step": 45910, "action_loss_avg": 0.0020940807822626083}
+{"step": 45920, "dynamics_loss_avg": 0.03352066967636347}
+{"step": 45920, "action_loss_avg": 0.0027521663228981196}
+{"step": 45930, "dynamics_loss_avg": 0.028334664646536112}
+{"step": 45930, "action_loss_avg": 0.0019088059198111296}
+{"step": 45940, "dynamics_loss_avg": 0.034236214123666286}
+{"step": 45940, "action_loss_avg": 0.002794708590954542}
+{"step": 45950, "loss": 0.0327, "learning_rate": 6.0747352660405455e-05}
+{"step": 45950, "dynamics_loss_avg": 0.030680096428841352}
+{"step": 45950, "action_loss_avg": 0.0027137336204759777}
+{"step": 45960, "dynamics_loss_avg": 0.0351925952360034}
+{"step": 45960, "action_loss_avg": 0.00231499980436638}
+{"step": 45970, "dynamics_loss_avg": 0.033972001541405915}
+{"step": 45970, "action_loss_avg": 0.002088669635122642}
+{"step": 45980, "dynamics_loss_avg": 0.027692290814593436}
+{"step": 45980, "action_loss_avg": 0.001907166060846066}
+{"step": 45990, "dynamics_loss_avg": 0.041198357939720154}
+{"step": 45990, "action_loss_avg": 0.002965248009422794}
+{"step": 46000, "loss": 0.0343, "learning_rate": 6.066659694959248e-05}
+{"step": 46000, "dynamics_loss_avg": 0.024160318542271852}
+{"step": 46000, "action_loss_avg": 0.0018400091605144553}
+{"step": 46010, "dynamics_loss_avg": 0.02672932166606188}
+{"step": 46010, "action_loss_avg": 0.0019860598986269906}
+{"step": 46020, "dynamics_loss_avg": 0.03091977359727025}
+{"step": 46020, "action_loss_avg": 0.002398863557027653}
+{"step": 46030, "dynamics_loss_avg": 0.028810660634189845}
+{"step": 46030, "action_loss_avg": 0.0014433150936383754}
+{"step": 46040, "dynamics_loss_avg": 0.03462054347619414}
+{"step": 46040, "action_loss_avg": 0.0018658992019481957}
+{"step": 46050, "loss": 0.0313, "learning_rate": 6.058581207671077e-05}
+{"step": 46050, "dynamics_loss_avg": 0.024736793525516988}
+{"step": 46050, "action_loss_avg": 0.0016363283852115274}
+{"step": 46060, "dynamics_loss_avg": 0.029351049475371836}
+{"step": 46060, "action_loss_avg": 0.0015607981447828933}
+{"step": 46070, "dynamics_loss_avg": 0.030136748403310775}
+{"step": 46070, "action_loss_avg": 0.0021629983908496796}
+{"step": 46080, "dynamics_loss_avg": 0.027837275899946688}
+{"step": 46080, "action_loss_avg": 0.0018603170377900825}
+{"step": 46090, "dynamics_loss_avg": 0.02905709226615727}
+{"step": 46090, "action_loss_avg": 0.0026051843160530552}
+{"step": 46100, "loss": 0.0316, "learning_rate": 6.050499826262306e-05}
+{"step": 46100, "dynamics_loss_avg": 0.031891032587736845}
+{"step": 46100, "action_loss_avg": 0.002177069068420678}
+{"step": 46110, "dynamics_loss_avg": 0.03865634016692639}
+{"step": 46110, "action_loss_avg": 0.002661940210964531}
+{"step": 46120, "dynamics_loss_avg": 0.025460954289883375}
+{"step": 46120, "action_loss_avg": 0.0016408393217716365}
+{"step": 46130, "dynamics_loss_avg": 0.025940185645595193}
+{"step": 46130, "action_loss_avg": 0.001442954657250084}
+{"step": 46140, "dynamics_loss_avg": 0.0287611722946167}
+{"step": 46140, "action_loss_avg": 0.0019989768625237048}
+{"step": 46150, "loss": 0.0307, "learning_rate": 6.0424155728271224e-05}
+{"step": 46150, "dynamics_loss_avg": 0.02615047269500792}
+{"step": 46150, "action_loss_avg": 0.0015776053973240779}
+{"step": 46160, "dynamics_loss_avg": 0.03378772642463446}
+{"step": 46160, "action_loss_avg": 0.001887001976137981}
+{"step": 46170, "dynamics_loss_avg": 0.031953991111367944}
+{"step": 46170, "action_loss_avg": 0.0016315406537614763}
+{"step": 46180, "dynamics_loss_avg": 0.03405482750386}
+{"step": 46180, "action_loss_avg": 0.0023769531631842255}
+{"step": 46190, "dynamics_loss_avg": 0.022219725651666522}
+{"step": 46190, "action_loss_avg": 0.0013391124637564644}
+{"step": 46200, "loss": 0.0327, "learning_rate": 6.034328469467566e-05}
+{"step": 46200, "dynamics_loss_avg": 0.0359184555709362}
+{"step": 46200, "action_loss_avg": 0.003023536340333521}
+{"step": 46210, "dynamics_loss_avg": 0.03486061990261078}
+{"step": 46210, "action_loss_avg": 0.002585092408116907}
+{"step": 46220, "dynamics_loss_avg": 0.02948351614177227}
+{"step": 46220, "action_loss_avg": 0.0022073667903896423}
+{"step": 46230, "dynamics_loss_avg": 0.028234096616506575}
+{"step": 46230, "action_loss_avg": 0.0017870756622869522}
+{"step": 46240, "dynamics_loss_avg": 0.02416875949129462}
+{"step": 46240, "action_loss_avg": 0.0011911268316907807}
+{"step": 46250, "loss": 0.0309, "learning_rate": 6.026238538293472e-05}
+{"step": 46250, "dynamics_loss_avg": 0.02659443817101419}
+{"step": 46250, "action_loss_avg": 0.0019610098664998078}
+{"step": 46260, "dynamics_loss_avg": 0.020856559928506612}
+{"step": 46260, "action_loss_avg": 0.001792707765707746}
+{"step": 46270, "dynamics_loss_avg": 0.033469438273459676}
+{"step": 46270, "action_loss_avg": 0.002024797984631732}
+{"step": 46280, "dynamics_loss_avg": 0.02794960169121623}
+{"step": 46280, "action_loss_avg": 0.0015124366036616266}
+{"step": 46290, "dynamics_loss_avg": 0.040608315728604794}
+{"step": 46290, "action_loss_avg": 0.0031746812514029444}
+{"step": 46300, "loss": 0.0301, "learning_rate": 6.0181458014224e-05}
+{"step": 46300, "dynamics_loss_avg": 0.01954246163368225}
+{"step": 46300, "action_loss_avg": 0.0013455460051773117}
+{"step": 46310, "dynamics_loss_avg": 0.028999757114797832}
+{"step": 46310, "action_loss_avg": 0.0016600868024397642}
+{"step": 46320, "dynamics_loss_avg": 0.026943142898380755}
+{"step": 46320, "action_loss_avg": 0.0019784765841905027}
+{"step": 46330, "dynamics_loss_avg": 0.03108458984643221}
+{"step": 46330, "action_loss_avg": 0.0016338940884452313}
+{"step": 46340, "dynamics_loss_avg": 0.028809568006545307}
+{"step": 46340, "action_loss_avg": 0.002513740712311119}
+{"step": 46350, "loss": 0.03, "learning_rate": 6.0100502809795845e-05}
+{"step": 46350, "dynamics_loss_avg": 0.03595296544954181}
+{"step": 46350, "action_loss_avg": 0.0022628122620517387}
+{"step": 46360, "dynamics_loss_avg": 0.025799270207062363}
+{"step": 46360, "action_loss_avg": 0.002633477275958285}
+{"step": 46370, "dynamics_loss_avg": 0.03399549070745707}
+{"step": 46370, "action_loss_avg": 0.0024183254892705007}
+{"step": 46380, "dynamics_loss_avg": 0.027125222701579334}
+{"step": 46380, "action_loss_avg": 0.0016444430337287485}
+{"step": 46390, "dynamics_loss_avg": 0.027527056727558376}
+{"step": 46390, "action_loss_avg": 0.0015753960964502768}
+{"step": 46400, "loss": 0.0312, "learning_rate": 6.00195199909787e-05}
+{"step": 46400, "dynamics_loss_avg": 0.03171553108841181}
+{"step": 46400, "action_loss_avg": 0.002015553432283923}
+{"step": 46410, "dynamics_loss_avg": 0.0412062156945467}
+{"step": 46410, "action_loss_avg": 0.001959232205990702}
+{"step": 46420, "dynamics_loss_avg": 0.03405531849712133}
+{"step": 46420, "action_loss_avg": 0.0024062425480224194}
+{"step": 46430, "dynamics_loss_avg": 0.031127517530694603}
+{"step": 46430, "action_loss_avg": 0.001938592758961022}
+{"step": 46440, "dynamics_loss_avg": 0.03832571404054761}
+{"step": 46440, "action_loss_avg": 0.0026897085073869674}
+{"step": 46450, "loss": 0.0358, "learning_rate": 5.993850977917649e-05}
+{"step": 46450, "dynamics_loss_avg": 0.03365186490118503}
+{"step": 46450, "action_loss_avg": 0.0026806855399627238}
+{"step": 46460, "dynamics_loss_avg": 0.0345329703297466}
+{"step": 46460, "action_loss_avg": 0.0023195229339762593}
+{"step": 46470, "dynamics_loss_avg": 0.03768740091472864}
+{"step": 46470, "action_loss_avg": 0.002335392276290804}
+{"step": 46480, "dynamics_loss_avg": 0.03663303218781948}
+{"step": 46480, "action_loss_avg": 0.0027264646778348833}
+{"step": 46490, "dynamics_loss_avg": 0.03439460285007954}
+{"step": 46490, "action_loss_avg": 0.0028739424073137344}
+{"step": 46500, "loss": 0.0351, "learning_rate": 5.9857472395868055e-05}
+{"step": 46500, "dynamics_loss_avg": 0.027967253979295493}
+{"step": 46500, "action_loss_avg": 0.001626499419216998}
+{"step": 46510, "dynamics_loss_avg": 0.03129967087879777}
+{"step": 46510, "action_loss_avg": 0.0016604569216724485}
+{"step": 46520, "dynamics_loss_avg": 0.03644016990438104}
+{"step": 46520, "action_loss_avg": 0.0030662447854410855}
+{"step": 46530, "dynamics_loss_avg": 0.03649207018315792}
+{"step": 46530, "action_loss_avg": 0.0026882114936597644}
+{"step": 46540, "dynamics_loss_avg": 0.03242390947416425}
+{"step": 46540, "action_loss_avg": 0.002225970197468996}
+{"step": 46550, "loss": 0.0326, "learning_rate": 5.977640806260648e-05}
+{"step": 46550, "dynamics_loss_avg": 0.03033080222085118}
+{"step": 46550, "action_loss_avg": 0.0018595808884128927}
+{"step": 46560, "dynamics_loss_avg": 0.03027177946642041}
+{"step": 46560, "action_loss_avg": 0.0017278226441703737}
+{"step": 46570, "dynamics_loss_avg": 0.025577017106115818}
+{"step": 46570, "action_loss_avg": 0.001685069254017435}
+{"step": 46580, "dynamics_loss_avg": 0.027953764889389277}
+{"step": 46580, "action_loss_avg": 0.0016814361151773483}
+{"step": 46590, "dynamics_loss_avg": 0.030240632034838198}
+{"step": 46590, "action_loss_avg": 0.002007200394291431}
+{"step": 46600, "loss": 0.0308, "learning_rate": 5.969531700101859e-05}
+{"step": 46600, "dynamics_loss_avg": 0.03884090892970562}
+{"step": 46600, "action_loss_avg": 0.002398556179832667}
+{"step": 46610, "dynamics_loss_avg": 0.0272249857429415}
+{"step": 46610, "action_loss_avg": 0.0021681814803741874}
+{"step": 46620, "dynamics_loss_avg": 0.0326982825063169}
+{"step": 46620, "action_loss_avg": 0.0019234595878515393}
+{"step": 46630, "dynamics_loss_avg": 0.030649807211011647}
+{"step": 46630, "action_loss_avg": 0.0019691250286996364}
+{"step": 46640, "dynamics_loss_avg": 0.035431184666231276}
+{"step": 46640, "action_loss_avg": 0.0031093798112124204}
+{"step": 46650, "loss": 0.0326, "learning_rate": 5.961419943280422e-05}
+{"step": 46650, "dynamics_loss_avg": 0.03181998766958714}
+{"step": 46650, "action_loss_avg": 0.002413583057932556}
+{"step": 46660, "dynamics_loss_avg": 0.027510828617960215}
+{"step": 46660, "action_loss_avg": 0.00240972243482247}
+{"step": 46670, "dynamics_loss_avg": 0.028616347443312408}
+{"step": 46670, "action_loss_avg": 0.0017540593165904284}
+{"step": 46680, "dynamics_loss_avg": 0.02609932776540518}
+{"step": 46680, "action_loss_avg": 0.001889293867861852}
+{"step": 46690, "dynamics_loss_avg": 0.028172837663441898}
+{"step": 46690, "action_loss_avg": 0.00232500079437159}
+{"step": 46700, "loss": 0.0312, "learning_rate": 5.953305557973572e-05}
+{"step": 46700, "dynamics_loss_avg": 0.03395262882113457}
+{"step": 46700, "action_loss_avg": 0.0024636105401441453}
+{"step": 46710, "dynamics_loss_avg": 0.02692314554005861}
+{"step": 46710, "action_loss_avg": 0.0014536066330038012}
+{"step": 46720, "dynamics_loss_avg": 0.03412622632458806}
+{"step": 46720, "action_loss_avg": 0.002584999118698761}
+{"step": 46730, "dynamics_loss_avg": 0.029983137175440787}
+{"step": 46730, "action_loss_avg": 0.0016401340428274125}
+{"step": 46740, "dynamics_loss_avg": 0.03175584608688951}
+{"step": 46740, "action_loss_avg": 0.002239596960134804}
+{"step": 46750, "loss": 0.0322, "learning_rate": 5.945188566365729e-05}
+{"step": 46750, "dynamics_loss_avg": 0.030612273886799813}
+{"step": 46750, "action_loss_avg": 0.0020712305442430077}
+{"step": 46760, "dynamics_loss_avg": 0.03860412938520312}
+{"step": 46760, "action_loss_avg": 0.0022382177121471614}
+{"step": 46770, "dynamics_loss_avg": 0.03617001697421074}
+{"step": 46770, "action_loss_avg": 0.0023571446188725533}
+{"step": 46780, "dynamics_loss_avg": 0.03386885030195117}
+{"step": 46780, "action_loss_avg": 0.002023601485416293}
+{"step": 46790, "dynamics_loss_avg": 0.029774693213403224}
+{"step": 46790, "action_loss_avg": 0.0026982133858837187}
+{"step": 46800, "loss": 0.0334, "learning_rate": 5.937068990648438e-05}
+{"step": 46800, "dynamics_loss_avg": 0.02710195416584611}
+{"step": 46800, "action_loss_avg": 0.00148271206417121}
+{"step": 46810, "dynamics_loss_avg": 0.029076911695301532}
+{"step": 46810, "action_loss_avg": 0.002073794649913907}
+{"step": 46820, "dynamics_loss_avg": 0.03308897130191326}
+{"step": 46820, "action_loss_avg": 0.0024682062037754806}
+{"step": 46830, "dynamics_loss_avg": 0.02337206285446882}
+{"step": 46830, "action_loss_avg": 0.0014938186388462782}
+{"step": 46840, "dynamics_loss_avg": 0.03198264483362436}
+{"step": 46840, "action_loss_avg": 0.0019055451906751842}
+{"step": 46850, "loss": 0.0308, "learning_rate": 5.928946853020309e-05}
+{"step": 46850, "dynamics_loss_avg": 0.029207046423107386}
+{"step": 46850, "action_loss_avg": 0.0019488707621349022}
+{"step": 46860, "dynamics_loss_avg": 0.03256883015856147}
+{"step": 46860, "action_loss_avg": 0.0026171757257543505}
+{"step": 46870, "dynamics_loss_avg": 0.03425767300650477}
+{"step": 46870, "action_loss_avg": 0.00253907167352736}
+{"step": 46880, "dynamics_loss_avg": 0.02436586688272655}
+{"step": 46880, "action_loss_avg": 0.0014931453100871296}
+{"step": 46890, "dynamics_loss_avg": 0.036654780991375445}
+{"step": 46890, "action_loss_avg": 0.0023621709726285188}
+{"step": 46900, "loss": 0.0338, "learning_rate": 5.920822175686952e-05}
+{"step": 46900, "dynamics_loss_avg": 0.03601432908326387}
+{"step": 46900, "action_loss_avg": 0.003019788544042967}
+{"step": 46910, "dynamics_loss_avg": 0.027488025650382043}
+{"step": 46910, "action_loss_avg": 0.0017987071361858398}
+{"step": 46920, "dynamics_loss_avg": 0.02484328639693558}
+{"step": 46920, "action_loss_avg": 0.0021801588591188192}
+{"step": 46930, "dynamics_loss_avg": 0.033607225865125656}
+{"step": 46930, "action_loss_avg": 0.0023253284161910415}
+{"step": 46940, "dynamics_loss_avg": 0.03188631338998675}
+{"step": 46940, "action_loss_avg": 0.0024179123574867845}
+{"step": 46950, "loss": 0.0323, "learning_rate": 5.912694980860931e-05}
+{"step": 46950, "dynamics_loss_avg": 0.02595349056646228}
+{"step": 46950, "action_loss_avg": 0.0019136667717248202}
+{"step": 46960, "dynamics_loss_avg": 0.03720581345260143}
+{"step": 46960, "action_loss_avg": 0.002065909668453969}
+{"step": 46970, "dynamics_loss_avg": 0.03406590353697538}
+{"step": 46970, "action_loss_avg": 0.00191017062170431}
+{"step": 46980, "dynamics_loss_avg": 0.021515265107154846}
+{"step": 46980, "action_loss_avg": 0.0014869425154756754}
+{"step": 46990, "dynamics_loss_avg": 0.02975706560537219}
+{"step": 46990, "action_loss_avg": 0.0018462501058820636}
+{"step": 47000, "loss": 0.0319, "learning_rate": 5.9045652907616835e-05}
+{"step": 47000, "dynamics_loss_avg": 0.03245797101408243}
+{"step": 47000, "action_loss_avg": 0.0019498141016811132}
+{"step": 47010, "dynamics_loss_avg": 0.02759929746389389}
+{"step": 47010, "action_loss_avg": 0.0020509134919848293}
+{"step": 47020, "dynamics_loss_avg": 0.02942105568945408}
+{"step": 47020, "action_loss_avg": 0.002681305771693587}
+{"step": 47030, "dynamics_loss_avg": 0.026511532347649337}
+{"step": 47030, "action_loss_avg": 0.0015759037749376148}
+{"step": 47040, "dynamics_loss_avg": 0.03157766638323665}
+{"step": 47040, "action_loss_avg": 0.002225317948614247}
+{"step": 47050, "loss": 0.0313, "learning_rate": 5.896433127615471e-05}
+{"step": 47050, "dynamics_loss_avg": 0.03145405100658536}
+{"step": 47050, "action_loss_avg": 0.0024875103059457614}
+{"step": 47060, "dynamics_loss_avg": 0.02263232246041298}
+{"step": 47060, "action_loss_avg": 0.0013202515023294837}
+{"step": 47070, "dynamics_loss_avg": 0.027343564480543137}
+{"step": 47070, "action_loss_avg": 0.0016577538917772472}
+{"step": 47080, "dynamics_loss_avg": 0.03820001361891627}
+{"step": 47080, "action_loss_avg": 0.0019825306604616343}
+{"step": 47090, "dynamics_loss_avg": 0.024684982560575008}
+{"step": 47090, "action_loss_avg": 0.001452876499388367}
+{"step": 47100, "loss": 0.0297, "learning_rate": 5.888298513655318e-05}
+{"step": 47100, "dynamics_loss_avg": 0.03424735423177481}
+{"step": 47100, "action_loss_avg": 0.0019449554791208356}
+{"step": 47110, "dynamics_loss_avg": 0.028523361217230557}
+{"step": 47110, "action_loss_avg": 0.0017088194726966321}
+{"step": 47120, "dynamics_loss_avg": 0.03517538169398904}
+{"step": 47120, "action_loss_avg": 0.002486813208088279}
+{"step": 47130, "dynamics_loss_avg": 0.0338937733322382}
+{"step": 47130, "action_loss_avg": 0.002263371564913541}
+{"step": 47140, "dynamics_loss_avg": 0.04266781471669674}
+{"step": 47140, "action_loss_avg": 0.002798996539786458}
+{"step": 47150, "loss": 0.0346, "learning_rate": 5.8801614711209474e-05}
+{"step": 47150, "dynamics_loss_avg": 0.025353079196065664}
+{"step": 47150, "action_loss_avg": 0.0016956916311755776}
+{"step": 47160, "dynamics_loss_avg": 0.030609446484595536}
+{"step": 47160, "action_loss_avg": 0.001755533620598726}
+{"step": 47170, "dynamics_loss_avg": 0.028686385694891216}
+{"step": 47170, "action_loss_avg": 0.0027690941467881204}
+{"step": 47180, "dynamics_loss_avg": 0.02795878639444709}
+{"step": 47180, "action_loss_avg": 0.002094605314778164}
+{"step": 47190, "dynamics_loss_avg": 0.033140360936522485}
+{"step": 47190, "action_loss_avg": 0.002033208729699254}
+{"step": 47200, "loss": 0.0314, "learning_rate": 5.872022022258725e-05}
+{"step": 47200, "dynamics_loss_avg": 0.02818841114640236}
+{"step": 47200, "action_loss_avg": 0.0016973590827547014}
+{"step": 47210, "dynamics_loss_avg": 0.04029416488483548}
+{"step": 47210, "action_loss_avg": 0.003272097685839981}
+{"step": 47220, "dynamics_loss_avg": 0.0229011376388371}
+{"step": 47220, "action_loss_avg": 0.001618397847050801}
+{"step": 47230, "dynamics_loss_avg": 0.022605127282440664}
+{"step": 47230, "action_loss_avg": 0.0012068028387147932}
+{"step": 47240, "dynamics_loss_avg": 0.033249299973249435}
+{"step": 47240, "action_loss_avg": 0.002443154715001583}
+{"step": 47250, "loss": 0.0306, "learning_rate": 5.863880189321592e-05}
+{"step": 47250, "dynamics_loss_avg": 0.025270513771101833}
+{"step": 47250, "action_loss_avg": 0.0014104089961620048}
+{"step": 47260, "dynamics_loss_avg": 0.028698501363396644}
+{"step": 47260, "action_loss_avg": 0.001896809003665112}
+{"step": 47270, "dynamics_loss_avg": 0.025857548229396343}
+{"step": 47270, "action_loss_avg": 0.00131300917128101}
+{"step": 47280, "dynamics_loss_avg": 0.038602125458419324}
+{"step": 47280, "action_loss_avg": 0.0023309226089622825}
+{"step": 47290, "dynamics_loss_avg": 0.02588986661285162}
+{"step": 47290, "action_loss_avg": 0.0011314904550090432}
+{"step": 47300, "loss": 0.031, "learning_rate": 5.8557359945690084e-05}
+{"step": 47300, "dynamics_loss_avg": 0.02838208582252264}
+{"step": 47300, "action_loss_avg": 0.0012273485364858062}
+{"step": 47310, "dynamics_loss_avg": 0.035597323812544344}
+{"step": 47310, "action_loss_avg": 0.0019396437099203467}
+{"step": 47320, "dynamics_loss_avg": 0.02466728361323476}
+{"step": 47320, "action_loss_avg": 0.001425099722109735}
+{"step": 47330, "dynamics_loss_avg": 0.02909845095127821}
+{"step": 47330, "action_loss_avg": 0.002019609499257058}
+{"step": 47340, "dynamics_loss_avg": 0.014598892373032867}
+{"step": 47340, "action_loss_avg": 0.001104579605453182}
+{"step": 47350, "loss": 0.028, "learning_rate": 5.847589460266891e-05}
+{"step": 47350, "dynamics_loss_avg": 0.03920502969995141}
+{"step": 47350, "action_loss_avg": 0.0021960099635180085}
+{"step": 47360, "dynamics_loss_avg": 0.027982735354453326}
+{"step": 47360, "action_loss_avg": 0.0021879370120586827}
+{"step": 47370, "dynamics_loss_avg": 0.03499514935538173}
+{"step": 47370, "action_loss_avg": 0.0020339002134278418}
+{"step": 47380, "dynamics_loss_avg": 0.02775551248341799}
+{"step": 47380, "action_loss_avg": 0.0017562710563652217}
+{"step": 47390, "dynamics_loss_avg": 0.02529539247043431}
+{"step": 47390, "action_loss_avg": 0.0015871975745540112}
+{"step": 47400, "loss": 0.0307, "learning_rate": 5.839440608687554e-05}
+{"step": 47400, "dynamics_loss_avg": 0.03150873882696033}
+{"step": 47400, "action_loss_avg": 0.001854187122080475}
+{"step": 47410, "dynamics_loss_avg": 0.03598394952714443}
+{"step": 47410, "action_loss_avg": 0.0020669559366069735}
+{"step": 47420, "dynamics_loss_avg": 0.024157524574548006}
+{"step": 47420, "action_loss_avg": 0.0012633899896172807}
+{"step": 47430, "dynamics_loss_avg": 0.024706633388996126}
+{"step": 47430, "action_loss_avg": 0.0015483188210055232}
+{"step": 47440, "dynamics_loss_avg": 0.03577718148007989}
+{"step": 47440, "action_loss_avg": 0.0025550053745973856}
+{"step": 47450, "loss": 0.0289, "learning_rate": 5.831289462109648e-05}
+{"step": 47450, "dynamics_loss_avg": 0.029803840350359677}
+{"step": 47450, "action_loss_avg": 0.002002962480764836}
+{"step": 47460, "dynamics_loss_avg": 0.03388309739530086}
+{"step": 47460, "action_loss_avg": 0.0019495624816045164}
+{"step": 47470, "dynamics_loss_avg": 0.03151643695309758}
+{"step": 47470, "action_loss_avg": 0.0018653306120540946}
+{"step": 47480, "dynamics_loss_avg": 0.025635646656155586}
+{"step": 47480, "action_loss_avg": 0.0021427024563308804}
+{"step": 47490, "dynamics_loss_avg": 0.019204369373619558}
+{"step": 47490, "action_loss_avg": 0.001435347375809215}
+{"step": 47500, "loss": 0.0306, "learning_rate": 5.8231360428180945e-05}
+{"step": 47500, "dynamics_loss_avg": 0.026936429366469384}
+{"step": 47500, "action_loss_avg": 0.0017866975802462548}
+{"step": 47510, "dynamics_loss_avg": 0.03176063345745206}
+{"step": 47510, "action_loss_avg": 0.0016170860268175601}
+{"step": 47520, "dynamics_loss_avg": 0.03057106616906822}
+{"step": 47520, "action_loss_avg": 0.0015161702875047922}
+{"step": 47530, "dynamics_loss_avg": 0.031040455773472787}
+{"step": 47530, "action_loss_avg": 0.002008333947742358}
+{"step": 47540, "dynamics_loss_avg": 0.02951486869715154}
+{"step": 47540, "action_loss_avg": 0.002411585516529158}
+{"step": 47550, "loss": 0.033, "learning_rate": 5.814980373104033e-05}
+{"step": 47550, "dynamics_loss_avg": 0.03459921991452575}
+{"step": 47550, "action_loss_avg": 0.001958279119571671}
+{"step": 47560, "dynamics_loss_avg": 0.031026098411530256}
+{"step": 47560, "action_loss_avg": 0.0018342815281357616}
+{"step": 47570, "dynamics_loss_avg": 0.02894152980297804}
+{"step": 47570, "action_loss_avg": 0.0023912519856821744}
+{"step": 47580, "dynamics_loss_avg": 0.02847982095554471}
+{"step": 47580, "action_loss_avg": 0.0019102932419627905}
+{"step": 47590, "dynamics_loss_avg": 0.03631480811163783}
+{"step": 47590, "action_loss_avg": 0.0016629833029583097}
+{"step": 47600, "loss": 0.0316, "learning_rate": 5.8068224752647497e-05}
+{"step": 47600, "dynamics_loss_avg": 0.027277231495827437}
+{"step": 47600, "action_loss_avg": 0.0029271294013597073}
+{"step": 47610, "dynamics_loss_avg": 0.028276570327579974}
+{"step": 47610, "action_loss_avg": 0.0014930385601473971}
+{"step": 47620, "dynamics_loss_avg": 0.03022017697803676}
+{"step": 47620, "action_loss_avg": 0.0023745263722958045}
+{"step": 47630, "dynamics_loss_avg": 0.02898708628490567}
+{"step": 47630, "action_loss_avg": 0.0018762916879495606}
+{"step": 47640, "dynamics_loss_avg": 0.030005164630711078}
+{"step": 47640, "action_loss_avg": 0.0018879379611462354}
+{"step": 47650, "loss": 0.0311, "learning_rate": 5.798662371603628e-05}
+{"step": 47650, "dynamics_loss_avg": 0.029613541346043347}
+{"step": 47650, "action_loss_avg": 0.0020043564378283917}
+{"step": 47660, "dynamics_loss_avg": 0.03309137364849448}
+{"step": 47660, "action_loss_avg": 0.002800408564507961}
+{"step": 47670, "dynamics_loss_avg": 0.03574570063501596}
+{"step": 47670, "action_loss_avg": 0.0023731634428258985}
+{"step": 47680, "dynamics_loss_avg": 0.035984086245298384}
+{"step": 47680, "action_loss_avg": 0.002284274552948773}
+{"step": 47690, "dynamics_loss_avg": 0.02675061151385307}
+{"step": 47690, "action_loss_avg": 0.0019090628367848695}
+{"step": 47700, "loss": 0.0349, "learning_rate": 5.790500084430078e-05}
+{"step": 47700, "dynamics_loss_avg": 0.037357186526060106}
+{"step": 47700, "action_loss_avg": 0.0022817522229161115}
+{"step": 47710, "dynamics_loss_avg": 0.03495029602199793}
+{"step": 47710, "action_loss_avg": 0.0019307601673062892}
+{"step": 47720, "dynamics_loss_avg": 0.028569188341498374}
+{"step": 47720, "action_loss_avg": 0.0020854637608863414}
+{"step": 47730, "dynamics_loss_avg": 0.03452105224132538}
+{"step": 47730, "action_loss_avg": 0.00252508056582883}
+{"step": 47740, "dynamics_loss_avg": 0.03526882492005825}
+{"step": 47740, "action_loss_avg": 0.002724874019622803}
+{"step": 47750, "loss": 0.0338, "learning_rate": 5.782335636059484e-05}
+{"step": 47750, "dynamics_loss_avg": 0.027688506152480842}
+{"step": 47750, "action_loss_avg": 0.0018100093235261737}
+{"step": 47760, "dynamics_loss_avg": 0.04349498227238655}
+{"step": 47760, "action_loss_avg": 0.0033785358304157854}
+{"step": 47770, "dynamics_loss_avg": 0.036076413840055464}
+{"step": 47770, "action_loss_avg": 0.0024615667934995145}
+{"step": 47780, "dynamics_loss_avg": 0.030157236848026514}
+{"step": 47780, "action_loss_avg": 0.0020393908314872535}
+{"step": 47790, "dynamics_loss_avg": 0.022531882952898742}
+{"step": 47790, "action_loss_avg": 0.0017070177593268455}
+{"step": 47800, "loss": 0.0334, "learning_rate": 5.774169048813134e-05}
+{"step": 47800, "dynamics_loss_avg": 0.045368367433547975}
+{"step": 47800, "action_loss_avg": 0.0032182555296458304}
+{"step": 47810, "dynamics_loss_avg": 0.03300882205367088}
+{"step": 47810, "action_loss_avg": 0.0025282161659561098}
+{"step": 47820, "dynamics_loss_avg": 0.030156617611646654}
+{"step": 47820, "action_loss_avg": 0.0018546261446317658}
+{"step": 47830, "dynamics_loss_avg": 0.03932015467435122}
+{"step": 47830, "action_loss_avg": 0.00231413037981838}
+{"step": 47840, "dynamics_loss_avg": 0.035988818109035495}
+{"step": 47840, "action_loss_avg": 0.00289940593065694}
+{"step": 47850, "loss": 0.0339, "learning_rate": 5.7660003450181655e-05}
+{"step": 47850, "dynamics_loss_avg": 0.03517072517424822}
+{"step": 47850, "action_loss_avg": 0.0021149957552552222}
+{"step": 47860, "dynamics_loss_avg": 0.025142515264451503}
+{"step": 47860, "action_loss_avg": 0.002224844018928707}
+{"step": 47870, "dynamics_loss_avg": 0.030022314563393594}
+{"step": 47870, "action_loss_avg": 0.0016086975228972733}
+{"step": 47880, "dynamics_loss_avg": 0.02112503396347165}
+{"step": 47880, "action_loss_avg": 0.001289694121805951}
+{"step": 47890, "dynamics_loss_avg": 0.028754438180476426}
+{"step": 47890, "action_loss_avg": 0.00129554919549264}
+{"step": 47900, "loss": 0.03, "learning_rate": 5.757829547007504e-05}
+{"step": 47900, "dynamics_loss_avg": 0.026390308467671274}
+{"step": 47900, "action_loss_avg": 0.0016110811760881917}
+{"step": 47910, "dynamics_loss_avg": 0.02399428579956293}
+{"step": 47910, "action_loss_avg": 0.0019610450486652552}
+{"step": 47920, "dynamics_loss_avg": 0.026860443875193596}
+{"step": 47920, "action_loss_avg": 0.0018831653986126184}
+{"step": 47930, "dynamics_loss_avg": 0.03695223964750767}
+{"step": 47930, "action_loss_avg": 0.002719715744024143}
+{"step": 47940, "dynamics_loss_avg": 0.03133448357693851}
+{"step": 47940, "action_loss_avg": 0.0019100801218883134}
+{"step": 47950, "loss": 0.0293, "learning_rate": 5.749656677119798e-05}
+{"step": 47950, "dynamics_loss_avg": 0.027564405277371407}
+{"step": 47950, "action_loss_avg": 0.0016228513442911208}
+{"step": 47960, "dynamics_loss_avg": 0.04163892325013876}
+{"step": 47960, "action_loss_avg": 0.002537426113849506}
+{"step": 47970, "dynamics_loss_avg": 0.026753844087943436}
+{"step": 47970, "action_loss_avg": 0.0018501874641515315}
+{"step": 47980, "dynamics_loss_avg": 0.034508079290390015}
+{"step": 47980, "action_loss_avg": 0.0018979104468598961}
+{"step": 47990, "dynamics_loss_avg": 0.030900032445788383}
+{"step": 47990, "action_loss_avg": 0.0018793613533489406}
+{"step": 48000, "loss": 0.0334, "learning_rate": 5.741481757699364e-05}
+{"step": 48000, "dynamics_loss_avg": 0.030492029432207347}
+{"step": 48000, "action_loss_avg": 0.0022938669600989668}
+{"step": 48010, "dynamics_loss_avg": 0.03854077998548746}
+{"step": 48010, "action_loss_avg": 0.0018359475361648947}
+{"step": 48020, "dynamics_loss_avg": 0.03292119894176722}
+{"step": 48020, "action_loss_avg": 0.0018795815005432815}
+{"step": 48030, "dynamics_loss_avg": 0.030646630004048346}
+{"step": 48030, "action_loss_avg": 0.0015461263654287904}
+{"step": 48040, "dynamics_loss_avg": 0.03691162832546979}
+{"step": 48040, "action_loss_avg": 0.0035490340291289614}
+{"step": 48050, "loss": 0.0336, "learning_rate": 5.733304811096116e-05}
+{"step": 48050, "dynamics_loss_avg": 0.01870694849640131}
+{"step": 48050, "action_loss_avg": 0.0012377086473861708}
+{"step": 48060, "dynamics_loss_avg": 0.02010006010532379}
+{"step": 48060, "action_loss_avg": 0.001749120090971701}
+{"step": 48070, "dynamics_loss_avg": 0.034033309668302536}
+{"step": 48070, "action_loss_avg": 0.002341755561064929}
+{"step": 48080, "dynamics_loss_avg": 0.03853188478387892}
+{"step": 48080, "action_loss_avg": 0.002288012724602595}
+{"step": 48090, "dynamics_loss_avg": 0.028236961364746092}
+{"step": 48090, "action_loss_avg": 0.001435158192180097}
+{"step": 48100, "loss": 0.0315, "learning_rate": 5.7251258596655155e-05}
+{"step": 48100, "dynamics_loss_avg": 0.033585000317543745}
+{"step": 48100, "action_loss_avg": 0.002127414318965748}
+{"step": 48110, "dynamics_loss_avg": 0.023858090676367284}
+{"step": 48110, "action_loss_avg": 0.001976268511498347}
+{"step": 48120, "dynamics_loss_avg": 0.03653434021398425}
+{"step": 48120, "action_loss_avg": 0.002522091177524999}
+{"step": 48130, "dynamics_loss_avg": 0.017089288495481015}
+{"step": 48130, "action_loss_avg": 0.0009412294428329914}
+{"step": 48140, "dynamics_loss_avg": 0.027365642599761486}
+{"step": 48140, "action_loss_avg": 0.0017443081800593064}
+{"step": 48150, "loss": 0.028, "learning_rate": 5.716944925768505e-05}
+{"step": 48150, "dynamics_loss_avg": 0.024999824725091456}
+{"step": 48150, "action_loss_avg": 0.0016839469317346811}
+{"step": 48160, "dynamics_loss_avg": 0.035815063212066886}
+{"step": 48160, "action_loss_avg": 0.001578899717424065}
+{"step": 48170, "dynamics_loss_avg": 0.028964478708803653}
+{"step": 48170, "action_loss_avg": 0.0024674517451785507}
+{"step": 48180, "dynamics_loss_avg": 0.042643398698419335}
+{"step": 48180, "action_loss_avg": 0.0025693393603432924}
+{"step": 48190, "dynamics_loss_avg": 0.03283885517157614}
+{"step": 48190, "action_loss_avg": 0.001955251712934114}
+{"step": 48200, "loss": 0.0353, "learning_rate": 5.708762031771442e-05}
+{"step": 48200, "dynamics_loss_avg": 0.029631595872342587}
+{"step": 48200, "action_loss_avg": 0.0019186842255294323}
+{"step": 48210, "dynamics_loss_avg": 0.019859680719673634}
+{"step": 48210, "action_loss_avg": 0.0016228460444835946}
+{"step": 48220, "dynamics_loss_avg": 0.031247180700302125}
+{"step": 48220, "action_loss_avg": 0.0021998807846102864}
+{"step": 48230, "dynamics_loss_avg": 0.01957962093874812}
+{"step": 48230, "action_loss_avg": 0.0011418001537094823}
+{"step": 48240, "dynamics_loss_avg": 0.03166589690372348}
+{"step": 48240, "action_loss_avg": 0.002287732466356829}
+{"step": 48250, "loss": 0.0277, "learning_rate": 5.7005772000460514e-05}
+{"step": 48250, "dynamics_loss_avg": 0.03308288939297199}
+{"step": 48250, "action_loss_avg": 0.0019784536445513366}
+{"step": 48260, "dynamics_loss_avg": 0.038897177949547765}
+{"step": 48260, "action_loss_avg": 0.0023629363684449347}
+{"step": 48270, "dynamics_loss_avg": 0.02531786123290658}
+{"step": 48270, "action_loss_avg": 0.0015388424275442959}
+{"step": 48280, "dynamics_loss_avg": 0.026774036046117545}
+{"step": 48280, "action_loss_avg": 0.0020111691963393243}
+{"step": 48290, "dynamics_loss_avg": 0.03312988076359034}
+{"step": 48290, "action_loss_avg": 0.0016622387513052673}
+{"step": 48300, "loss": 0.0324, "learning_rate": 5.692390452969344e-05}
+{"step": 48300, "dynamics_loss_avg": 0.030962582118809222}
+{"step": 48300, "action_loss_avg": 0.0024535074946470557}
+{"step": 48310, "dynamics_loss_avg": 0.027360515668988228}
+{"step": 48310, "action_loss_avg": 0.001632804301334545}
+{"step": 48320, "dynamics_loss_avg": 0.02479728776961565}
+{"step": 48320, "action_loss_avg": 0.0012363544257823378}
+{"step": 48330, "dynamics_loss_avg": 0.032521574292331934}
+{"step": 48330, "action_loss_avg": 0.002608075499301776}
+{"step": 48340, "dynamics_loss_avg": 0.032834808947518467}
+{"step": 48340, "action_loss_avg": 0.002391159994294867}
+{"step": 48350, "loss": 0.0319, "learning_rate": 5.6842018129235786e-05}
+{"step": 48350, "dynamics_loss_avg": 0.025227112881839275}
+{"step": 48350, "action_loss_avg": 0.0019971804111264648}
+{"step": 48360, "dynamics_loss_avg": 0.024075816106051206}
+{"step": 48360, "action_loss_avg": 0.0016794858791399747}
+{"step": 48370, "dynamics_loss_avg": 0.027608608128502965}
+{"step": 48370, "action_loss_avg": 0.0016571954009123146}
+{"step": 48380, "dynamics_loss_avg": 0.026353792194277047}
+{"step": 48380, "action_loss_avg": 0.001256725611165166}
+{"step": 48390, "dynamics_loss_avg": 0.03589279558509588}
+{"step": 48390, "action_loss_avg": 0.00252417954034172}
+{"step": 48400, "loss": 0.0301, "learning_rate": 5.6760113022961824e-05}
+{"step": 48400, "dynamics_loss_avg": 0.028105408977717163}
+{"step": 48400, "action_loss_avg": 0.0020364695985335855}
+{"step": 48410, "dynamics_loss_avg": 0.03421297464519739}
+{"step": 48410, "action_loss_avg": 0.0018346761527936906}
+{"step": 48420, "dynamics_loss_avg": 0.037377608474344015}
+{"step": 48420, "action_loss_avg": 0.0029807240498485044}
+{"step": 48430, "dynamics_loss_avg": 0.025655130250379445}
+{"step": 48430, "action_loss_avg": 0.001333956333110109}
+{"step": 48440, "dynamics_loss_avg": 0.035405044257640836}
+{"step": 48440, "action_loss_avg": 0.0020865166967269032}
+{"step": 48450, "loss": 0.0298, "learning_rate": 5.667818943479699e-05}
+{"step": 48450, "dynamics_loss_avg": 0.021201541274785997}
+{"step": 48450, "action_loss_avg": 0.0011744899180484935}
+{"step": 48460, "dynamics_loss_avg": 0.026740406663157044}
+{"step": 48460, "action_loss_avg": 0.0022806699911598117}
+{"step": 48470, "dynamics_loss_avg": 0.029600091138854624}
+{"step": 48470, "action_loss_avg": 0.0019098303804639728}
+{"step": 48480, "dynamics_loss_avg": 0.026946286018937827}
+{"step": 48480, "action_loss_avg": 0.0015744775882922113}
+{"step": 48490, "dynamics_loss_avg": 0.026195199321955444}
+{"step": 48490, "action_loss_avg": 0.0018397562351310625}
+{"step": 48500, "loss": 0.0321, "learning_rate": 5.6596247588717254e-05}
+{"step": 48500, "dynamics_loss_avg": 0.026145644905045628}
+{"step": 48500, "action_loss_avg": 0.0020308022270910443}
+{"step": 48510, "dynamics_loss_avg": 0.026842497289180756}
+{"step": 48510, "action_loss_avg": 0.0018434598750900477}
+{"step": 48520, "dynamics_loss_avg": 0.029213277343660592}
+{"step": 48520, "action_loss_avg": 0.0015499257599003613}
+{"step": 48530, "dynamics_loss_avg": 0.033694851119071244}
+{"step": 48530, "action_loss_avg": 0.0020737947372253982}
+{"step": 48540, "dynamics_loss_avg": 0.0333472341299057}
+{"step": 48540, "action_loss_avg": 0.0021086812950670717}
+{"step": 48550, "loss": 0.0309, "learning_rate": 5.651428770874848e-05}
+{"step": 48550, "dynamics_loss_avg": 0.0272901832126081}
+{"step": 48550, "action_loss_avg": 0.0021576519589871167}
+{"step": 48560, "dynamics_loss_avg": 0.02859321581199765}
+{"step": 48560, "action_loss_avg": 0.0014606435899622739}
+{"step": 48570, "dynamics_loss_avg": 0.030219519045203924}
+{"step": 48570, "action_loss_avg": 0.00148339974693954}
+{"step": 48580, "dynamics_loss_avg": 0.037573618534952405}
+{"step": 48580, "action_loss_avg": 0.0021647716755978765}
+{"step": 48590, "dynamics_loss_avg": 0.038997091446071865}
+{"step": 48590, "action_loss_avg": 0.0023677300428971647}
+{"step": 48600, "loss": 0.0338, "learning_rate": 5.643231001896586e-05}
+{"step": 48600, "dynamics_loss_avg": 0.03165042018517852}
+{"step": 48600, "action_loss_avg": 0.001508408458903432}
+{"step": 48610, "dynamics_loss_avg": 0.02508912868797779}
+{"step": 48610, "action_loss_avg": 0.0016753611154854298}
+{"step": 48620, "dynamics_loss_avg": 0.018996442155912518}
+{"step": 48620, "action_loss_avg": 0.0013600845239125192}
+{"step": 48630, "dynamics_loss_avg": 0.031412341818213466}
+{"step": 48630, "action_loss_avg": 0.0016921816917601974}
+{"step": 48640, "dynamics_loss_avg": 0.03378599863499403}
+{"step": 48640, "action_loss_avg": 0.0030452931358013304}
+{"step": 48650, "loss": 0.0291, "learning_rate": 5.635031474349327e-05}
+{"step": 48650, "dynamics_loss_avg": 0.028336219117045404}
+{"step": 48650, "action_loss_avg": 0.0015002020547399298}
+{"step": 48660, "dynamics_loss_avg": 0.02683708434924483}
+{"step": 48660, "action_loss_avg": 0.001542329351650551}
+{"step": 48670, "dynamics_loss_avg": 0.027015914022922517}
+{"step": 48670, "action_loss_avg": 0.001649877376621589}
+{"step": 48680, "dynamics_loss_avg": 0.029284252505749463}
+{"step": 48680, "action_loss_avg": 0.0017205700278282166}
+{"step": 48690, "dynamics_loss_avg": 0.03366413153707981}
+{"step": 48690, "action_loss_avg": 0.0025349981035105882}
+{"step": 48700, "loss": 0.0301, "learning_rate": 5.626830210650266e-05}
+{"step": 48700, "dynamics_loss_avg": 0.03209435977041721}
+{"step": 48700, "action_loss_avg": 0.002214423683471978}
+{"step": 48710, "dynamics_loss_avg": 0.03748951833695173}
+{"step": 48710, "action_loss_avg": 0.0020381115115014835}
+{"step": 48720, "dynamics_loss_avg": 0.030215276358649134}
+{"step": 48720, "action_loss_avg": 0.0016066353593487293}
+{"step": 48730, "dynamics_loss_avg": 0.02839132910594344}
+{"step": 48730, "action_loss_avg": 0.002102320350240916}
+{"step": 48740, "dynamics_loss_avg": 0.035645412746816874}
+{"step": 48740, "action_loss_avg": 0.0029534074565162882}
+{"step": 48750, "loss": 0.0318, "learning_rate": 5.618627233221344e-05}
+{"step": 48750, "dynamics_loss_avg": 0.02681971648707986}
+{"step": 48750, "action_loss_avg": 0.00165114855626598}
+{"step": 48760, "dynamics_loss_avg": 0.031600396055728196}
+{"step": 48760, "action_loss_avg": 0.0016510772606125102}
+{"step": 48770, "dynamics_loss_avg": 0.0235016118735075}
+{"step": 48770, "action_loss_avg": 0.0016753233940107748}
+{"step": 48780, "dynamics_loss_avg": 0.023325762804597618}
+{"step": 48780, "action_loss_avg": 0.001681024464778602}
+{"step": 48790, "dynamics_loss_avg": 0.04035137090831995}
+{"step": 48790, "action_loss_avg": 0.0029254381079226732}
+{"step": 48800, "loss": 0.0316, "learning_rate": 5.610422564489188e-05}
+{"step": 48800, "dynamics_loss_avg": 0.0362655894830823}
+{"step": 48800, "action_loss_avg": 0.003108283126493916}
+{"step": 48810, "dynamics_loss_avg": 0.03151831366121769}
+{"step": 48810, "action_loss_avg": 0.0021976834745146335}
+{"step": 48820, "dynamics_loss_avg": 0.028092887811362745}
+{"step": 48820, "action_loss_avg": 0.0019429682288318872}
+{"step": 48830, "dynamics_loss_avg": 0.02191607393324375}
+{"step": 48830, "action_loss_avg": 0.0021481848030816763}
+{"step": 48840, "dynamics_loss_avg": 0.030151323368772864}
+{"step": 48840, "action_loss_avg": 0.0021735208894824607}
+{"step": 48850, "loss": 0.029, "learning_rate": 5.60221622688505e-05}
+{"step": 48850, "dynamics_loss_avg": 0.028459133952856062}
+{"step": 48850, "action_loss_avg": 0.0028686839970760046}
+{"step": 48860, "dynamics_loss_avg": 0.031385332951322197}
+{"step": 48860, "action_loss_avg": 0.002564562053885311}
+{"step": 48870, "dynamics_loss_avg": 0.02946167243644595}
+{"step": 48870, "action_loss_avg": 0.0020447646820684895}
+{"step": 48880, "dynamics_loss_avg": 0.027901637740433215}
+{"step": 48880, "action_loss_avg": 0.0013889288355130702}
+{"step": 48890, "dynamics_loss_avg": 0.0204031172208488}
+{"step": 48890, "action_loss_avg": 0.001241937157465145}
+{"step": 48900, "loss": 0.0317, "learning_rate": 5.5940082428447426e-05}
+{"step": 48900, "dynamics_loss_avg": 0.03922488521784544}
+{"step": 48900, "action_loss_avg": 0.0036417319381143896}
+{"step": 48910, "dynamics_loss_avg": 0.023598888190463185}
+{"step": 48910, "action_loss_avg": 0.0014859002956654876}
+{"step": 48920, "dynamics_loss_avg": 0.03375937486998737}
+{"step": 48920, "action_loss_avg": 0.0027247839199844746}
+{"step": 48930, "dynamics_loss_avg": 0.030310988798737525}
+{"step": 48930, "action_loss_avg": 0.0025130467722192405}
+{"step": 48940, "dynamics_loss_avg": 0.03588763810694218}
+{"step": 48940, "action_loss_avg": 0.0020685408730059863}
+{"step": 48950, "loss": 0.0329, "learning_rate": 5.585798634808583e-05}
+{"step": 48950, "dynamics_loss_avg": 0.03553259167820215}
+{"step": 48950, "action_loss_avg": 0.0019087600870989264}
+{"step": 48960, "dynamics_loss_avg": 0.03212063172832132}
+{"step": 48960, "action_loss_avg": 0.0023669336223974824}
+{"step": 48970, "dynamics_loss_avg": 0.020107671432197095}
+{"step": 48970, "action_loss_avg": 0.0012723999156150968}
+{"step": 48980, "dynamics_loss_avg": 0.023021762631833552}
+{"step": 48980, "action_loss_avg": 0.0013590741204097868}
+{"step": 48990, "dynamics_loss_avg": 0.02932986607775092}
+{"step": 48990, "action_loss_avg": 0.001423934323247522}
+{"step": 49000, "loss": 0.0303, "learning_rate": 5.5775874252213247e-05}
+{"step": 49000, "dynamics_loss_avg": 0.0334812369197607}
+{"step": 49000, "action_loss_avg": 0.0023069700167980046}
+{"step": 49010, "dynamics_loss_avg": 0.02628925321623683}
+{"step": 49010, "action_loss_avg": 0.0017105294449720533}
+{"step": 49020, "dynamics_loss_avg": 0.027703204471617938}
+{"step": 49020, "action_loss_avg": 0.0018858295399695635}
+{"step": 49030, "dynamics_loss_avg": 0.03554962705820799}
+{"step": 49030, "action_loss_avg": 0.0028486567607615143}
+{"step": 49040, "dynamics_loss_avg": 0.026065164851024746}
+{"step": 49040, "action_loss_avg": 0.0016294912667945028}
+{"step": 49050, "loss": 0.0299, "learning_rate": 5.5693746365320984e-05}
+{"step": 49050, "dynamics_loss_avg": 0.026666273549199104}
+{"step": 49050, "action_loss_avg": 0.001333010575035587}
+{"step": 49060, "dynamics_loss_avg": 0.025542738381773233}
+{"step": 49060, "action_loss_avg": 0.0016711068979930132}
+{"step": 49070, "dynamics_loss_avg": 0.02479347148910165}
+{"step": 49070, "action_loss_avg": 0.0017696303460979835}
+{"step": 49080, "dynamics_loss_avg": 0.042242197599261996}
+{"step": 49080, "action_loss_avg": 0.003538334381300956}
+{"step": 49090, "dynamics_loss_avg": 0.0357093021273613}
+{"step": 49090, "action_loss_avg": 0.0031602219329215585}
+{"step": 49100, "loss": 0.0329, "learning_rate": 5.5611602911943596e-05}
+{"step": 49100, "dynamics_loss_avg": 0.025684716645628214}
+{"step": 49100, "action_loss_avg": 0.001558408950222656}
+{"step": 49110, "dynamics_loss_avg": 0.036724353581666945}
+{"step": 49110, "action_loss_avg": 0.0027564787131268533}
+{"step": 49120, "dynamics_loss_avg": 0.036149391811341046}
+{"step": 49120, "action_loss_avg": 0.0026685724966228007}
+{"step": 49130, "dynamics_loss_avg": 0.02792592248879373}
+{"step": 49130, "action_loss_avg": 0.0019107744446955621}
+{"step": 49140, "dynamics_loss_avg": 0.023102595238015056}
+{"step": 49140, "action_loss_avg": 0.001416583827813156}
+{"step": 49150, "loss": 0.032, "learning_rate": 5.552944411665811e-05}
+{"step": 49150, "dynamics_loss_avg": 0.042104591615498066}
+{"step": 49150, "action_loss_avg": 0.0035829679341986775}
+{"step": 49160, "dynamics_loss_avg": 0.031058779172599315}
+{"step": 49160, "action_loss_avg": 0.0018528162545408122}
+{"step": 49170, "dynamics_loss_avg": 0.03404623456299305}
+{"step": 49170, "action_loss_avg": 0.0016152217460330576}
+{"step": 49180, "dynamics_loss_avg": 0.02857629777863622}
+{"step": 49180, "action_loss_avg": 0.0018942643946502358}
+{"step": 49190, "dynamics_loss_avg": 0.02843968626111746}
+{"step": 49190, "action_loss_avg": 0.001990614150417969}
+{"step": 49200, "loss": 0.0315, "learning_rate": 5.544727020408358e-05}
+{"step": 49200, "dynamics_loss_avg": 0.022397507820278405}
+{"step": 49200, "action_loss_avg": 0.0014641451649367808}
+{"step": 49210, "dynamics_loss_avg": 0.03167203068733215}
+{"step": 49210, "action_loss_avg": 0.0015968625259120018}
+{"step": 49220, "dynamics_loss_avg": 0.023129322845488787}
+{"step": 49220, "action_loss_avg": 0.0014186281536240132}
+{"step": 49230, "dynamics_loss_avg": 0.0338227316737175}
+{"step": 49230, "action_loss_avg": 0.00224056983133778}
+{"step": 49240, "dynamics_loss_avg": 0.03380585247650743}
+{"step": 49240, "action_loss_avg": 0.0016271161905024201}
+{"step": 49250, "loss": 0.0313, "learning_rate": 5.536508139888028e-05}
+{"step": 49250, "dynamics_loss_avg": 0.029292522929608822}
+{"step": 49250, "action_loss_avg": 0.0021408901433460415}
+{"step": 49260, "dynamics_loss_avg": 0.03174140956252813}
+{"step": 49260, "action_loss_avg": 0.002005812060087919}
+{"step": 49270, "dynamics_loss_avg": 0.03755428311415017}
+{"step": 49270, "action_loss_avg": 0.002640424232231453}
+{"step": 49280, "dynamics_loss_avg": 0.03427913300693035}
+{"step": 49280, "action_loss_avg": 0.002119472168851644}
+{"step": 49290, "dynamics_loss_avg": 0.04328533727675676}
+{"step": 49290, "action_loss_avg": 0.0033779230318032203}
+{"step": 49300, "loss": 0.035, "learning_rate": 5.528287792574932e-05}
+{"step": 49300, "dynamics_loss_avg": 0.03169157905504107}
+{"step": 49300, "action_loss_avg": 0.002228840616589878}
+{"step": 49310, "dynamics_loss_avg": 0.024762408062815666}
+{"step": 49310, "action_loss_avg": 0.0014998139609815552}
+{"step": 49320, "dynamics_loss_avg": 0.029974049795418976}
+{"step": 49320, "action_loss_avg": 0.0019316075777169317}
+{"step": 49330, "dynamics_loss_avg": 0.03051902214065194}
+{"step": 49330, "action_loss_avg": 0.0021041192201664673}
+{"step": 49340, "dynamics_loss_avg": 0.025296092592179777}
+{"step": 49340, "action_loss_avg": 0.001833919173805043}
+{"step": 49350, "loss": 0.0309, "learning_rate": 5.5200660009431826e-05}
+{"step": 49350, "dynamics_loss_avg": 0.04013800024986267}
+{"step": 49350, "action_loss_avg": 0.002598801744170487}
+{"step": 49360, "dynamics_loss_avg": 0.025119587872177364}
+{"step": 49360, "action_loss_avg": 0.0020376230066176506}
+{"step": 49370, "dynamics_loss_avg": 0.03632411099970341}
+{"step": 49370, "action_loss_avg": 0.0022149508353322745}
+{"step": 49380, "dynamics_loss_avg": 0.02543760882690549}
+{"step": 49380, "action_loss_avg": 0.001241810925421305}
+{"step": 49390, "dynamics_loss_avg": 0.028456587996333837}
+{"step": 49390, "action_loss_avg": 0.0021007031959015877}
+{"step": 49400, "loss": 0.0308, "learning_rate": 5.5118427874708466e-05}
+{"step": 49400, "dynamics_loss_avg": 0.03830176591873169}
+{"step": 49400, "action_loss_avg": 0.0022356659930665044}
+{"step": 49410, "dynamics_loss_avg": 0.02218887908384204}
+{"step": 49410, "action_loss_avg": 0.001154318277258426}
+{"step": 49420, "dynamics_loss_avg": 0.026516810432076453}
+{"step": 49420, "action_loss_avg": 0.0015830024232855067}
+{"step": 49430, "dynamics_loss_avg": 0.023344740690663456}
+{"step": 49430, "action_loss_avg": 0.0013121365424012764}
+{"step": 49440, "dynamics_loss_avg": 0.02319651683792472}
+{"step": 49440, "action_loss_avg": 0.0013586965680588037}
+{"step": 49450, "loss": 0.0277, "learning_rate": 5.503618174639874e-05}
+{"step": 49450, "dynamics_loss_avg": 0.03380523407831788}
+{"step": 49450, "action_loss_avg": 0.0015908412693534046}
+{"step": 49460, "dynamics_loss_avg": 0.0284246196039021}
+{"step": 49460, "action_loss_avg": 0.0018967826734296977}
+{"step": 49470, "dynamics_loss_avg": 0.03143056770786643}
+{"step": 49470, "action_loss_avg": 0.001698400010354817}
+{"step": 49480, "dynamics_loss_avg": 0.02695535230450332}
+{"step": 49480, "action_loss_avg": 0.0014190568181220442}
+{"step": 49490, "dynamics_loss_avg": 0.03479423699900508}
+{"step": 49490, "action_loss_avg": 0.002839011896867305}
+{"step": 49500, "loss": 0.0305, "learning_rate": 5.4953921849360424e-05}
+{"step": 49500, "dynamics_loss_avg": 0.02104822392575443}
+{"step": 49500, "action_loss_avg": 0.0013531159464037045}
+{"step": 49510, "dynamics_loss_avg": 0.024925900856032968}
+{"step": 49510, "action_loss_avg": 0.0014576682995539158}
+{"step": 49520, "dynamics_loss_avg": 0.03346416763961315}
+{"step": 49520, "action_loss_avg": 0.0029160171805415304}
+{"step": 49530, "dynamics_loss_avg": 0.032991000451147556}
+{"step": 49530, "action_loss_avg": 0.001902182144112885}
+{"step": 49540, "dynamics_loss_avg": 0.02328317114152014}
+{"step": 49540, "action_loss_avg": 0.00127211706712842}
+{"step": 49550, "loss": 0.0294, "learning_rate": 5.4871648408488926e-05}
+{"step": 49550, "dynamics_loss_avg": 0.028904401138424872}
+{"step": 49550, "action_loss_avg": 0.0022567942272871734}
+{"step": 49560, "dynamics_loss_avg": 0.026992359571158885}
+{"step": 49560, "action_loss_avg": 0.0022034372726920993}
+{"step": 49570, "dynamics_loss_avg": 0.02533871727064252}
+{"step": 49570, "action_loss_avg": 0.0020435238082427533}
+{"step": 49580, "dynamics_loss_avg": 0.040572131890803574}
+{"step": 49580, "action_loss_avg": 0.0033109877374954523}
+{"step": 49590, "dynamics_loss_avg": 0.024483200255781414}
+{"step": 49590, "action_loss_avg": 0.001356563501758501}
+{"step": 49600, "loss": 0.031, "learning_rate": 5.478936164871671e-05}
+{"step": 49600, "dynamics_loss_avg": 0.03464210145175457}
+{"step": 49600, "action_loss_avg": 0.0023499919450841846}
+{"step": 49610, "dynamics_loss_avg": 0.033677999023348094}
+{"step": 49610, "action_loss_avg": 0.0023982771061128007}
+{"step": 49620, "dynamics_loss_avg": 0.03105975463986397}
+{"step": 49620, "action_loss_avg": 0.001742513250792399}
+{"step": 49630, "dynamics_loss_avg": 0.0456623399630189}
+{"step": 49630, "action_loss_avg": 0.003183421929134056}
+{"step": 49640, "dynamics_loss_avg": 0.03895386718213558}
+{"step": 49640, "action_loss_avg": 0.002267630794085562}
+{"step": 49650, "loss": 0.0356, "learning_rate": 5.470706179501264e-05}
+{"step": 49650, "dynamics_loss_avg": 0.0251828839071095}
+{"step": 49650, "action_loss_avg": 0.001446341726114042}
+{"step": 49660, "dynamics_loss_avg": 0.027007915917783974}
+{"step": 49660, "action_loss_avg": 0.0011382413911633193}
+{"step": 49670, "dynamics_loss_avg": 0.02732121916487813}
+{"step": 49670, "action_loss_avg": 0.0017095307179261}
+{"step": 49680, "dynamics_loss_avg": 0.03200854326132685}
+{"step": 49680, "action_loss_avg": 0.0018492036848329007}
+{"step": 49690, "dynamics_loss_avg": 0.021022992534562947}
+{"step": 49690, "action_loss_avg": 0.0010669087583664804}
+{"step": 49700, "loss": 0.0284, "learning_rate": 5.4624749072381343e-05}
+{"step": 49700, "dynamics_loss_avg": 0.03373819887638092}
+{"step": 49700, "action_loss_avg": 0.0024652726599015294}
+{"step": 49710, "dynamics_loss_avg": 0.025290313735604288}
+{"step": 49710, "action_loss_avg": 0.0022254161594901234}
+{"step": 49720, "dynamics_loss_avg": 0.02581665962934494}
+{"step": 49720, "action_loss_avg": 0.001673407678026706}
+{"step": 49730, "dynamics_loss_avg": 0.029008057527244092}
+{"step": 49730, "action_loss_avg": 0.0014086204988416283}
+{"step": 49740, "dynamics_loss_avg": 0.02410311931744218}
+{"step": 49740, "action_loss_avg": 0.0012438160862075164}
+{"step": 49750, "loss": 0.0293, "learning_rate": 5.454242370586269e-05}
+{"step": 49750, "dynamics_loss_avg": 0.020683608297258616}
+{"step": 49750, "action_loss_avg": 0.0012711058894637971}
+{"step": 49760, "dynamics_loss_avg": 0.02241142066195607}
+{"step": 49760, "action_loss_avg": 0.001632002298720181}
+{"step": 49770, "dynamics_loss_avg": 0.022886449284851552}
+{"step": 49770, "action_loss_avg": 0.0010967194684781134}
+{"step": 49780, "dynamics_loss_avg": 0.02935006031766534}
+{"step": 49780, "action_loss_avg": 0.0019267115741968155}
+{"step": 49790, "dynamics_loss_avg": 0.029056021012365818}
+{"step": 49790, "action_loss_avg": 0.001688084425404668}
+{"step": 49800, "loss": 0.0285, "learning_rate": 5.446008592053107e-05}
+{"step": 49800, "dynamics_loss_avg": 0.021249534050002693}
+{"step": 49800, "action_loss_avg": 0.0012237084156367928}
+{"step": 49810, "dynamics_loss_avg": 0.0243108588270843}
+{"step": 49810, "action_loss_avg": 0.0016128261690028013}
+{"step": 49820, "dynamics_loss_avg": 0.029426144622266292}
+{"step": 49820, "action_loss_avg": 0.001740596565650776}
+{"step": 49830, "dynamics_loss_avg": 0.02801232021301985}
+{"step": 49830, "action_loss_avg": 0.0010835780471097679}
+{"step": 49840, "dynamics_loss_avg": 0.03258540453389287}
+{"step": 49840, "action_loss_avg": 0.0016630631813313811}
+{"step": 49850, "loss": 0.0287, "learning_rate": 5.437773594149484e-05}
+{"step": 49850, "dynamics_loss_avg": 0.022842964716255666}
+{"step": 49850, "action_loss_avg": 0.0016158645506948234}
+{"step": 49860, "dynamics_loss_avg": 0.02528762649744749}
+{"step": 49860, "action_loss_avg": 0.001572015101555735}
+{"step": 49870, "dynamics_loss_avg": 0.032413649559021}
+{"step": 49870, "action_loss_avg": 0.0018951420148368924}
+{"step": 49880, "dynamics_loss_avg": 0.03504489967599511}
+{"step": 49880, "action_loss_avg": 0.002073663572082296}
+{"step": 49890, "dynamics_loss_avg": 0.028642349783331154}
+{"step": 49890, "action_loss_avg": 0.0017886016052216292}
+{"step": 49900, "loss": 0.029, "learning_rate": 5.4295373993895736e-05}
+{"step": 49900, "dynamics_loss_avg": 0.034079682640731336}
+{"step": 49900, "action_loss_avg": 0.0018352503975620493}
+{"step": 49910, "dynamics_loss_avg": 0.02818873440846801}
+{"step": 49910, "action_loss_avg": 0.001577898656250909}
+{"step": 49920, "dynamics_loss_avg": 0.030821757204830647}
+{"step": 49920, "action_loss_avg": 0.0018097607942763716}
+{"step": 49930, "dynamics_loss_avg": 0.03242014935240149}
+{"step": 49930, "action_loss_avg": 0.00220975634874776}
+{"step": 49940, "dynamics_loss_avg": 0.03686889447271824}
+{"step": 49940, "action_loss_avg": 0.001889784203376621}
+{"step": 49950, "loss": 0.0327, "learning_rate": 5.4213000302908134e-05}
+{"step": 49950, "dynamics_loss_avg": 0.027839479316025973}
+{"step": 49950, "action_loss_avg": 0.0022807648871093988}
+{"step": 49960, "dynamics_loss_avg": 0.025692460499703883}
+{"step": 49960, "action_loss_avg": 0.0015180914138909428}
+{"step": 49970, "dynamics_loss_avg": 0.02773933419957757}
+{"step": 49970, "action_loss_avg": 0.0017708699131617322}
+{"step": 49980, "dynamics_loss_avg": 0.026306342240422963}
+{"step": 49980, "action_loss_avg": 0.0019473065505735577}
+{"step": 49990, "dynamics_loss_avg": 0.0324852405115962}
+{"step": 49990, "action_loss_avg": 0.0017679457960184664}
+{"step": 50000, "loss": 0.0322, "learning_rate": 5.413061509373858e-05}
+{"step": 50000, "dynamics_loss_avg": 0.0345740114338696}
+{"step": 50000, "action_loss_avg": 0.0030051174631807952}
+{"step": 50010, "dynamics_loss_avg": 0.02299153823405504}
+{"step": 50010, "action_loss_avg": 0.0017883812019135804}
+{"step": 50020, "dynamics_loss_avg": 0.03389436956495047}
+{"step": 50020, "action_loss_avg": 0.0018501756072510033}
+{"step": 50030, "dynamics_loss_avg": 0.030708261765539646}
+{"step": 50030, "action_loss_avg": 0.0013475002837367357}
+{"step": 50040, "dynamics_loss_avg": 0.029817164409905672}
+{"step": 50040, "action_loss_avg": 0.0019008577219210565}
+{"step": 50050, "loss": 0.0295, "learning_rate": 5.404821859162509e-05}
+{"step": 50050, "dynamics_loss_avg": 0.027686435356736185}
+{"step": 50050, "action_loss_avg": 0.0014841556985629722}
+{"step": 50060, "dynamics_loss_avg": 0.03368664151057601}
+{"step": 50060, "action_loss_avg": 0.0020956013235263527}
+{"step": 50070, "dynamics_loss_avg": 0.030170710198581217}
+{"step": 50070, "action_loss_avg": 0.0018825893988832832}
+{"step": 50080, "dynamics_loss_avg": 0.030939136724919082}
+{"step": 50080, "action_loss_avg": 0.0020065775839611887}
+{"step": 50090, "dynamics_loss_avg": 0.03207821985706687}
+{"step": 50090, "action_loss_avg": 0.0014200232049915939}
+{"step": 50100, "loss": 0.0324, "learning_rate": 5.396581102183655e-05}
+{"step": 50100, "dynamics_loss_avg": 0.03442298034206033}
+{"step": 50100, "action_loss_avg": 0.002989678282756358}
+{"step": 50110, "dynamics_loss_avg": 0.023549759946763515}
+{"step": 50110, "action_loss_avg": 0.0016357387939933687}
+{"step": 50120, "dynamics_loss_avg": 0.02985749039798975}
+{"step": 50120, "action_loss_avg": 0.0015014854026958347}
+{"step": 50130, "dynamics_loss_avg": 0.033642811700701714}
+{"step": 50130, "action_loss_avg": 0.0021059200400486587}
+{"step": 50140, "dynamics_loss_avg": 0.03433124432340264}
+{"step": 50140, "action_loss_avg": 0.003167257073801011}
+{"step": 50150, "loss": 0.033, "learning_rate": 5.3883392609672114e-05}
+{"step": 50150, "dynamics_loss_avg": 0.03999158255755901}
+{"step": 50150, "action_loss_avg": 0.0023250849568285047}
+{"step": 50160, "dynamics_loss_avg": 0.027597335213795305}
+{"step": 50160, "action_loss_avg": 0.0019376710813958197}
+{"step": 50170, "dynamics_loss_avg": 0.02868934250436723}
+{"step": 50170, "action_loss_avg": 0.0020882134311250413}
+{"step": 50180, "dynamics_loss_avg": 0.03710485314950347}
+{"step": 50180, "action_loss_avg": 0.0024590963032096623}
+{"step": 50190, "dynamics_loss_avg": 0.019417232973501085}
+{"step": 50190, "action_loss_avg": 0.001281428409856744}
+{"step": 50200, "loss": 0.0278, "learning_rate": 5.380096358046056e-05}
+{"step": 50200, "dynamics_loss_avg": 0.028043408505618574}
+{"step": 50200, "action_loss_avg": 0.002052362309768796}
+{"step": 50210, "dynamics_loss_avg": 0.02483626171015203}
+{"step": 50210, "action_loss_avg": 0.0017953308211872353}
+{"step": 50220, "dynamics_loss_avg": 0.02987819444388151}
+{"step": 50220, "action_loss_avg": 0.001496245071757585}
+{"step": 50230, "dynamics_loss_avg": 0.03915868960320949}
+{"step": 50230, "action_loss_avg": 0.0027097263024188577}
+{"step": 50240, "dynamics_loss_avg": 0.02348686894401908}
+{"step": 50240, "action_loss_avg": 0.0013569000526331364}
+{"step": 50250, "loss": 0.0324, "learning_rate": 5.3718524159559726e-05}
+{"step": 50250, "dynamics_loss_avg": 0.04359122682362795}
+{"step": 50250, "action_loss_avg": 0.0030895105097442865}
+{"step": 50260, "dynamics_loss_avg": 0.02855902276933193}
+{"step": 50260, "action_loss_avg": 0.0012297998182475567}
+{"step": 50270, "dynamics_loss_avg": 0.025325353629887103}
+{"step": 50270, "action_loss_avg": 0.0015387143939733505}
+{"step": 50280, "dynamics_loss_avg": 0.03276381865143776}
+{"step": 50280, "action_loss_avg": 0.0019936216122005135}
+{"step": 50290, "dynamics_loss_avg": 0.030490396544337273}
+{"step": 50290, "action_loss_avg": 0.0018639393732883037}
+{"step": 50300, "loss": 0.0321, "learning_rate": 5.3636074572355824e-05}
+{"step": 50300, "dynamics_loss_avg": 0.03340441873297095}
+{"step": 50300, "action_loss_avg": 0.0022879057796671987}
+{"step": 50310, "dynamics_loss_avg": 0.03436541128903627}
+{"step": 50310, "action_loss_avg": 0.002457086998037994}
+{"step": 50320, "dynamics_loss_avg": 0.032977997232228516}
+{"step": 50320, "action_loss_avg": 0.0019275032100267708}
+{"step": 50330, "dynamics_loss_avg": 0.026850129035301505}
+{"step": 50330, "action_loss_avg": 0.0013992127642268315}
+{"step": 50340, "dynamics_loss_avg": 0.022536816820502282}
+{"step": 50340, "action_loss_avg": 0.0016102283785585313}
+{"step": 50350, "loss": 0.0295, "learning_rate": 5.3553615044262895e-05}
+{"step": 50350, "dynamics_loss_avg": 0.02324473299086094}
+{"step": 50350, "action_loss_avg": 0.0011844000313431025}
+{"step": 50360, "dynamics_loss_avg": 0.023326130397617818}
+{"step": 50360, "action_loss_avg": 0.0015078081254614518}
+{"step": 50370, "dynamics_loss_avg": 0.02586297718808055}
+{"step": 50370, "action_loss_avg": 0.001351020869333297}
+{"step": 50380, "dynamics_loss_avg": 0.029239597311243416}
+{"step": 50380, "action_loss_avg": 0.0016907898883800954}
+{"step": 50390, "dynamics_loss_avg": 0.02580060912296176}
+{"step": 50390, "action_loss_avg": 0.00136049494612962}
+{"step": 50400, "loss": 0.0276, "learning_rate": 5.347114580072212e-05}
+{"step": 50400, "dynamics_loss_avg": 0.028731804434210063}
+{"step": 50400, "action_loss_avg": 0.0021616126497974618}
+{"step": 50410, "dynamics_loss_avg": 0.02706027776002884}
+{"step": 50410, "action_loss_avg": 0.0015991642256267368}
+{"step": 50420, "dynamics_loss_avg": 0.025462175905704498}
+{"step": 50420, "action_loss_avg": 0.0015023600426502526}
+{"step": 50430, "dynamics_loss_avg": 0.02981027411296964}
+{"step": 50430, "action_loss_avg": 0.0017470104969106615}
+{"step": 50440, "dynamics_loss_avg": 0.02152628074400127}
+{"step": 50440, "action_loss_avg": 0.0013729378901189194}
+{"step": 50450, "loss": 0.0286, "learning_rate": 5.338866706720128e-05}
+{"step": 50450, "dynamics_loss_avg": 0.03815414495766163}
+{"step": 50450, "action_loss_avg": 0.002156420616665855}
+{"step": 50460, "dynamics_loss_avg": 0.027004085294902325}
+{"step": 50460, "action_loss_avg": 0.001788598211714998}
+{"step": 50470, "dynamics_loss_avg": 0.025477717677131296}
+{"step": 50470, "action_loss_avg": 0.0014169414062052965}
+{"step": 50480, "dynamics_loss_avg": 0.02550720041617751}
+{"step": 50480, "action_loss_avg": 0.0011727293313015252}
+{"step": 50490, "dynamics_loss_avg": 0.029057379346340895}
+{"step": 50490, "action_loss_avg": 0.0021524082927498966}
+{"step": 50500, "loss": 0.0309, "learning_rate": 5.330617906919405e-05}
+{"step": 50500, "dynamics_loss_avg": 0.02878696834668517}
+{"step": 50500, "action_loss_avg": 0.0019095932540949434}
+{"step": 50510, "dynamics_loss_avg": 0.031184036564081908}
+{"step": 50510, "action_loss_avg": 0.001839278102852404}
+{"step": 50520, "dynamics_loss_avg": 0.025654873065650462}
+{"step": 50520, "action_loss_avg": 0.0016513330978341401}
+{"step": 50530, "dynamics_loss_avg": 0.028983759693801403}
+{"step": 50530, "action_loss_avg": 0.0017129269312135876}
+{"step": 50540, "dynamics_loss_avg": 0.03187285279855132}
+{"step": 50540, "action_loss_avg": 0.0019703394500538707}
+{"step": 50550, "loss": 0.0312, "learning_rate": 5.3223682032219515e-05}
+{"step": 50550, "dynamics_loss_avg": 0.031874504219740626}
+{"step": 50550, "action_loss_avg": 0.0018558544950792566}
+{"step": 50560, "dynamics_loss_avg": 0.026086341217160226}
+{"step": 50560, "action_loss_avg": 0.001502149278530851}
+{"step": 50570, "dynamics_loss_avg": 0.024914851831272244}
+{"step": 50570, "action_loss_avg": 0.001228596578584984}
+{"step": 50580, "dynamics_loss_avg": 0.026739612920209765}
+{"step": 50580, "action_loss_avg": 0.0016957195301074534}
+{"step": 50590, "dynamics_loss_avg": 0.02125720363110304}
+{"step": 50590, "action_loss_avg": 0.0015068830922245978}
+{"step": 50600, "loss": 0.0277, "learning_rate": 5.3141176181821395e-05}
+{"step": 50600, "dynamics_loss_avg": 0.027218681201338767}
+{"step": 50600, "action_loss_avg": 0.0014733342570252717}
+{"step": 50610, "dynamics_loss_avg": 0.030530101899057627}
+{"step": 50610, "action_loss_avg": 0.0016810887900646776}
+{"step": 50620, "dynamics_loss_avg": 0.03222948713228106}
+{"step": 50620, "action_loss_avg": 0.0018896336201578378}
+{"step": 50630, "dynamics_loss_avg": 0.029455657862126828}
+{"step": 50630, "action_loss_avg": 0.0016461248800624163}
+{"step": 50640, "dynamics_loss_avg": 0.025495258439332247}
+{"step": 50640, "action_loss_avg": 0.0014135654317215085}
+{"step": 50650, "loss": 0.0289, "learning_rate": 5.305866174356754e-05}
+{"step": 50650, "dynamics_loss_avg": 0.026306539960205554}
+{"step": 50650, "action_loss_avg": 0.0013279756240081042}
+{"step": 50660, "dynamics_loss_avg": 0.03462751042097807}
+{"step": 50660, "action_loss_avg": 0.001732445729430765}
+{"step": 50670, "dynamics_loss_avg": 0.030356210842728614}
+{"step": 50670, "action_loss_avg": 0.0018094645900418981}
+{"step": 50680, "dynamics_loss_avg": 0.02857273519039154}
+{"step": 50680, "action_loss_avg": 0.0019026359543204308}
+{"step": 50690, "dynamics_loss_avg": 0.03434052933007479}
+{"step": 50690, "action_loss_avg": 0.001903852468240075}
+{"step": 50700, "loss": 0.0333, "learning_rate": 5.297613894304928e-05}
+{"step": 50700, "dynamics_loss_avg": 0.03523822203278541}
+{"step": 50700, "action_loss_avg": 0.002319746604189277}
+{"step": 50710, "dynamics_loss_avg": 0.03557062046602368}
+{"step": 50710, "action_loss_avg": 0.0022297271527349947}
+{"step": 50720, "dynamics_loss_avg": 0.02616869634948671}
+{"step": 50720, "action_loss_avg": 0.0022329309926135466}
+{"step": 50730, "dynamics_loss_avg": 0.02838406041264534}
+{"step": 50730, "action_loss_avg": 0.0013815238140523433}
+{"step": 50740, "dynamics_loss_avg": 0.025325884576886892}
+{"step": 50740, "action_loss_avg": 0.0016055790969403461}
+{"step": 50750, "loss": 0.0307, "learning_rate": 5.2893608005880767e-05}
+{"step": 50750, "dynamics_loss_avg": 0.03086971342563629}
+{"step": 50750, "action_loss_avg": 0.0016367943084333093}
+{"step": 50760, "dynamics_loss_avg": 0.0292949665337801}
+{"step": 50760, "action_loss_avg": 0.0013968553219456225}
+{"step": 50770, "dynamics_loss_avg": 0.030118493223562838}
+{"step": 50770, "action_loss_avg": 0.0016887332007172518}
+{"step": 50780, "dynamics_loss_avg": 0.024187399679794906}
+{"step": 50780, "action_loss_avg": 0.0012468848930438981}
+{"step": 50790, "dynamics_loss_avg": 0.03000077260658145}
+{"step": 50790, "action_loss_avg": 0.0012731402734061704}
+{"step": 50800, "loss": 0.0303, "learning_rate": 5.281106915769849e-05}
+{"step": 50800, "dynamics_loss_avg": 0.02399223977699876}
+{"step": 50800, "action_loss_avg": 0.0013998195965541527}
+{"step": 50810, "dynamics_loss_avg": 0.03302575028501451}
+{"step": 50810, "action_loss_avg": 0.0021242001705104483}
+{"step": 50820, "dynamics_loss_avg": 0.023640560498461128}
+{"step": 50820, "action_loss_avg": 0.0015065928906551561}
+{"step": 50830, "dynamics_loss_avg": 0.016468085069209337}
+{"step": 50830, "action_loss_avg": 0.0007583550352137536}
+{"step": 50840, "dynamics_loss_avg": 0.022685272432863713}
+{"step": 50840, "action_loss_avg": 0.0018484910891857}
+{"step": 50850, "loss": 0.0292, "learning_rate": 5.272852262416046e-05}
+{"step": 50850, "dynamics_loss_avg": 0.030730750504881145}
+{"step": 50850, "action_loss_avg": 0.0012670089374296368}
+{"step": 50860, "dynamics_loss_avg": 0.028559302166104316}
+{"step": 50860, "action_loss_avg": 0.0016568187216762452}
+{"step": 50870, "dynamics_loss_avg": 0.032128213346004485}
+{"step": 50870, "action_loss_avg": 0.00208250904106535}
+{"step": 50880, "dynamics_loss_avg": 0.03167491434141993}
+{"step": 50880, "action_loss_avg": 0.0016401552129536867}
+{"step": 50890, "dynamics_loss_avg": 0.02738980483263731}
+{"step": 50890, "action_loss_avg": 0.001839518139604479}
+{"step": 50900, "loss": 0.0324, "learning_rate": 5.264596863094575e-05}
+{"step": 50900, "dynamics_loss_avg": 0.03905495554208756}
+{"step": 50900, "action_loss_avg": 0.0019133992143906652}
+{"step": 50910, "dynamics_loss_avg": 0.03670237842015922}
+{"step": 50910, "action_loss_avg": 0.003025896631879732}
+{"step": 50920, "dynamics_loss_avg": 0.026105484971776605}
+{"step": 50920, "action_loss_avg": 0.001711322003393434}
+{"step": 50930, "dynamics_loss_avg": 0.028589159343391658}
+{"step": 50930, "action_loss_avg": 0.001240439579123631}
+{"step": 50940, "dynamics_loss_avg": 0.024284416157752276}
+{"step": 50940, "action_loss_avg": 0.001357769686728716}
+{"step": 50950, "loss": 0.0304, "learning_rate": 5.256340740375387e-05}
+{"step": 50950, "dynamics_loss_avg": 0.025237900111824273}
+{"step": 50950, "action_loss_avg": 0.0013382314937189221}
+{"step": 50960, "dynamics_loss_avg": 0.024167347233742476}
+{"step": 50960, "action_loss_avg": 0.001621769554913044}
+{"step": 50970, "dynamics_loss_avg": 0.03429749580100179}
+{"step": 50970, "action_loss_avg": 0.0014845099416561426}
+{"step": 50980, "dynamics_loss_avg": 0.03397664297372103}
+{"step": 50980, "action_loss_avg": 0.0017154427187051624}
+{"step": 50990, "dynamics_loss_avg": 0.02559307599440217}
+{"step": 50990, "action_loss_avg": 0.0012507674138760195}
+{"step": 51000, "loss": 0.0312, "learning_rate": 5.2480839168304e-05}
+{"step": 51000, "dynamics_loss_avg": 0.03212872315198183}
+{"step": 51000, "action_loss_avg": 0.00245751176844351}
+{"step": 51010, "dynamics_loss_avg": 0.025975880585610865}
+{"step": 51010, "action_loss_avg": 0.0013165707030566409}
+{"step": 51020, "dynamics_loss_avg": 0.03523277607746422}
+{"step": 51020, "action_loss_avg": 0.001815179068944417}
+{"step": 51030, "dynamics_loss_avg": 0.03762699421495199}
+{"step": 51030, "action_loss_avg": 0.0025007267948240043}
+{"step": 51040, "dynamics_loss_avg": 0.02581348973326385}
+{"step": 51040, "action_loss_avg": 0.001281023380579427}
+{"step": 51050, "loss": 0.0307, "learning_rate": 5.23982641503346e-05}
+{"step": 51050, "dynamics_loss_avg": 0.03168867379426956}
+{"step": 51050, "action_loss_avg": 0.0017621384118683635}
+{"step": 51060, "dynamics_loss_avg": 0.027510839467868208}
+{"step": 51060, "action_loss_avg": 0.0017416647810023279}
+{"step": 51070, "dynamics_loss_avg": 0.03736846037209034}
+{"step": 51070, "action_loss_avg": 0.002146655775140971}
+{"step": 51080, "dynamics_loss_avg": 0.023484360333532094}
+{"step": 51080, "action_loss_avg": 0.0011876729578943924}
+{"step": 51090, "dynamics_loss_avg": 0.02825599955394864}
+{"step": 51090, "action_loss_avg": 0.001649169868323952}
+{"step": 51100, "loss": 0.0299, "learning_rate": 5.2315682575602576e-05}
+{"step": 51100, "dynamics_loss_avg": 0.03179975235834718}
+{"step": 51100, "action_loss_avg": 0.0012341134570306167}
+{"step": 51110, "dynamics_loss_avg": 0.03214138373732567}
+{"step": 51110, "action_loss_avg": 0.0022404524264857174}
+{"step": 51120, "dynamics_loss_avg": 0.028786192275583745}
+{"step": 51120, "action_loss_avg": 0.001797043060651049}
+{"step": 51130, "dynamics_loss_avg": 0.03168938932940364}
+{"step": 51130, "action_loss_avg": 0.001743460405850783}
+{"step": 51140, "dynamics_loss_avg": 0.030108212400227784}
+{"step": 51140, "action_loss_avg": 0.0019322378328070044}
+{"step": 51150, "loss": 0.0325, "learning_rate": 5.223309466988283e-05}
+{"step": 51150, "dynamics_loss_avg": 0.037497094739228486}
+{"step": 51150, "action_loss_avg": 0.002549246561829932}
+{"step": 51160, "dynamics_loss_avg": 0.02361574643291533}
+{"step": 51160, "action_loss_avg": 0.0015991478401701897}
+{"step": 51170, "dynamics_loss_avg": 0.028178355377167463}
+{"step": 51170, "action_loss_avg": 0.0014349529810715467}
+{"step": 51180, "dynamics_loss_avg": 0.026276928931474687}
+{"step": 51180, "action_loss_avg": 0.0013734553824178875}
+{"step": 51190, "dynamics_loss_avg": 0.03318309877067804}
+{"step": 51190, "action_loss_avg": 0.0018216021300759167}
+{"step": 51200, "loss": 0.0301, "learning_rate": 5.215050065896752e-05}
+{"step": 51200, "dynamics_loss_avg": 0.028923582471907138}
+{"step": 51200, "action_loss_avg": 0.0017026529472786932}
+{"step": 51210, "dynamics_loss_avg": 0.028022682340815664}
+{"step": 51210, "action_loss_avg": 0.0017492312617832795}
+{"step": 51220, "dynamics_loss_avg": 0.03215117612853646}
+{"step": 51220, "action_loss_avg": 0.0017154382599983363}
+{"step": 51230, "dynamics_loss_avg": 0.036413976922631264}
+{"step": 51230, "action_loss_avg": 0.0017913481337018312}
+{"step": 51240, "dynamics_loss_avg": 0.03193076783791184}
+{"step": 51240, "action_loss_avg": 0.0018300976720638574}
+{"step": 51250, "loss": 0.0338, "learning_rate": 5.20679007686655e-05}
+{"step": 51250, "dynamics_loss_avg": 0.032897364581003785}
+{"step": 51250, "action_loss_avg": 0.0019671042275149373}
+{"step": 51260, "dynamics_loss_avg": 0.028732098080217837}
+{"step": 51260, "action_loss_avg": 0.0017757292691385374}
+{"step": 51270, "dynamics_loss_avg": 0.03230990236625075}
+{"step": 51270, "action_loss_avg": 0.00210592215298675}
+{"step": 51280, "dynamics_loss_avg": 0.02759460024535656}
+{"step": 51280, "action_loss_avg": 0.001544756576186046}
+{"step": 51290, "dynamics_loss_avg": 0.032729197107255456}
+{"step": 51290, "action_loss_avg": 0.0019373420742340385}
+{"step": 51300, "loss": 0.0326, "learning_rate": 5.1985295224801777e-05}
+{"step": 51300, "dynamics_loss_avg": 0.031771259801462295}
+{"step": 51300, "action_loss_avg": 0.0016889824823010714}
+{"step": 51310, "dynamics_loss_avg": 0.026849711826071144}
+{"step": 51310, "action_loss_avg": 0.0018075546657200902}
+{"step": 51320, "dynamics_loss_avg": 0.029961585626006128}
+{"step": 51320, "action_loss_avg": 0.0019432661298196762}
+{"step": 51330, "dynamics_loss_avg": 0.03132041795179248}
+{"step": 51330, "action_loss_avg": 0.0017508076969534158}
+{"step": 51340, "dynamics_loss_avg": 0.027299317251890897}
+{"step": 51340, "action_loss_avg": 0.0019905492663383484}
+{"step": 51350, "loss": 0.0293, "learning_rate": 5.1902684253216695e-05}
+{"step": 51350, "dynamics_loss_avg": 0.032407797686755654}
+{"step": 51350, "action_loss_avg": 0.0028633227688260377}
+{"step": 51360, "dynamics_loss_avg": 0.03847939781844616}
+{"step": 51360, "action_loss_avg": 0.002071843872545287}
+{"step": 51370, "dynamics_loss_avg": 0.03414921537041664}
+{"step": 51370, "action_loss_avg": 0.0019121387624181807}
+{"step": 51380, "dynamics_loss_avg": 0.03014548122882843}
+{"step": 51380, "action_loss_avg": 0.0016410500160418452}
+{"step": 51390, "dynamics_loss_avg": 0.026859924662858248}
+{"step": 51390, "action_loss_avg": 0.0014361666806507855}
+{"step": 51400, "loss": 0.0329, "learning_rate": 5.182006807976554e-05}
+{"step": 51400, "dynamics_loss_avg": 0.029563174489885567}
+{"step": 51400, "action_loss_avg": 0.0020251024601748214}
+{"step": 51410, "dynamics_loss_avg": 0.034657820546999576}
+{"step": 51410, "action_loss_avg": 0.0013373900146689266}
+{"step": 51420, "dynamics_loss_avg": 0.030519182607531548}
+{"step": 51420, "action_loss_avg": 0.0018816376861650497}
+{"step": 51430, "dynamics_loss_avg": 0.02631744146347046}
+{"step": 51430, "action_loss_avg": 0.001639418429112993}
+{"step": 51440, "dynamics_loss_avg": 0.02100752852857113}
+{"step": 51440, "action_loss_avg": 0.001171044632792473}
+{"step": 51450, "loss": 0.0305, "learning_rate": 5.1737446930317736e-05}
+{"step": 51450, "dynamics_loss_avg": 0.026567232329398394}
+{"step": 51450, "action_loss_avg": 0.001826301115215756}
+{"step": 51460, "dynamics_loss_avg": 0.046023120544850825}
+{"step": 51460, "action_loss_avg": 0.004217779112514109}
+{"step": 51470, "dynamics_loss_avg": 0.03358058463782072}
+{"step": 51470, "action_loss_avg": 0.002030812745215371}
+{"step": 51480, "dynamics_loss_avg": 0.03146253265440464}
+{"step": 51480, "action_loss_avg": 0.0022683708841213955}
+{"step": 51490, "dynamics_loss_avg": 0.029546296689659357}
+{"step": 51490, "action_loss_avg": 0.0014098490471951663}
+{"step": 51500, "loss": 0.0347, "learning_rate": 5.165482103075637e-05}
+{"step": 51500, "dynamics_loss_avg": 0.03300498784519732}
+{"step": 51500, "action_loss_avg": 0.0021751126099843533}
+{"step": 51510, "dynamics_loss_avg": 0.032126654777675866}
+{"step": 51510, "action_loss_avg": 0.0025275651743868364}
+{"step": 51520, "dynamics_loss_avg": 0.030523138400167227}
+{"step": 51520, "action_loss_avg": 0.0022015652619302275}
+{"step": 51530, "dynamics_loss_avg": 0.04264963837340474}
+{"step": 51530, "action_loss_avg": 0.002977398835355416}
+{"step": 51540, "dynamics_loss_avg": 0.023587987176142633}
+{"step": 51540, "action_loss_avg": 0.0016532746478333138}
+{"step": 51550, "loss": 0.0325, "learning_rate": 5.15721906069775e-05}
+{"step": 51550, "dynamics_loss_avg": 0.024782370403409006}
+{"step": 51550, "action_loss_avg": 0.001440014285617508}
+{"step": 51560, "dynamics_loss_avg": 0.026907112263143063}
+{"step": 51560, "action_loss_avg": 0.001655370951630175}
+{"step": 51570, "dynamics_loss_avg": 0.02311152284964919}
+{"step": 51570, "action_loss_avg": 0.0010552379448199646}
+{"step": 51580, "dynamics_loss_avg": 0.03283061999827623}
+{"step": 51580, "action_loss_avg": 0.002138130401726812}
+{"step": 51590, "dynamics_loss_avg": 0.03678027093410492}
+{"step": 51590, "action_loss_avg": 0.0019441750540863723}
+{"step": 51600, "loss": 0.0321, "learning_rate": 5.148955588488955e-05}
+{"step": 51600, "dynamics_loss_avg": 0.032723855972290036}
+{"step": 51600, "action_loss_avg": 0.0022143362439237535}
+{"step": 51610, "dynamics_loss_avg": 0.0379242442548275}
+{"step": 51610, "action_loss_avg": 0.0020920603303238748}
+{"step": 51620, "dynamics_loss_avg": 0.029477895610034464}
+{"step": 51620, "action_loss_avg": 0.002483522266265936}
+{"step": 51630, "dynamics_loss_avg": 0.030229076370596887}
+{"step": 51630, "action_loss_avg": 0.0017548012314364315}
+{"step": 51640, "dynamics_loss_avg": 0.03750849785283208}
+{"step": 51640, "action_loss_avg": 0.00229649031534791}
+{"step": 51650, "loss": 0.0337, "learning_rate": 5.1406917090412673e-05}
+{"step": 51650, "dynamics_loss_avg": 0.02813713811337948}
+{"step": 51650, "action_loss_avg": 0.001626235368894413}
+{"step": 51660, "dynamics_loss_avg": 0.04080915916711092}
+{"step": 51660, "action_loss_avg": 0.002973219566047192}
+{"step": 51670, "dynamics_loss_avg": 0.023918082611635326}
+{"step": 51670, "action_loss_avg": 0.0012227450672071428}
+{"step": 51680, "dynamics_loss_avg": 0.038793588243424895}
+{"step": 51680, "action_loss_avg": 0.002248759911162779}
+{"step": 51690, "dynamics_loss_avg": 0.02570259729400277}
+{"step": 51690, "action_loss_avg": 0.0012668698851484804}
+{"step": 51700, "loss": 0.0303, "learning_rate": 5.1324274449478204e-05}
+{"step": 51700, "dynamics_loss_avg": 0.022802663827314974}
+{"step": 51700, "action_loss_avg": 0.0017942402511835099}
+{"step": 51710, "dynamics_loss_avg": 0.030200577341020107}
+{"step": 51710, "action_loss_avg": 0.002217688801465556}
+{"step": 51720, "dynamics_loss_avg": 0.03432293022051454}
+{"step": 51720, "action_loss_avg": 0.002077184000518173}
+{"step": 51730, "dynamics_loss_avg": 0.02569070002064109}
+{"step": 51730, "action_loss_avg": 0.0012893773266114295}
+{"step": 51740, "dynamics_loss_avg": 0.023047782108187677}
+{"step": 51740, "action_loss_avg": 0.0016739843093091622}
+{"step": 51750, "loss": 0.0316, "learning_rate": 5.1241628188027956e-05}
+{"step": 51750, "dynamics_loss_avg": 0.03169954838231206}
+{"step": 51750, "action_loss_avg": 0.001508048750110902}
+{"step": 51760, "dynamics_loss_avg": 0.026148071978241205}
+{"step": 51760, "action_loss_avg": 0.0019934400712372734}
+{"step": 51770, "dynamics_loss_avg": 0.03089549969881773}
+{"step": 51770, "action_loss_avg": 0.001843007782008499}
+{"step": 51780, "dynamics_loss_avg": 0.028536096215248108}
+{"step": 51780, "action_loss_avg": 0.0015105894883163274}
+{"step": 51790, "dynamics_loss_avg": 0.02449320862069726}
+{"step": 51790, "action_loss_avg": 0.0015046994609292596}
+{"step": 51800, "loss": 0.0288, "learning_rate": 5.1158978532013645e-05}
+{"step": 51800, "dynamics_loss_avg": 0.02646378641948104}
+{"step": 51800, "action_loss_avg": 0.001426338727469556}
+{"step": 51810, "dynamics_loss_avg": 0.028248441219329835}
+{"step": 51810, "action_loss_avg": 0.0017986045160796494}
+{"step": 51820, "dynamics_loss_avg": 0.027698547393083573}
+{"step": 51820, "action_loss_avg": 0.0016727262700442225}
+{"step": 51830, "dynamics_loss_avg": 0.04123205859214067}
+{"step": 51830, "action_loss_avg": 0.002601298020454124}
+{"step": 51840, "dynamics_loss_avg": 0.02828183863312006}
+{"step": 51840, "action_loss_avg": 0.0018978587453602814}
+{"step": 51850, "loss": 0.0324, "learning_rate": 5.107632570739631e-05}
+{"step": 51850, "dynamics_loss_avg": 0.03208172861486673}
+{"step": 51850, "action_loss_avg": 0.0019675609277328477}
+{"step": 51860, "dynamics_loss_avg": 0.026548758149147034}
+{"step": 51860, "action_loss_avg": 0.0016802684782305732}
+{"step": 51870, "dynamics_loss_avg": 0.028003685735166074}
+{"step": 51870, "action_loss_avg": 0.0017960776400286703}
+{"step": 51880, "dynamics_loss_avg": 0.027106270659714937}
+{"step": 51880, "action_loss_avg": 0.0015744859032565729}
+{"step": 51890, "dynamics_loss_avg": 0.01967075769789517}
+{"step": 51890, "action_loss_avg": 0.0008933858887758106}
+{"step": 51900, "loss": 0.0294, "learning_rate": 5.099366994014556e-05}
+{"step": 51900, "dynamics_loss_avg": 0.02843523952178657}
+{"step": 51900, "action_loss_avg": 0.001949360320577398}
+{"step": 51910, "dynamics_loss_avg": 0.029632671736180782}
+{"step": 51910, "action_loss_avg": 0.0016505409439560026}
+{"step": 51920, "dynamics_loss_avg": 0.01974372654221952}
+{"step": 51920, "action_loss_avg": 0.0014111654105363413}
+{"step": 51930, "dynamics_loss_avg": 0.02735852086916566}
+{"step": 51930, "action_loss_avg": 0.0011792938748840243}
+{"step": 51940, "dynamics_loss_avg": 0.029436136269941925}
+{"step": 51940, "action_loss_avg": 0.0022534628966241143}
+{"step": 51950, "loss": 0.029, "learning_rate": 5.0911011456239157e-05}
+{"step": 51950, "dynamics_loss_avg": 0.026613733172416686}
+{"step": 51950, "action_loss_avg": 0.0013722143456107005}
+{"step": 51960, "dynamics_loss_avg": 0.028382453229278327}
+{"step": 51960, "action_loss_avg": 0.0020064715412445367}
+{"step": 51970, "dynamics_loss_avg": 0.028115378692746162}
+{"step": 51970, "action_loss_avg": 0.0014770418580155819}
+{"step": 51980, "dynamics_loss_avg": 0.028752715000882743}
+{"step": 51980, "action_loss_avg": 0.0023916470585390926}
+{"step": 51990, "dynamics_loss_avg": 0.03152787433937192}
+{"step": 51990, "action_loss_avg": 0.0019555979466531425}
+{"step": 52000, "loss": 0.0293, "learning_rate": 5.08283504816622e-05}
+{"step": 52000, "dynamics_loss_avg": 0.03015785040333867}
+{"step": 52000, "action_loss_avg": 0.0019905925350030885}
+{"step": 52010, "dynamics_loss_avg": 0.02678619185462594}
+{"step": 52010, "action_loss_avg": 0.0017576795478817075}
+{"step": 52020, "dynamics_loss_avg": 0.022690495196729898}
+{"step": 52020, "action_loss_avg": 0.0013443355768686161}
+{"step": 52030, "dynamics_loss_avg": 0.03301416002213955}
+{"step": 52030, "action_loss_avg": 0.002099777845432982}
+{"step": 52040, "dynamics_loss_avg": 0.02613293454051018}
+{"step": 52040, "action_loss_avg": 0.0019306760281324387}
+{"step": 52050, "loss": 0.0294, "learning_rate": 5.074568724240667e-05}
+{"step": 52050, "dynamics_loss_avg": 0.02687382623553276}
+{"step": 52050, "action_loss_avg": 0.0016343415598385036}
+{"step": 52060, "dynamics_loss_avg": 0.032304792385548356}
+{"step": 52060, "action_loss_avg": 0.002068900899030268}
+{"step": 52070, "dynamics_loss_avg": 0.022863756213337184}
+{"step": 52070, "action_loss_avg": 0.0013596341595984995}
+{"step": 52080, "dynamics_loss_avg": 0.027731843013316392}
+{"step": 52080, "action_loss_avg": 0.001959103622357361}
+{"step": 52090, "dynamics_loss_avg": 0.027008122950792312}
+{"step": 52090, "action_loss_avg": 0.0014507888001389802}
+{"step": 52100, "loss": 0.0303, "learning_rate": 5.06630219644707e-05}
+{"step": 52100, "dynamics_loss_avg": 0.032756905630230905}
+{"step": 52100, "action_loss_avg": 0.0021641017054207625}
+{"step": 52110, "dynamics_loss_avg": 0.03305084891617298}
+{"step": 52110, "action_loss_avg": 0.002382887713611126}
+{"step": 52120, "dynamics_loss_avg": 0.03225877396762371}
+{"step": 52120, "action_loss_avg": 0.0022979323111940175}
+{"step": 52130, "dynamics_loss_avg": 0.026409925334155558}
+{"step": 52130, "action_loss_avg": 0.0017299676779657601}
+{"step": 52140, "dynamics_loss_avg": 0.03888528579846025}
+{"step": 52140, "action_loss_avg": 0.002505721463239752}
+{"step": 52150, "loss": 0.0342, "learning_rate": 5.058035487385798e-05}
+{"step": 52150, "dynamics_loss_avg": 0.02793871462345123}
+{"step": 52150, "action_loss_avg": 0.001144371199188754}
+{"step": 52160, "dynamics_loss_avg": 0.026371556613594294}
+{"step": 52160, "action_loss_avg": 0.0017507150652818382}
+{"step": 52170, "dynamics_loss_avg": 0.027323158597573637}
+{"step": 52170, "action_loss_avg": 0.0017906779859913513}
+{"step": 52180, "dynamics_loss_avg": 0.029585904069244863}
+{"step": 52180, "action_loss_avg": 0.0021320256986655296}
+{"step": 52190, "dynamics_loss_avg": 0.026549719087779523}
+{"step": 52190, "action_loss_avg": 0.0016164292203029618}
+{"step": 52200, "loss": 0.0287, "learning_rate": 5.049768619657721e-05}
+{"step": 52200, "dynamics_loss_avg": 0.02832977371290326}
+{"step": 52200, "action_loss_avg": 0.0015928191191051156}
+{"step": 52210, "dynamics_loss_avg": 0.023549969587475062}
+{"step": 52210, "action_loss_avg": 0.0013706010126043112}
+{"step": 52220, "dynamics_loss_avg": 0.028494801372289658}
+{"step": 52220, "action_loss_avg": 0.0018663436756469309}
+{"step": 52230, "dynamics_loss_avg": 0.027758678374812006}
+{"step": 52230, "action_loss_avg": 0.0016840318043250591}
+{"step": 52240, "dynamics_loss_avg": 0.02006315728649497}
+{"step": 52240, "action_loss_avg": 0.0012509564752690495}
+{"step": 52250, "loss": 0.0294, "learning_rate": 5.041501615864137e-05}
+{"step": 52250, "dynamics_loss_avg": 0.028830550890415908}
+{"step": 52250, "action_loss_avg": 0.0016965132002951578}
+{"step": 52260, "dynamics_loss_avg": 0.030997144291177392}
+{"step": 52260, "action_loss_avg": 0.0017130400170572101}
+{"step": 52270, "dynamics_loss_avg": 0.023493226896971465}
+{"step": 52270, "action_loss_avg": 0.001341651106486097}
+{"step": 52280, "dynamics_loss_avg": 0.020620695874094964}
+{"step": 52280, "action_loss_avg": 0.0009663198055932298}
+{"step": 52290, "dynamics_loss_avg": 0.030537796253338457}
+{"step": 52290, "action_loss_avg": 0.0015990433370461688}
+{"step": 52300, "loss": 0.0282, "learning_rate": 5.033234498606721e-05}
+{"step": 52300, "dynamics_loss_avg": 0.029376952443271875}
+{"step": 52300, "action_loss_avg": 0.00172374626272358}
+{"step": 52310, "dynamics_loss_avg": 0.034176590666174886}
+{"step": 52310, "action_loss_avg": 0.0019106273204670288}
+{"step": 52320, "dynamics_loss_avg": 0.032047163043171165}
+{"step": 52320, "action_loss_avg": 0.0018358840723522007}
+{"step": 52330, "dynamics_loss_avg": 0.03196767568588257}
+{"step": 52330, "action_loss_avg": 0.0015921381011139602}
+{"step": 52340, "dynamics_loss_avg": 0.02722989353351295}
+{"step": 52340, "action_loss_avg": 0.0017989496380323544}
+{"step": 52350, "loss": 0.031, "learning_rate": 5.024967290487455e-05}
+{"step": 52350, "dynamics_loss_avg": 0.027067059464752675}
+{"step": 52350, "action_loss_avg": 0.0016609655693173408}
+{"step": 52360, "dynamics_loss_avg": 0.0381758832372725}
+{"step": 52360, "action_loss_avg": 0.002332983398810029}
+{"step": 52370, "dynamics_loss_avg": 0.03663296634331346}
+{"step": 52370, "action_loss_avg": 0.0018003535107709468}
+{"step": 52380, "dynamics_loss_avg": 0.024426292348653077}
+{"step": 52380, "action_loss_avg": 0.0010397401943919248}
+{"step": 52390, "dynamics_loss_avg": 0.031711244396865367}
+{"step": 52390, "action_loss_avg": 0.0018832392292097212}
+{"step": 52400, "loss": 0.0315, "learning_rate": 5.0167000141085686e-05}
+{"step": 52400, "dynamics_loss_avg": 0.029422537423670292}
+{"step": 52400, "action_loss_avg": 0.0014187974215019495}
+{"step": 52410, "dynamics_loss_avg": 0.03151411283761263}
+{"step": 52410, "action_loss_avg": 0.0018669274519197642}
+{"step": 52420, "dynamics_loss_avg": 0.03219236843287945}
+{"step": 52420, "action_loss_avg": 0.002412863145582378}
+{"step": 52430, "dynamics_loss_avg": 0.02251241160556674}
+{"step": 52430, "action_loss_avg": 0.0017570475349202753}
+{"step": 52440, "dynamics_loss_avg": 0.030357890017330646}
+{"step": 52440, "action_loss_avg": 0.0017556341394083575}
+{"step": 52450, "loss": 0.0296, "learning_rate": 5.008432692072482e-05}
+{"step": 52450, "dynamics_loss_avg": 0.03992071547545493}
+{"step": 52450, "action_loss_avg": 0.002479668980231509}
+{"step": 52460, "dynamics_loss_avg": 0.026165138371288775}
+{"step": 52460, "action_loss_avg": 0.00165492954547517}
+{"step": 52470, "dynamics_loss_avg": 0.03733229357749224}
+{"step": 52470, "action_loss_avg": 0.0018354539992287756}
+{"step": 52480, "dynamics_loss_avg": 0.026521390629932286}
+{"step": 52480, "action_loss_avg": 0.0013790037191938609}
+{"step": 52490, "dynamics_loss_avg": 0.020969124045222998}
+{"step": 52490, "action_loss_avg": 0.0014265213103499264}
+{"step": 52500, "loss": 0.0326, "learning_rate": 5.000165346981738e-05}
+{"step": 52500, "dynamics_loss_avg": 0.033754615345969796}
+{"step": 52500, "action_loss_avg": 0.00231781889742706}
+{"step": 52510, "dynamics_loss_avg": 0.03314330857247114}
+{"step": 52510, "action_loss_avg": 0.0016399483080022036}
+{"step": 52520, "dynamics_loss_avg": 0.03405715534463525}
+{"step": 52520, "action_loss_avg": 0.0018290518259163947}
+{"step": 52530, "dynamics_loss_avg": 0.033107030857354405}
+{"step": 52530, "action_loss_avg": 0.0017576084821484983}
+{"step": 52540, "dynamics_loss_avg": 0.03304775729775429}
+{"step": 52540, "action_loss_avg": 0.0020576053517288528}
+{"step": 52550, "loss": 0.032, "learning_rate": 4.991898001438941e-05}
+{"step": 52550, "dynamics_loss_avg": 0.03214213037863374}
+{"step": 52550, "action_loss_avg": 0.002172378104296513}
+{"step": 52560, "dynamics_loss_avg": 0.03139104014262557}
+{"step": 52560, "action_loss_avg": 0.001848344795871526}
+{"step": 52570, "dynamics_loss_avg": 0.027715567406266926}
+{"step": 52570, "action_loss_avg": 0.001819879308459349}
+{"step": 52580, "dynamics_loss_avg": 0.034652883931994435}
+{"step": 52580, "action_loss_avg": 0.0016985834517981857}
+{"step": 52590, "dynamics_loss_avg": 0.03945530708879232}
+{"step": 52590, "action_loss_avg": 0.0022164761554449796}
+{"step": 52600, "loss": 0.0345, "learning_rate": 4.9836306780467e-05}
+{"step": 52600, "dynamics_loss_avg": 0.028163006994873285}
+{"step": 52600, "action_loss_avg": 0.0013152326631825418}
+{"step": 52610, "dynamics_loss_avg": 0.02625507805496454}
+{"step": 52610, "action_loss_avg": 0.0014831843262072652}
+{"step": 52620, "dynamics_loss_avg": 0.024377560941502452}
+{"step": 52620, "action_loss_avg": 0.0017609719128813595}
+{"step": 52630, "dynamics_loss_avg": 0.03245585234835744}
+{"step": 52630, "action_loss_avg": 0.0027092801174148917}
+{"step": 52640, "dynamics_loss_avg": 0.02813113434240222}
+{"step": 52640, "action_loss_avg": 0.0016428274102509022}
+{"step": 52650, "loss": 0.0294, "learning_rate": 4.975363399407559e-05}
+{"step": 52650, "dynamics_loss_avg": 0.0292667293921113}
+{"step": 52650, "action_loss_avg": 0.001384543137100991}
+{"step": 52660, "dynamics_loss_avg": 0.027559420559555292}
+{"step": 52660, "action_loss_avg": 0.0015781478577991948}
+{"step": 52670, "dynamics_loss_avg": 0.028911621309816837}
+{"step": 52670, "action_loss_avg": 0.0016461070685181768}
+{"step": 52680, "dynamics_loss_avg": 0.026204029889777304}
+{"step": 52680, "action_loss_avg": 0.001212584953464102}
+{"step": 52690, "dynamics_loss_avg": 0.03047240376472473}
+{"step": 52690, "action_loss_avg": 0.0017941707919817418}
+{"step": 52700, "loss": 0.0305, "learning_rate": 4.967096188123943e-05}
+{"step": 52700, "dynamics_loss_avg": 0.027729459945112465}
+{"step": 52700, "action_loss_avg": 0.0016887743317056448}
+{"step": 52710, "dynamics_loss_avg": 0.025595438946038485}
+{"step": 52710, "action_loss_avg": 0.0014844616496702656}
+{"step": 52720, "dynamics_loss_avg": 0.03762678769417107}
+{"step": 52720, "action_loss_avg": 0.002231274580117315}
+{"step": 52730, "dynamics_loss_avg": 0.030435674637556077}
+{"step": 52730, "action_loss_avg": 0.0016234259004704655}
+{"step": 52740, "dynamics_loss_avg": 0.025175484642386437}
+{"step": 52740, "action_loss_avg": 0.001939546427456662}
+{"step": 52750, "loss": 0.0307, "learning_rate": 4.958829066798092e-05}
+{"step": 52750, "dynamics_loss_avg": 0.032169852685183284}
+{"step": 52750, "action_loss_avg": 0.001456779465661384}
+{"step": 52760, "dynamics_loss_avg": 0.027083294373005627}
+{"step": 52760, "action_loss_avg": 0.0015993328066542744}
+{"step": 52770, "dynamics_loss_avg": 0.017823002208024262}
+{"step": 52770, "action_loss_avg": 0.001333840866573155}
+{"step": 52780, "dynamics_loss_avg": 0.02848697192966938}
+{"step": 52780, "action_loss_avg": 0.0016873976972419768}
+{"step": 52790, "dynamics_loss_avg": 0.029520378448069096}
+{"step": 52790, "action_loss_avg": 0.0013982857228256762}
+{"step": 52800, "loss": 0.0292, "learning_rate": 4.950562058032001e-05}
+{"step": 52800, "dynamics_loss_avg": 0.03344365451484919}
+{"step": 52800, "action_loss_avg": 0.001722375873941928}
+{"step": 52810, "dynamics_loss_avg": 0.036614001356065275}
+{"step": 52810, "action_loss_avg": 0.0017076947260648012}
+{"step": 52820, "dynamics_loss_avg": 0.02856894014403224}
+{"step": 52820, "action_loss_avg": 0.0022585255501326174}
+{"step": 52830, "dynamics_loss_avg": 0.026698630861938}
+{"step": 52830, "action_loss_avg": 0.0015618437610100955}
+{"step": 52840, "dynamics_loss_avg": 0.027092140913009644}
+{"step": 52840, "action_loss_avg": 0.001683106311247684}
+{"step": 52850, "loss": 0.0309, "learning_rate": 4.942295184427356e-05}
+{"step": 52850, "dynamics_loss_avg": 0.03335390742868185}
+{"step": 52850, "action_loss_avg": 0.0017214142135344446}
+{"step": 52860, "dynamics_loss_avg": 0.03157431203871965}
+{"step": 52860, "action_loss_avg": 0.0020946524804458023}
+{"step": 52870, "dynamics_loss_avg": 0.028747763019055128}
+{"step": 52870, "action_loss_avg": 0.0016428779083071277}
+{"step": 52880, "dynamics_loss_avg": 0.02770910244435072}
+{"step": 52880, "action_loss_avg": 0.0017351099930237978}
+{"step": 52890, "dynamics_loss_avg": 0.02536099525168538}
+{"step": 52890, "action_loss_avg": 0.0014119230152573436}
+{"step": 52900, "loss": 0.0303, "learning_rate": 4.934028468585473e-05}
+{"step": 52900, "dynamics_loss_avg": 0.023675563745200634}
+{"step": 52900, "action_loss_avg": 0.0013688650797121227}
+{"step": 52910, "dynamics_loss_avg": 0.03484588861465454}
+{"step": 52910, "action_loss_avg": 0.0024808109388686716}
+{"step": 52920, "dynamics_loss_avg": 0.02853688164614141}
+{"step": 52920, "action_loss_avg": 0.0017347573157167062}
+{"step": 52930, "dynamics_loss_avg": 0.032775409333407876}
+{"step": 52930, "action_loss_avg": 0.0016346136340871452}
+{"step": 52940, "dynamics_loss_avg": 0.035221751872450115}
+{"step": 52940, "action_loss_avg": 0.0021933233831077812}
+{"step": 52950, "loss": 0.0338, "learning_rate": 4.9257619331072375e-05}
+{"step": 52950, "dynamics_loss_avg": 0.03150707250460982}
+{"step": 52950, "action_loss_avg": 0.0018518238619435578}
+{"step": 52960, "dynamics_loss_avg": 0.02100432524457574}
+{"step": 52960, "action_loss_avg": 0.0012889109551906587}
+{"step": 52970, "dynamics_loss_avg": 0.025163548346608878}
+{"step": 52970, "action_loss_avg": 0.001270234098774381}
+{"step": 52980, "dynamics_loss_avg": 0.042460386920720336}
+{"step": 52980, "action_loss_avg": 0.0025774988171178848}
+{"step": 52990, "dynamics_loss_avg": 0.026590779516845943}
+{"step": 52990, "action_loss_avg": 0.0016572327382164075}
+{"step": 53000, "loss": 0.0309, "learning_rate": 4.917495600593042e-05}
+{"step": 53000, "dynamics_loss_avg": 0.035331548936665055}
+{"step": 53000, "action_loss_avg": 0.0018704763846471907}
+{"step": 53010, "dynamics_loss_avg": 0.028376086708158256}
+{"step": 53010, "action_loss_avg": 0.0019316960009746254}
+{"step": 53020, "dynamics_loss_avg": 0.027511706482619046}
+{"step": 53020, "action_loss_avg": 0.0014034104300662876}
+{"step": 53030, "dynamics_loss_avg": 0.03315164381638169}
+{"step": 53030, "action_loss_avg": 0.0017744902259437367}
+{"step": 53040, "dynamics_loss_avg": 0.02553407335653901}
+{"step": 53040, "action_loss_avg": 0.001431597291957587}
+{"step": 53050, "loss": 0.0328, "learning_rate": 4.9092294936427234e-05}
+{"step": 53050, "dynamics_loss_avg": 0.040068427287042144}
+{"step": 53050, "action_loss_avg": 0.0025936962803825734}
+{"step": 53060, "dynamics_loss_avg": 0.03070587646216154}
+{"step": 53060, "action_loss_avg": 0.0019169574952684343}
+{"step": 53070, "dynamics_loss_avg": 0.02368702320381999}
+{"step": 53070, "action_loss_avg": 0.0012029475183226168}
+{"step": 53080, "dynamics_loss_avg": 0.029898392409086226}
+{"step": 53080, "action_loss_avg": 0.001449511552345939}
+{"step": 53090, "dynamics_loss_avg": 0.022768779704347254}
+{"step": 53090, "action_loss_avg": 0.0013135342567693442}
+{"step": 53100, "loss": 0.0289, "learning_rate": 4.900963634855505e-05}
+{"step": 53100, "dynamics_loss_avg": 0.02659638235345483}
+{"step": 53100, "action_loss_avg": 0.001277809160819743}
+{"step": 53110, "dynamics_loss_avg": 0.027689346112310886}
+{"step": 53110, "action_loss_avg": 0.0013903188722906635}
+{"step": 53120, "dynamics_loss_avg": 0.024207886354997755}
+{"step": 53120, "action_loss_avg": 0.0014949862466892227}
+{"step": 53130, "dynamics_loss_avg": 0.03103882009163499}
+{"step": 53130, "action_loss_avg": 0.0018658274930203333}
+{"step": 53140, "dynamics_loss_avg": 0.035707411170005796}
+{"step": 53140, "action_loss_avg": 0.002314588846638799}
+{"step": 53150, "loss": 0.0302, "learning_rate": 4.892698046829926e-05}
+{"step": 53150, "dynamics_loss_avg": 0.029489507246762515}
+{"step": 53150, "action_loss_avg": 0.001849400976789184}
+{"step": 53160, "dynamics_loss_avg": 0.026619716454297303}
+{"step": 53160, "action_loss_avg": 0.0016260047908872367}
+{"step": 53170, "dynamics_loss_avg": 0.03486966034397483}
+{"step": 53170, "action_loss_avg": 0.0015377626346889882}
+{"step": 53180, "dynamics_loss_avg": 0.03258063471876085}
+{"step": 53180, "action_loss_avg": 0.002273808646714315}
+{"step": 53190, "dynamics_loss_avg": 0.020705697312951087}
+{"step": 53190, "action_loss_avg": 0.0012781373923644423}
+{"step": 53200, "loss": 0.0302, "learning_rate": 4.884432752163789e-05}
+{"step": 53200, "dynamics_loss_avg": 0.028891408164054156}
+{"step": 53200, "action_loss_avg": 0.0016823974350700156}
+{"step": 53210, "dynamics_loss_avg": 0.026385095808655022}
+{"step": 53210, "action_loss_avg": 0.0018417337734717876}
+{"step": 53220, "dynamics_loss_avg": 0.03331804517656565}
+{"step": 53220, "action_loss_avg": 0.002066344756167382}
+{"step": 53230, "dynamics_loss_avg": 0.03500019870698452}
+{"step": 53230, "action_loss_avg": 0.002045902219833806}
+{"step": 53240, "dynamics_loss_avg": 0.028784705605357886}
+{"step": 53240, "action_loss_avg": 0.0019195907516404986}
+{"step": 53250, "loss": 0.0301, "learning_rate": 4.8761677734540956e-05}
+{"step": 53250, "dynamics_loss_avg": 0.028044160315766932}
+{"step": 53250, "action_loss_avg": 0.0014437878446187824}
+{"step": 53260, "dynamics_loss_avg": 0.021786374691873788}
+{"step": 53260, "action_loss_avg": 0.001415089622605592}
+{"step": 53270, "dynamics_loss_avg": 0.02949157883413136}
+{"step": 53270, "action_loss_avg": 0.0016374938597436995}
+{"step": 53280, "dynamics_loss_avg": 0.031328754499554634}
+{"step": 53280, "action_loss_avg": 0.0016833933914313093}
+{"step": 53290, "dynamics_loss_avg": 0.02679281570017338}
+{"step": 53290, "action_loss_avg": 0.001473248773254454}
+{"step": 53300, "loss": 0.0311, "learning_rate": 4.8679031332969835e-05}
+{"step": 53300, "dynamics_loss_avg": 0.03893236666917801}
+{"step": 53300, "action_loss_avg": 0.002016603396623395}
+{"step": 53310, "dynamics_loss_avg": 0.022581585636362433}
+{"step": 53310, "action_loss_avg": 0.0013363728823605925}
+{"step": 53320, "dynamics_loss_avg": 0.022481856867671013}
+{"step": 53320, "action_loss_avg": 0.0013713422929868102}
+{"step": 53330, "dynamics_loss_avg": 0.03372124778106809}
+{"step": 53330, "action_loss_avg": 0.0014853227767162025}
+{"step": 53340, "dynamics_loss_avg": 0.02972863344475627}
+{"step": 53340, "action_loss_avg": 0.0018868357292376459}
+{"step": 53350, "loss": 0.0299, "learning_rate": 4.8596388542876563e-05}
+{"step": 53350, "dynamics_loss_avg": 0.021896668802946807}
+{"step": 53350, "action_loss_avg": 0.0011526861606398597}
+{"step": 53360, "dynamics_loss_avg": 0.033598637022078034}
+{"step": 53360, "action_loss_avg": 0.0021245830634143204}
+{"step": 53370, "dynamics_loss_avg": 0.027793626068159938}
+{"step": 53370, "action_loss_avg": 0.0027842203562613577}
+{"step": 53380, "dynamics_loss_avg": 0.03918851800262928}
+{"step": 53380, "action_loss_avg": 0.0024800860090181233}
+{"step": 53390, "dynamics_loss_avg": 0.032032419554889204}
+{"step": 53390, "action_loss_avg": 0.002059129485860467}
+{"step": 53400, "loss": 0.0346, "learning_rate": 4.851374959020344e-05}
+{"step": 53400, "dynamics_loss_avg": 0.04575751442462206}
+{"step": 53400, "action_loss_avg": 0.0028613807051442565}
+{"step": 53410, "dynamics_loss_avg": 0.026591916382312775}
+{"step": 53410, "action_loss_avg": 0.002000480639981106}
+{"step": 53420, "dynamics_loss_avg": 0.03089017579331994}
+{"step": 53420, "action_loss_avg": 0.0015719756076578051}
+{"step": 53430, "dynamics_loss_avg": 0.0380228316411376}
+{"step": 53430, "action_loss_avg": 0.0025303934002295137}
+{"step": 53440, "dynamics_loss_avg": 0.026515011582523583}
+{"step": 53440, "action_loss_avg": 0.0014199845783878118}
+{"step": 53450, "loss": 0.0327, "learning_rate": 4.843111470088218e-05}
+{"step": 53450, "dynamics_loss_avg": 0.028968262765556575}
+{"step": 53450, "action_loss_avg": 0.001525405776919797}
+{"step": 53460, "dynamics_loss_avg": 0.029321012552827597}
+{"step": 53460, "action_loss_avg": 0.0017671632958808914}
+{"step": 53470, "dynamics_loss_avg": 0.03936582310125232}
+{"step": 53470, "action_loss_avg": 0.0019913785945391282}
+{"step": 53480, "dynamics_loss_avg": 0.028735434962436558}
+{"step": 53480, "action_loss_avg": 0.0015696463466156273}
+{"step": 53490, "dynamics_loss_avg": 0.02927553690969944}
+{"step": 53490, "action_loss_avg": 0.001278406463097781}
+{"step": 53500, "loss": 0.0335, "learning_rate": 4.834848410083342e-05}
+{"step": 53500, "dynamics_loss_avg": 0.03054870506748557}
+{"step": 53500, "action_loss_avg": 0.0017631082329899073}
+{"step": 53510, "dynamics_loss_avg": 0.024912867601960896}
+{"step": 53510, "action_loss_avg": 0.0013140828552423045}
+{"step": 53520, "dynamics_loss_avg": 0.030598430428653955}
+{"step": 53520, "action_loss_avg": 0.0021214624517597257}
+{"step": 53530, "dynamics_loss_avg": 0.03338785283267498}
+{"step": 53530, "action_loss_avg": 0.002299979457166046}
+{"step": 53540, "dynamics_loss_avg": 0.02676169741898775}
+{"step": 53540, "action_loss_avg": 0.0012732203002087771}
+{"step": 53550, "loss": 0.0311, "learning_rate": 4.826585801596609e-05}
+{"step": 53550, "dynamics_loss_avg": 0.032423627399839464}
+{"step": 53550, "action_loss_avg": 0.0016603731724899261}
+{"step": 53560, "dynamics_loss_avg": 0.024238167237490414}
+{"step": 53560, "action_loss_avg": 0.0015179715177509935}
+{"step": 53570, "dynamics_loss_avg": 0.025669348845258354}
+{"step": 53570, "action_loss_avg": 0.0018457413418218494}
+{"step": 53580, "dynamics_loss_avg": 0.0312950586900115}
+{"step": 53580, "action_loss_avg": 0.002320561115629971}
+{"step": 53590, "dynamics_loss_avg": 0.023286224249750374}
+{"step": 53590, "action_loss_avg": 0.0010802053962834179}
+{"step": 53600, "loss": 0.0289, "learning_rate": 4.818323667217669e-05}
+{"step": 53600, "dynamics_loss_avg": 0.03006672509945929}
+{"step": 53600, "action_loss_avg": 0.0016483249055454507}
+{"step": 53610, "dynamics_loss_avg": 0.02906095962971449}
+{"step": 53610, "action_loss_avg": 0.0016834466252475977}
+{"step": 53620, "dynamics_loss_avg": 0.024986788211390377}
+{"step": 53620, "action_loss_avg": 0.0015531978686340153}
+{"step": 53630, "dynamics_loss_avg": 0.03064908068627119}
+{"step": 53630, "action_loss_avg": 0.0013481236121151597}
+{"step": 53640, "dynamics_loss_avg": 0.025321275275200606}
+{"step": 53640, "action_loss_avg": 0.0017497150518465787}
+{"step": 53650, "loss": 0.031, "learning_rate": 4.810062029534886e-05}
+{"step": 53650, "dynamics_loss_avg": 0.032556581497192386}
+{"step": 53650, "action_loss_avg": 0.001890205859672278}
+{"step": 53660, "dynamics_loss_avg": 0.030985068809241057}
+{"step": 53660, "action_loss_avg": 0.001784578594379127}
+{"step": 53670, "dynamics_loss_avg": 0.026022051554173233}
+{"step": 53670, "action_loss_avg": 0.0017733073502313346}
+{"step": 53680, "dynamics_loss_avg": 0.020703507494181393}
+{"step": 53680, "action_loss_avg": 0.0010039093845989554}
+{"step": 53690, "dynamics_loss_avg": 0.017896950896829366}
+{"step": 53690, "action_loss_avg": 0.0011635433271294459}
+{"step": 53700, "loss": 0.027, "learning_rate": 4.801800911135263e-05}
+{"step": 53700, "dynamics_loss_avg": 0.03771841581910849}
+{"step": 53700, "action_loss_avg": 0.0021561446454143153}
+{"step": 53710, "dynamics_loss_avg": 0.03077033571898937}
+{"step": 53710, "action_loss_avg": 0.0015090985281858594}
+{"step": 53720, "dynamics_loss_avg": 0.03118767701089382}
+{"step": 53720, "action_loss_avg": 0.0015029216214315967}
+{"step": 53730, "dynamics_loss_avg": 0.03337931530550122}
+{"step": 53730, "action_loss_avg": 0.002002404653467238}
+{"step": 53740, "dynamics_loss_avg": 0.040916554443538186}
+{"step": 53740, "action_loss_avg": 0.0024278125376440583}
+{"step": 53750, "loss": 0.0345, "learning_rate": 4.79354033460438e-05}
+{"step": 53750, "dynamics_loss_avg": 0.03770461492240429}
+{"step": 53750, "action_loss_avg": 0.0018082376074744389}
+{"step": 53760, "dynamics_loss_avg": 0.0301712978631258}
+{"step": 53760, "action_loss_avg": 0.0019251351128332316}
+{"step": 53770, "dynamics_loss_avg": 0.03209564997814596}
+{"step": 53770, "action_loss_avg": 0.0022931789280846715}
+{"step": 53780, "dynamics_loss_avg": 0.03372988365590572}
+{"step": 53780, "action_loss_avg": 0.0020081379741895946}
+{"step": 53790, "dynamics_loss_avg": 0.025003552017733455}
+{"step": 53790, "action_loss_avg": 0.0014525519218295813}
+{"step": 53800, "loss": 0.0318, "learning_rate": 4.78528032252634e-05}
+{"step": 53800, "dynamics_loss_avg": 0.025707662384957076}
+{"step": 53800, "action_loss_avg": 0.0015962334990035742}
+{"step": 53810, "dynamics_loss_avg": 0.020681964000687003}
+{"step": 53810, "action_loss_avg": 0.00110355941724265}
+{"step": 53820, "dynamics_loss_avg": 0.030386865697801115}
+{"step": 53820, "action_loss_avg": 0.0018271458859089762}
+{"step": 53830, "dynamics_loss_avg": 0.0326556402258575}
+{"step": 53830, "action_loss_avg": 0.001753525680396706}
+{"step": 53840, "dynamics_loss_avg": 0.03008071016520262}
+{"step": 53840, "action_loss_avg": 0.001746917626587674}
+{"step": 53850, "loss": 0.0282, "learning_rate": 4.777020897483697e-05}
+{"step": 53850, "dynamics_loss_avg": 0.028291008714586497}
+{"step": 53850, "action_loss_avg": 0.0013204549948568455}
+{"step": 53860, "dynamics_loss_avg": 0.02210254776291549}
+{"step": 53860, "action_loss_avg": 0.00139116927748546}
+{"step": 53870, "dynamics_loss_avg": 0.02764480272307992}
+{"step": 53870, "action_loss_avg": 0.0017496684449724853}
+{"step": 53880, "dynamics_loss_avg": 0.03497453173622489}
+{"step": 53880, "action_loss_avg": 0.002399161283392459}
+{"step": 53890, "dynamics_loss_avg": 0.03702236618846655}
+{"step": 53890, "action_loss_avg": 0.0017015347897540779}
+{"step": 53900, "loss": 0.0317, "learning_rate": 4.768762082057407e-05}
+{"step": 53900, "dynamics_loss_avg": 0.033447731658816336}
+{"step": 53900, "action_loss_avg": 0.001758209685795009}
+{"step": 53910, "dynamics_loss_avg": 0.024536008248105645}
+{"step": 53910, "action_loss_avg": 0.0012170311238151044}
+{"step": 53920, "dynamics_loss_avg": 0.020304197538644077}
+{"step": 53920, "action_loss_avg": 0.001386857609031722}
+{"step": 53930, "dynamics_loss_avg": 0.02887919172644615}
+{"step": 53930, "action_loss_avg": 0.001265078055439517}
+{"step": 53940, "dynamics_loss_avg": 0.036642042966559527}
+{"step": 53940, "action_loss_avg": 0.0023721441131783648}
+{"step": 53950, "loss": 0.0298, "learning_rate": 4.760503898826754e-05}
+{"step": 53950, "dynamics_loss_avg": 0.023086904431693256}
+{"step": 53950, "action_loss_avg": 0.001337474629690405}
+{"step": 53960, "dynamics_loss_avg": 0.031194914411753417}
+{"step": 53960, "action_loss_avg": 0.0020029916253406555}
+{"step": 53970, "dynamics_loss_avg": 0.032194601558148864}
+{"step": 53970, "action_loss_avg": 0.001312710327329114}
+{"step": 53980, "dynamics_loss_avg": 0.03365498599596321}
+{"step": 53980, "action_loss_avg": 0.0019002461747732013}
+{"step": 53990, "dynamics_loss_avg": 0.028130939975380898}
+{"step": 53990, "action_loss_avg": 0.0016285437246551736}
+{"step": 54000, "loss": 0.0324, "learning_rate": 4.7522463703692994e-05}
+{"step": 54000, "dynamics_loss_avg": 0.03012431929819286}
+{"step": 54000, "action_loss_avg": 0.001233480530208908}
+{"step": 54010, "dynamics_loss_avg": 0.02694500917568803}
+{"step": 54010, "action_loss_avg": 0.0012332317099208012}
+{"step": 54020, "dynamics_loss_avg": 0.03638308988884091}
+{"step": 54020, "action_loss_avg": 0.0017458311223890633}
+{"step": 54030, "dynamics_loss_avg": 0.04244566475972533}
+{"step": 54030, "action_loss_avg": 0.002707269397797063}
+{"step": 54040, "dynamics_loss_avg": 0.025477310083806513}
+{"step": 54040, "action_loss_avg": 0.001562852581264451}
+{"step": 54050, "loss": 0.0316, "learning_rate": 4.7439895192608054e-05}
+{"step": 54050, "dynamics_loss_avg": 0.03038510847836733}
+{"step": 54050, "action_loss_avg": 0.001806240127189085}
+{"step": 54060, "dynamics_loss_avg": 0.03212910667061806}
+{"step": 54060, "action_loss_avg": 0.001903550885617733}
+{"step": 54070, "dynamics_loss_avg": 0.03273415509611368}
+{"step": 54070, "action_loss_avg": 0.0014999446750152857}
+{"step": 54080, "dynamics_loss_avg": 0.035649535804986955}
+{"step": 54080, "action_loss_avg": 0.0018112789490260183}
+{"step": 54090, "dynamics_loss_avg": 0.03061639773659408}
+{"step": 54090, "action_loss_avg": 0.0015227254742057994}
+{"step": 54100, "loss": 0.0328, "learning_rate": 4.735733368075189e-05}
+{"step": 54100, "dynamics_loss_avg": 0.034866354614496234}
+{"step": 54100, "action_loss_avg": 0.0019979802222223953}
+{"step": 54110, "dynamics_loss_avg": 0.030396035686135293}
+{"step": 54110, "action_loss_avg": 0.0014817088085692376}
+{"step": 54120, "dynamics_loss_avg": 0.0394924221560359}
+{"step": 54120, "action_loss_avg": 0.0023441203171387314}
+{"step": 54130, "dynamics_loss_avg": 0.030335593363270165}
+{"step": 54130, "action_loss_avg": 0.0019419841511989944}
+{"step": 54140, "dynamics_loss_avg": 0.03223658502101898}
+{"step": 54140, "action_loss_avg": 0.0018690437136683613}
+{"step": 54150, "loss": 0.0322, "learning_rate": 4.7274779393844536e-05}
+{"step": 54150, "dynamics_loss_avg": 0.024216621462255717}
+{"step": 54150, "action_loss_avg": 0.0016663133108522743}
+{"step": 54160, "dynamics_loss_avg": 0.03262925166636706}
+{"step": 54160, "action_loss_avg": 0.0021582228131592275}
+{"step": 54170, "dynamics_loss_avg": 0.02833847440779209}
+{"step": 54170, "action_loss_avg": 0.0015882114588748665}
+{"step": 54180, "dynamics_loss_avg": 0.026882684789597988}
+{"step": 54180, "action_loss_avg": 0.001361232396448031}
+{"step": 54190, "dynamics_loss_avg": 0.034396369475871325}
+{"step": 54190, "action_loss_avg": 0.00208176820888184}
+{"step": 54200, "loss": 0.0316, "learning_rate": 4.7192232557586264e-05}
+{"step": 54200, "dynamics_loss_avg": 0.022276262473315}
+{"step": 54200, "action_loss_avg": 0.0013074207992758602}
+{"step": 54210, "dynamics_loss_avg": 0.02359347683377564}
+{"step": 54210, "action_loss_avg": 0.0016169404596439562}
+{"step": 54220, "dynamics_loss_avg": 0.02383359051309526}
+{"step": 54220, "action_loss_avg": 0.0014853128435788677}
+{"step": 54230, "dynamics_loss_avg": 0.0303626905195415}
+{"step": 54230, "action_loss_avg": 0.0019697641022503377}
+{"step": 54240, "dynamics_loss_avg": 0.027874481584876775}
+{"step": 54240, "action_loss_avg": 0.0020351666171336547}
+{"step": 54250, "loss": 0.0294, "learning_rate": 4.7109693397656986e-05}
+{"step": 54250, "dynamics_loss_avg": 0.025169579964131116}
+{"step": 54250, "action_loss_avg": 0.0010851872531929985}
+{"step": 54260, "dynamics_loss_avg": 0.03179005039855838}
+{"step": 54260, "action_loss_avg": 0.0016262971534160898}
+{"step": 54270, "dynamics_loss_avg": 0.031569226644933224}
+{"step": 54270, "action_loss_avg": 0.0015164931071922183}
+{"step": 54280, "dynamics_loss_avg": 0.02446694313548505}
+{"step": 54280, "action_loss_avg": 0.0014064452436286957}
+{"step": 54290, "dynamics_loss_avg": 0.029451752826571465}
+{"step": 54290, "action_loss_avg": 0.001720838010078296}
+{"step": 54300, "loss": 0.0325, "learning_rate": 4.702716213971557e-05}
+{"step": 54300, "dynamics_loss_avg": 0.04089218806475401}
+{"step": 54300, "action_loss_avg": 0.0016463625768665224}
+{"step": 54310, "dynamics_loss_avg": 0.03522022571414709}
+{"step": 54310, "action_loss_avg": 0.0019113210262730717}
+{"step": 54320, "dynamics_loss_avg": 0.026025968324393033}
+{"step": 54320, "action_loss_avg": 0.0014005374163389207}
+{"step": 54330, "dynamics_loss_avg": 0.022547055734321475}
+{"step": 54330, "action_loss_avg": 0.0015102030360139907}
+{"step": 54340, "dynamics_loss_avg": 0.031989692337810995}
+{"step": 54340, "action_loss_avg": 0.0016630666272249074}
+{"step": 54350, "loss": 0.0315, "learning_rate": 4.694463900939933e-05}
+{"step": 54350, "dynamics_loss_avg": 0.03061487963423133}
+{"step": 54350, "action_loss_avg": 0.0013083474972518162}
+{"step": 54360, "dynamics_loss_avg": 0.02893824060447514}
+{"step": 54360, "action_loss_avg": 0.0022364741191267965}
+{"step": 54370, "dynamics_loss_avg": 0.035369593929499385}
+{"step": 54370, "action_loss_avg": 0.0017889971728436648}
+{"step": 54380, "dynamics_loss_avg": 0.024545588996261358}
+{"step": 54380, "action_loss_avg": 0.0017090102133806794}
+{"step": 54390, "dynamics_loss_avg": 0.02933551324531436}
+{"step": 54390, "action_loss_avg": 0.001572705662692897}
+{"step": 54400, "loss": 0.032, "learning_rate": 4.686212423232339e-05}
+{"step": 54400, "dynamics_loss_avg": 0.031398987770080565}
+{"step": 54400, "action_loss_avg": 0.0016227996064117178}
+{"step": 54410, "dynamics_loss_avg": 0.028154595149680973}
+{"step": 54410, "action_loss_avg": 0.0013845162582583725}
+{"step": 54420, "dynamics_loss_avg": 0.022301938198506833}
+{"step": 54420, "action_loss_avg": 0.0010127154411748052}
+{"step": 54430, "dynamics_loss_avg": 0.025174649152904748}
+{"step": 54430, "action_loss_avg": 0.0014190980000421405}
+{"step": 54440, "dynamics_loss_avg": 0.02422099793329835}
+{"step": 54440, "action_loss_avg": 0.0010893670289078728}
+{"step": 54450, "loss": 0.0301, "learning_rate": 4.6779618034079975e-05}
+{"step": 54450, "dynamics_loss_avg": 0.035963610373437406}
+{"step": 54450, "action_loss_avg": 0.002167302812449634}
+{"step": 54460, "dynamics_loss_avg": 0.03070300128310919}
+{"step": 54460, "action_loss_avg": 0.0013922041689511389}
+{"step": 54470, "dynamics_loss_avg": 0.025933159096166492}
+{"step": 54470, "action_loss_avg": 0.0014373935468029232}
+{"step": 54480, "dynamics_loss_avg": 0.028380489069968463}
+{"step": 54480, "action_loss_avg": 0.0014024151430930942}
+{"step": 54490, "dynamics_loss_avg": 0.0342147346585989}
+{"step": 54490, "action_loss_avg": 0.0017359536635922269}
+{"step": 54500, "loss": 0.033, "learning_rate": 4.669712064023791e-05}
+{"step": 54500, "dynamics_loss_avg": 0.031864348938688634}
+{"step": 54500, "action_loss_avg": 0.0022408522956538944}
+{"step": 54510, "dynamics_loss_avg": 0.02246672259643674}
+{"step": 54510, "action_loss_avg": 0.0015069861139636487}
+{"step": 54520, "dynamics_loss_avg": 0.023821711260825395}
+{"step": 54520, "action_loss_avg": 0.0012781161422026344}
+{"step": 54530, "dynamics_loss_avg": 0.0318261475302279}
+{"step": 54530, "action_loss_avg": 0.0020709008735138924}
+{"step": 54540, "dynamics_loss_avg": 0.025999591406434774}
+{"step": 54540, "action_loss_avg": 0.0012324561888817699}
+{"step": 54550, "loss": 0.0291, "learning_rate": 4.661463227634187e-05}
+{"step": 54550, "dynamics_loss_avg": 0.027940339082852005}
+{"step": 54550, "action_loss_avg": 0.0011358687363099307}
+{"step": 54560, "dynamics_loss_avg": 0.02460276400670409}
+{"step": 54560, "action_loss_avg": 0.001596066093770787}
+{"step": 54570, "dynamics_loss_avg": 0.025701962877064943}
+{"step": 54570, "action_loss_avg": 0.001403677772032097}
+{"step": 54580, "dynamics_loss_avg": 0.025096209067851306}
+{"step": 54580, "action_loss_avg": 0.0013327649881830438}
+{"step": 54590, "dynamics_loss_avg": 0.030801284220069648}
+{"step": 54590, "action_loss_avg": 0.0014718513819389045}
+{"step": 54600, "loss": 0.0302, "learning_rate": 4.65321531679119e-05}
+{"step": 54600, "dynamics_loss_avg": 0.038534451927989724}
+{"step": 54600, "action_loss_avg": 0.0020372775819851086}
+{"step": 54610, "dynamics_loss_avg": 0.03459088858217001}
+{"step": 54610, "action_loss_avg": 0.002053083182545379}
+{"step": 54620, "dynamics_loss_avg": 0.039197398070245984}
+{"step": 54620, "action_loss_avg": 0.0016639858833514154}
+{"step": 54630, "dynamics_loss_avg": 0.025103114359080792}
+{"step": 54630, "action_loss_avg": 0.0010988939029630274}
+{"step": 54640, "dynamics_loss_avg": 0.028769179293885828}
+{"step": 54640, "action_loss_avg": 0.0011019802244845779}
+{"step": 54650, "loss": 0.0329, "learning_rate": 4.644968354044277e-05}
+{"step": 54650, "dynamics_loss_avg": 0.04031558837741613}
+{"step": 54650, "action_loss_avg": 0.0022209829825442285}
+{"step": 54660, "dynamics_loss_avg": 0.0248220001347363}
+{"step": 54660, "action_loss_avg": 0.001306019228650257}
+{"step": 54670, "dynamics_loss_avg": 0.034447063505649564}
+{"step": 54670, "action_loss_avg": 0.0015547556686215103}
+{"step": 54680, "dynamics_loss_avg": 0.016666190023534}
+{"step": 54680, "action_loss_avg": 0.0009775447979336604}
+{"step": 54690, "dynamics_loss_avg": 0.025063095800578594}
+{"step": 54690, "action_loss_avg": 0.0011048750369809569}
+{"step": 54700, "loss": 0.0299, "learning_rate": 4.636722361940329e-05}
+{"step": 54700, "dynamics_loss_avg": 0.03519508168101311}
+{"step": 54700, "action_loss_avg": 0.0018033988191746176}
+{"step": 54710, "dynamics_loss_avg": 0.0318496385589242}
+{"step": 54710, "action_loss_avg": 0.001520409234217368}
+{"step": 54720, "dynamics_loss_avg": 0.031522417161613706}
+{"step": 54720, "action_loss_avg": 0.0019147155137034134}
+{"step": 54730, "dynamics_loss_avg": 0.035052406159229575}
+{"step": 54730, "action_loss_avg": 0.0018157935613999144}
+{"step": 54740, "dynamics_loss_avg": 0.02044898197054863}
+{"step": 54740, "action_loss_avg": 0.0014584566146368162}
+{"step": 54750, "loss": 0.0315, "learning_rate": 4.628477363023569e-05}
+{"step": 54750, "dynamics_loss_avg": 0.036238664062693715}
+{"step": 54750, "action_loss_avg": 0.0019735691603273153}
+{"step": 54760, "dynamics_loss_avg": 0.025243519432842733}
+{"step": 54760, "action_loss_avg": 0.0014459484198596328}
+{"step": 54770, "dynamics_loss_avg": 0.032146808411926034}
+{"step": 54770, "action_loss_avg": 0.001862770234583877}
+{"step": 54780, "dynamics_loss_avg": 0.03471190687268973}
+{"step": 54780, "action_loss_avg": 0.002250452822772786}
+{"step": 54790, "dynamics_loss_avg": 0.023825672548264266}
+{"step": 54790, "action_loss_avg": 0.001479898573597893}
+{"step": 54800, "loss": 0.0296, "learning_rate": 4.620233379835513e-05}
+{"step": 54800, "dynamics_loss_avg": 0.024543279316276312}
+{"step": 54800, "action_loss_avg": 0.0006935625016922132}
+{"step": 54810, "dynamics_loss_avg": 0.025173203833401204}
+{"step": 54810, "action_loss_avg": 0.0012854170228820295}
+{"step": 54820, "dynamics_loss_avg": 0.026695098355412485}
+{"step": 54820, "action_loss_avg": 0.0015325107058743014}
+{"step": 54830, "dynamics_loss_avg": 0.0312006208114326}
+{"step": 54830, "action_loss_avg": 0.0017196435714140535}
+{"step": 54840, "dynamics_loss_avg": 0.029827400017529725}
+{"step": 54840, "action_loss_avg": 0.002211611467646435}
+{"step": 54850, "loss": 0.0307, "learning_rate": 4.6119904349148935e-05}
+{"step": 54850, "dynamics_loss_avg": 0.034054912719875575}
+{"step": 54850, "action_loss_avg": 0.002032698894618079}
+{"step": 54860, "dynamics_loss_avg": 0.02565949857234955}
+{"step": 54860, "action_loss_avg": 0.0015893860487267374}
+{"step": 54870, "dynamics_loss_avg": 0.022486830502748488}
+{"step": 54870, "action_loss_avg": 0.0015271358599420637}
+{"step": 54880, "dynamics_loss_avg": 0.03382543902844191}
+{"step": 54880, "action_loss_avg": 0.0019960705074481668}
+{"step": 54890, "dynamics_loss_avg": 0.02313498405274004}
+{"step": 54890, "action_loss_avg": 0.0011115986941149457}
+{"step": 54900, "loss": 0.0308, "learning_rate": 4.6037485507976094e-05}
+{"step": 54900, "dynamics_loss_avg": 0.03942391686141491}
+{"step": 54900, "action_loss_avg": 0.0024619337142212316}
+{"step": 54910, "dynamics_loss_avg": 0.039482903108000754}
+{"step": 54910, "action_loss_avg": 0.0024326209910213946}
+{"step": 54920, "dynamics_loss_avg": 0.02924056528136134}
+{"step": 54920, "action_loss_avg": 0.0014940862281946465}
+{"step": 54930, "dynamics_loss_avg": 0.03938458450138569}
+{"step": 54930, "action_loss_avg": 0.0020857617200817913}
+{"step": 54940, "dynamics_loss_avg": 0.03363564135506749}
+{"step": 54940, "action_loss_avg": 0.002004621044034138}
+{"step": 54950, "loss": 0.0326, "learning_rate": 4.59550775001666e-05}
+{"step": 54950, "dynamics_loss_avg": 0.021848274441435934}
+{"step": 54950, "action_loss_avg": 0.0008549399790354073}
+{"step": 54960, "dynamics_loss_avg": 0.0337243883870542}
+{"step": 54960, "action_loss_avg": 0.0017868663650006055}
+{"step": 54970, "dynamics_loss_avg": 0.026215449313167483}
+{"step": 54970, "action_loss_avg": 0.001553559460444376}
+{"step": 54980, "dynamics_loss_avg": 0.02672099326737225}
+{"step": 54980, "action_loss_avg": 0.0012674932659137994}
+{"step": 54990, "dynamics_loss_avg": 0.03409726768732071}
+{"step": 54990, "action_loss_avg": 0.0016300001763738692}
+{"step": 55000, "loss": 0.0309, "learning_rate": 4.5872680551020734e-05}
+{"step": 55000, "dynamics_loss_avg": 0.034817708656191826}
+{"step": 55000, "action_loss_avg": 0.002015224669594318}
+{"step": 55010, "dynamics_loss_avg": 0.03261342067271471}
+{"step": 55010, "action_loss_avg": 0.001599059603177011}
+{"step": 55020, "dynamics_loss_avg": 0.038956517726182936}
+{"step": 55020, "action_loss_avg": 0.0025659372739028187}
+{"step": 55030, "dynamics_loss_avg": 0.02182105416432023}
+{"step": 55030, "action_loss_avg": 0.0010911422781646253}
+{"step": 55040, "dynamics_loss_avg": 0.028002177644521}
+{"step": 55040, "action_loss_avg": 0.0017835665785241872}
+{"step": 55050, "loss": 0.0305, "learning_rate": 4.579029488580865e-05}
+{"step": 55050, "dynamics_loss_avg": 0.018679440347477795}
+{"step": 55050, "action_loss_avg": 0.0012244327735970728}
+{"step": 55060, "dynamics_loss_avg": 0.023188717709854246}
+{"step": 55060, "action_loss_avg": 0.0009898489370243624}
+{"step": 55070, "dynamics_loss_avg": 0.02919613877311349}
+{"step": 55070, "action_loss_avg": 0.0013858737802365795}
+{"step": 55080, "dynamics_loss_avg": 0.02981828819029033}
+{"step": 55080, "action_loss_avg": 0.0020966715150279925}
+{"step": 55090, "dynamics_loss_avg": 0.032458706945180896}
+{"step": 55090, "action_loss_avg": 0.0018989329575560987}
+{"step": 55100, "loss": 0.0294, "learning_rate": 4.570792072976958e-05}
+{"step": 55100, "dynamics_loss_avg": 0.02358323847874999}
+{"step": 55100, "action_loss_avg": 0.0014664529269794002}
+{"step": 55110, "dynamics_loss_avg": 0.029388386569917203}
+{"step": 55110, "action_loss_avg": 0.0017147785460110755}
+{"step": 55120, "dynamics_loss_avg": 0.025248247664421797}
+{"step": 55120, "action_loss_avg": 0.0018497638055123388}
+{"step": 55130, "dynamics_loss_avg": 0.021074107475578786}
+{"step": 55130, "action_loss_avg": 0.0009318124211858958}
+{"step": 55140, "dynamics_loss_avg": 0.027937075961381196}
+{"step": 55140, "action_loss_avg": 0.0016392509685829281}
+{"step": 55150, "loss": 0.0272, "learning_rate": 4.5625558308111356e-05}
+{"step": 55150, "dynamics_loss_avg": 0.025627330876886845}
+{"step": 55150, "action_loss_avg": 0.0012608325574547052}
+{"step": 55160, "dynamics_loss_avg": 0.03235268220305443}
+{"step": 55160, "action_loss_avg": 0.0015028873225674034}
+{"step": 55170, "dynamics_loss_avg": 0.019419067678973077}
+{"step": 55170, "action_loss_avg": 0.0009964409895474092}
+{"step": 55180, "dynamics_loss_avg": 0.021758933179080488}
+{"step": 55180, "action_loss_avg": 0.0012849371298216284}
+{"step": 55190, "dynamics_loss_avg": 0.03194295037537813}
+{"step": 55190, "action_loss_avg": 0.0014657446299679577}
+{"step": 55200, "loss": 0.0295, "learning_rate": 4.5543207846009705e-05}
+{"step": 55200, "dynamics_loss_avg": 0.029474645759910344}
+{"step": 55200, "action_loss_avg": 0.0014448871574131773}
+{"step": 55210, "dynamics_loss_avg": 0.03002001205459237}
+{"step": 55210, "action_loss_avg": 0.0016710511757992209}
+{"step": 55220, "dynamics_loss_avg": 0.03077788222581148}
+{"step": 55220, "action_loss_avg": 0.0012470940302591771}
+{"step": 55230, "dynamics_loss_avg": 0.030684377625584604}
+{"step": 55230, "action_loss_avg": 0.0014855083951260894}
+{"step": 55240, "dynamics_loss_avg": 0.0421273767016828}
+{"step": 55240, "action_loss_avg": 0.0027161840815097095}
+{"step": 55250, "loss": 0.0317, "learning_rate": 4.546086956860759e-05}
+{"step": 55250, "dynamics_loss_avg": 0.023508598934859036}
+{"step": 55250, "action_loss_avg": 0.0013969331455882638}
+{"step": 55260, "dynamics_loss_avg": 0.02719037593342364}
+{"step": 55260, "action_loss_avg": 0.001499657379463315}
+{"step": 55270, "dynamics_loss_avg": 0.028958558943122624}
+{"step": 55270, "action_loss_avg": 0.0021983823855407534}
+{"step": 55280, "dynamics_loss_avg": 0.024705262784846128}
+{"step": 55280, "action_loss_avg": 0.0016719166582333856}
+{"step": 55290, "dynamics_loss_avg": 0.031407846976071595}
+{"step": 55290, "action_loss_avg": 0.001991036330582574}
+{"step": 55300, "loss": 0.0291, "learning_rate": 4.537854370101475e-05}
+{"step": 55300, "dynamics_loss_avg": 0.02638287590816617}
+{"step": 55300, "action_loss_avg": 0.00147500456077978}
+{"step": 55310, "dynamics_loss_avg": 0.026226604450494052}
+{"step": 55310, "action_loss_avg": 0.0017404334677848965}
+{"step": 55320, "dynamics_loss_avg": 0.04011127604171634}
+{"step": 55320, "action_loss_avg": 0.0027724572573788464}
+{"step": 55330, "dynamics_loss_avg": 0.022372209979221225}
+{"step": 55330, "action_loss_avg": 0.0012952179240528494}
+{"step": 55340, "dynamics_loss_avg": 0.024562314338982105}
+{"step": 55340, "action_loss_avg": 0.0016536183975404128}
+{"step": 55350, "loss": 0.0278, "learning_rate": 4.529623046830696e-05}
+{"step": 55350, "dynamics_loss_avg": 0.02480847090482712}
+{"step": 55350, "action_loss_avg": 0.0017520409892313182}
+{"step": 55360, "dynamics_loss_avg": 0.025592204509302975}
+{"step": 55360, "action_loss_avg": 0.0015980004623997956}
+{"step": 55370, "dynamics_loss_avg": 0.025287877954542636}
+{"step": 55370, "action_loss_avg": 0.0012159907346358523}
+{"step": 55380, "dynamics_loss_avg": 0.03504644436761737}
+{"step": 55380, "action_loss_avg": 0.0027161652251379564}
+{"step": 55390, "dynamics_loss_avg": 0.030292895436286927}
+{"step": 55390, "action_loss_avg": 0.0013595771917607636}
+{"step": 55400, "loss": 0.0297, "learning_rate": 4.521393009552549e-05}
+{"step": 55400, "dynamics_loss_avg": 0.0329517631791532}
+{"step": 55400, "action_loss_avg": 0.0017083691258449108}
+{"step": 55410, "dynamics_loss_avg": 0.025657234154641627}
+{"step": 55410, "action_loss_avg": 0.0009612759051378817}
+{"step": 55420, "dynamics_loss_avg": 0.03060266929678619}
+{"step": 55420, "action_loss_avg": 0.0014167975372401998}
+{"step": 55430, "dynamics_loss_avg": 0.028734491346403955}
+{"step": 55430, "action_loss_avg": 0.0012920472770929336}
+{"step": 55440, "dynamics_loss_avg": 0.029383631236851216}
+{"step": 55440, "action_loss_avg": 0.002059124922379851}
+{"step": 55450, "loss": 0.0297, "learning_rate": 4.5131642807676356e-05}
+{"step": 55450, "dynamics_loss_avg": 0.02433455679565668}
+{"step": 55450, "action_loss_avg": 0.0013144005148205905}
+{"step": 55460, "dynamics_loss_avg": 0.02584833772853017}
+{"step": 55460, "action_loss_avg": 0.0013476991734933108}
+{"step": 55470, "dynamics_loss_avg": 0.02091600652784109}
+{"step": 55470, "action_loss_avg": 0.0013685667305253445}
+{"step": 55480, "dynamics_loss_avg": 0.024505415465682745}
+{"step": 55480, "action_loss_avg": 0.0017088186694309115}
+{"step": 55490, "dynamics_loss_avg": 0.029814221523702146}
+{"step": 55490, "action_loss_avg": 0.00173072760226205}
+{"step": 55500, "loss": 0.0268, "learning_rate": 4.504936882972989e-05}
+{"step": 55500, "dynamics_loss_avg": 0.02639817213639617}
+{"step": 55500, "action_loss_avg": 0.001509468659060076}
+{"step": 55510, "dynamics_loss_avg": 0.027998715359717607}
+{"step": 55510, "action_loss_avg": 0.001309576176572591}
+{"step": 55520, "dynamics_loss_avg": 0.023572988994419574}
+{"step": 55520, "action_loss_avg": 0.0009288309141993522}
+{"step": 55530, "dynamics_loss_avg": 0.02865158119238913}
+{"step": 55530, "action_loss_avg": 0.001810675160959363}
+{"step": 55540, "dynamics_loss_avg": 0.025893796980381013}
+{"step": 55540, "action_loss_avg": 0.0014092358469497412}
+{"step": 55550, "loss": 0.0279, "learning_rate": 4.496710838661999e-05}
+{"step": 55550, "dynamics_loss_avg": 0.026755896490067245}
+{"step": 55550, "action_loss_avg": 0.0015219800581689924}
+{"step": 55560, "dynamics_loss_avg": 0.02797583704814315}
+{"step": 55560, "action_loss_avg": 0.00187256985809654}
+{"step": 55570, "dynamics_loss_avg": 0.034432812873274085}
+{"step": 55570, "action_loss_avg": 0.0018410680466331541}
+{"step": 55580, "dynamics_loss_avg": 0.03536727237515151}
+{"step": 55580, "action_loss_avg": 0.0013562836800701916}
+{"step": 55590, "dynamics_loss_avg": 0.0313859885558486}
+{"step": 55590, "action_loss_avg": 0.0015202251612208783}
+{"step": 55600, "loss": 0.0323, "learning_rate": 4.488486170324359e-05}
+{"step": 55600, "dynamics_loss_avg": 0.03352578347548842}
+{"step": 55600, "action_loss_avg": 0.0016253698238870129}
+{"step": 55610, "dynamics_loss_avg": 0.03513604155741632}
+{"step": 55610, "action_loss_avg": 0.0020330850093159825}
+{"step": 55620, "dynamics_loss_avg": 0.028941152337938546}
+{"step": 55620, "action_loss_avg": 0.0015035475633339956}
+{"step": 55630, "dynamics_loss_avg": 0.03635232294909656}
+{"step": 55630, "action_loss_avg": 0.0013011931034270674}
+{"step": 55640, "dynamics_loss_avg": 0.024532398954033852}
+{"step": 55640, "action_loss_avg": 0.0015376284543890506}
+{"step": 55650, "loss": 0.0324, "learning_rate": 4.480262900446e-05}
+{"step": 55650, "dynamics_loss_avg": 0.03156696697697044}
+{"step": 55650, "action_loss_avg": 0.0016612267121672631}
+{"step": 55660, "dynamics_loss_avg": 0.027290976140648127}
+{"step": 55660, "action_loss_avg": 0.001255350827705115}
+{"step": 55670, "dynamics_loss_avg": 0.025074374210089446}
+{"step": 55670, "action_loss_avg": 0.0012881830334663391}
+{"step": 55680, "dynamics_loss_avg": 0.03414803054183722}
+{"step": 55680, "action_loss_avg": 0.0014278044109232724}
+{"step": 55690, "dynamics_loss_avg": 0.02525388514623046}
+{"step": 55690, "action_loss_avg": 0.0014167909743264318}
+{"step": 55700, "loss": 0.029, "learning_rate": 4.472041051509023e-05}
+{"step": 55700, "dynamics_loss_avg": 0.027912462875247002}
+{"step": 55700, "action_loss_avg": 0.0011783589026890696}
+{"step": 55710, "dynamics_loss_avg": 0.028939459193497896}
+{"step": 55710, "action_loss_avg": 0.0011056961608119308}
+{"step": 55720, "dynamics_loss_avg": 0.031796346930786965}
+{"step": 55720, "action_loss_avg": 0.0016100723063573242}
+{"step": 55730, "dynamics_loss_avg": 0.0449719819240272}
+{"step": 55730, "action_loss_avg": 0.002067829793668352}
+{"step": 55740, "dynamics_loss_avg": 0.026606045104563235}
+{"step": 55740, "action_loss_avg": 0.00173445614927914}
+{"step": 55750, "loss": 0.0324, "learning_rate": 4.463820645991651e-05}
+{"step": 55750, "dynamics_loss_avg": 0.025741119030863048}
+{"step": 55750, "action_loss_avg": 0.0014854821725748478}
+{"step": 55760, "dynamics_loss_avg": 0.035983174480497836}
+{"step": 55760, "action_loss_avg": 0.0018568497791420669}
+{"step": 55770, "dynamics_loss_avg": 0.033224148815497755}
+{"step": 55770, "action_loss_avg": 0.0017916537035489455}
+{"step": 55780, "dynamics_loss_avg": 0.04147805701941252}
+{"step": 55780, "action_loss_avg": 0.0027412814320996403}
+{"step": 55790, "dynamics_loss_avg": 0.03682235721498728}
+{"step": 55790, "action_loss_avg": 0.002317003428470343}
+{"step": 55800, "loss": 0.0365, "learning_rate": 4.455601706368157e-05}
+{"step": 55800, "dynamics_loss_avg": 0.03542238473892212}
+{"step": 55800, "action_loss_avg": 0.0022855966817587614}
+{"step": 55810, "dynamics_loss_avg": 0.0270756914280355}
+{"step": 55810, "action_loss_avg": 0.0014029998623300345}
+{"step": 55820, "dynamics_loss_avg": 0.025303597468882798}
+{"step": 55820, "action_loss_avg": 0.0014825869206106291}
+{"step": 55830, "dynamics_loss_avg": 0.03317122012376785}
+{"step": 55830, "action_loss_avg": 0.001797109900508076}
+{"step": 55840, "dynamics_loss_avg": 0.029662500880658627}
+{"step": 55840, "action_loss_avg": 0.00194019969785586}
+{"step": 55850, "loss": 0.0313, "learning_rate": 4.4473842551088135e-05}
+{"step": 55850, "dynamics_loss_avg": 0.03774599824100733}
+{"step": 55850, "action_loss_avg": 0.0021353600663132966}
+{"step": 55860, "dynamics_loss_avg": 0.033199348766356704}
+{"step": 55860, "action_loss_avg": 0.0015324750274885446}
+{"step": 55870, "dynamics_loss_avg": 0.027189888060092926}
+{"step": 55870, "action_loss_avg": 0.001621616934426129}
+{"step": 55880, "dynamics_loss_avg": 0.02454095664434135}
+{"step": 55880, "action_loss_avg": 0.0016255394206382335}
+{"step": 55890, "dynamics_loss_avg": 0.021097161155194045}
+{"step": 55890, "action_loss_avg": 0.0011525371199240908}
+{"step": 55900, "loss": 0.0297, "learning_rate": 4.439168314679813e-05}
+{"step": 55900, "dynamics_loss_avg": 0.02154949023388326}
+{"step": 55900, "action_loss_avg": 0.001388254648190923}
+{"step": 55910, "dynamics_loss_avg": 0.030755096487700938}
+{"step": 55910, "action_loss_avg": 0.0014837560360319913}
+{"step": 55920, "dynamics_loss_avg": 0.038322298368439076}
+{"step": 55920, "action_loss_avg": 0.0022615219408180566}
+{"step": 55930, "dynamics_loss_avg": 0.03081697253510356}
+{"step": 55930, "action_loss_avg": 0.0019664014980662614}
+{"step": 55940, "dynamics_loss_avg": 0.03838148396462202}
+{"step": 55940, "action_loss_avg": 0.00189547014888376}
+{"step": 55950, "loss": 0.0332, "learning_rate": 4.430953907543225e-05}
+{"step": 55950, "dynamics_loss_avg": 0.037941761501133445}
+{"step": 55950, "action_loss_avg": 0.001999958575470373}
+{"step": 55960, "dynamics_loss_avg": 0.02618319382891059}
+{"step": 55960, "action_loss_avg": 0.0012901418900582939}
+{"step": 55970, "dynamics_loss_avg": 0.02764274850487709}
+{"step": 55970, "action_loss_avg": 0.0012963591259904205}
+{"step": 55980, "dynamics_loss_avg": 0.021754837594926357}
+{"step": 55980, "action_loss_avg": 0.0015431759165949188}
+{"step": 55990, "dynamics_loss_avg": 0.029632912017405033}
+{"step": 55990, "action_loss_avg": 0.0012651569268200547}
+{"step": 56000, "loss": 0.0295, "learning_rate": 4.422741056156925e-05}
+{"step": 56000, "dynamics_loss_avg": 0.036077491007745266}
+{"step": 56000, "action_loss_avg": 0.002963485202053562}
+{"step": 56010, "dynamics_loss_avg": 0.02148555628955364}
+{"step": 56010, "action_loss_avg": 0.0009651644068071619}
+{"step": 56020, "dynamics_loss_avg": 0.032275880221277475}
+{"step": 56020, "action_loss_avg": 0.001959523861296475}
+{"step": 56030, "dynamics_loss_avg": 0.030738027207553385}
+{"step": 56030, "action_loss_avg": 0.0016240030206972733}
+{"step": 56040, "dynamics_loss_avg": 0.025403673481196164}
+{"step": 56040, "action_loss_avg": 0.0012954096135217696}
+{"step": 56050, "loss": 0.031, "learning_rate": 4.414529782974533e-05}
+{"step": 56050, "dynamics_loss_avg": 0.03838665913790464}
+{"step": 56050, "action_loss_avg": 0.0021113988070283083}
+{"step": 56060, "dynamics_loss_avg": 0.02998393103480339}
+{"step": 56060, "action_loss_avg": 0.001784943137317896}
+{"step": 56070, "dynamics_loss_avg": 0.022539458610117434}
+{"step": 56070, "action_loss_avg": 0.0011967638187343256}
+{"step": 56080, "dynamics_loss_avg": 0.03523885952308774}
+{"step": 56080, "action_loss_avg": 0.0015277641650754958}
+{"step": 56090, "dynamics_loss_avg": 0.02995154056698084}
+{"step": 56090, "action_loss_avg": 0.001467946486081928}
+{"step": 56100, "loss": 0.0311, "learning_rate": 4.406320110445362e-05}
+{"step": 56100, "dynamics_loss_avg": 0.02887624790892005}
+{"step": 56100, "action_loss_avg": 0.0015036362514365465}
+{"step": 56110, "dynamics_loss_avg": 0.03363756658509374}
+{"step": 56110, "action_loss_avg": 0.0022646061435807495}
+{"step": 56120, "dynamics_loss_avg": 0.030927058402448894}
+{"step": 56120, "action_loss_avg": 0.00198695317376405}
+{"step": 56130, "dynamics_loss_avg": 0.030875822063535452}
+{"step": 56130, "action_loss_avg": 0.0014319415669888258}
+{"step": 56140, "dynamics_loss_avg": 0.029691191064193843}
+{"step": 56140, "action_loss_avg": 0.0022939226822927595}
+{"step": 56150, "loss": 0.0308, "learning_rate": 4.398112061014337e-05}
+{"step": 56150, "dynamics_loss_avg": 0.03843764159828424}
+{"step": 56150, "action_loss_avg": 0.001985765347490087}
+{"step": 56160, "dynamics_loss_avg": 0.034234915487468244}
+{"step": 56160, "action_loss_avg": 0.0017996249080169946}
+{"step": 56170, "dynamics_loss_avg": 0.03936904678121209}
+{"step": 56170, "action_loss_avg": 0.002068159164628014}
+{"step": 56180, "dynamics_loss_avg": 0.027673315722495317}
+{"step": 56180, "action_loss_avg": 0.0009338840725831687}
+{"step": 56190, "dynamics_loss_avg": 0.02228703214786947}
+{"step": 56190, "action_loss_avg": 0.0009232213167706504}
+{"step": 56200, "loss": 0.0322, "learning_rate": 4.389905657121955e-05}
+{"step": 56200, "dynamics_loss_avg": 0.02805372920120135}
+{"step": 56200, "action_loss_avg": 0.0015120528638362884}
+{"step": 56210, "dynamics_loss_avg": 0.028049031924456357}
+{"step": 56210, "action_loss_avg": 0.0013044750783592462}
+{"step": 56220, "dynamics_loss_avg": 0.02289827917702496}
+{"step": 56220, "action_loss_avg": 0.0009565155472955666}
+{"step": 56230, "dynamics_loss_avg": 0.028090290632098912}
+{"step": 56230, "action_loss_avg": 0.0014701184787554666}
+{"step": 56240, "dynamics_loss_avg": 0.028968915203586222}
+{"step": 56240, "action_loss_avg": 0.0011087512160884217}
+{"step": 56250, "loss": 0.029, "learning_rate": 4.381700921204209e-05}
+{"step": 56250, "dynamics_loss_avg": 0.0347124857828021}
+{"step": 56250, "action_loss_avg": 0.0014351724414154888}
+{"step": 56260, "dynamics_loss_avg": 0.02484711315482855}
+{"step": 56260, "action_loss_avg": 0.0011009691312210633}
+{"step": 56270, "dynamics_loss_avg": 0.032984380656853315}
+{"step": 56270, "action_loss_avg": 0.0016069364894065075}
+{"step": 56280, "dynamics_loss_avg": 0.0224898817948997}
+{"step": 56280, "action_loss_avg": 0.0011471290548797698}
+{"step": 56290, "dynamics_loss_avg": 0.02648418853059411}
+{"step": 56290, "action_loss_avg": 0.0010525569261517376}
+{"step": 56300, "loss": 0.0295, "learning_rate": 4.3734978756925346e-05}
+{"step": 56300, "dynamics_loss_avg": 0.03819253789260983}
+{"step": 56300, "action_loss_avg": 0.0016935776569880546}
+{"step": 56310, "dynamics_loss_avg": 0.029996647126972677}
+{"step": 56310, "action_loss_avg": 0.0014418182574445382}
+{"step": 56320, "dynamics_loss_avg": 0.030535204336047173}
+{"step": 56320, "action_loss_avg": 0.0017218359687831252}
+{"step": 56330, "dynamics_loss_avg": 0.020835709758102894}
+{"step": 56330, "action_loss_avg": 0.0011129941151011736}
+{"step": 56340, "dynamics_loss_avg": 0.022341697569936515}
+{"step": 56340, "action_loss_avg": 0.0013828008435666562}
+{"step": 56350, "loss": 0.0303, "learning_rate": 4.3652965430137474e-05}
+{"step": 56350, "dynamics_loss_avg": 0.027862699516117573}
+{"step": 56350, "action_loss_avg": 0.001885460750781931}
+{"step": 56360, "dynamics_loss_avg": 0.024981418903917075}
+{"step": 56360, "action_loss_avg": 0.0011292539595160634}
+{"step": 56370, "dynamics_loss_avg": 0.026724952459335326}
+{"step": 56370, "action_loss_avg": 0.0013483750866726042}
+{"step": 56380, "dynamics_loss_avg": 0.026573659013956787}
+{"step": 56380, "action_loss_avg": 0.0014297326997620985}
+{"step": 56390, "dynamics_loss_avg": 0.03030316550284624}
+{"step": 56390, "action_loss_avg": 0.0019146761391311885}
+{"step": 56400, "loss": 0.0284, "learning_rate": 4.357096945589974e-05}
+{"step": 56400, "dynamics_loss_avg": 0.028881727065891028}
+{"step": 56400, "action_loss_avg": 0.0018756346893496812}
+{"step": 56410, "dynamics_loss_avg": 0.03520362954586744}
+{"step": 56410, "action_loss_avg": 0.002123902412131429}
+{"step": 56420, "dynamics_loss_avg": 0.01941861156374216}
+{"step": 56420, "action_loss_avg": 0.0009519684768747539}
+{"step": 56430, "dynamics_loss_avg": 0.034848449379205705}
+{"step": 56430, "action_loss_avg": 0.0021743948804214598}
+{"step": 56440, "dynamics_loss_avg": 0.03262191582471132}
+{"step": 56440, "action_loss_avg": 0.0018013265042100101}
+{"step": 56450, "loss": 0.0307, "learning_rate": 4.348899105838602e-05}
+{"step": 56450, "dynamics_loss_avg": 0.030651956796646118}
+{"step": 56450, "action_loss_avg": 0.0013315680902451278}
+{"step": 56460, "dynamics_loss_avg": 0.03176349988207221}
+{"step": 56460, "action_loss_avg": 0.001854478137101978}
+{"step": 56470, "dynamics_loss_avg": 0.027783689461648463}
+{"step": 56470, "action_loss_avg": 0.001686084721586667}
+{"step": 56480, "dynamics_loss_avg": 0.03194259852170944}
+{"step": 56480, "action_loss_avg": 0.0016793015936855226}
+{"step": 56490, "dynamics_loss_avg": 0.022317239688709377}
+{"step": 56490, "action_loss_avg": 0.0013535051708458922}
+{"step": 56500, "loss": 0.0288, "learning_rate": 4.340703046172213e-05}
+{"step": 56500, "dynamics_loss_avg": 0.023453044798225166}
+{"step": 56500, "action_loss_avg": 0.001030748145421967}
+{"step": 56510, "dynamics_loss_avg": 0.02471015420742333}
+{"step": 56510, "action_loss_avg": 0.001506032340694219}
+{"step": 56520, "dynamics_loss_avg": 0.025733229145407675}
+{"step": 56520, "action_loss_avg": 0.0018117826577508823}
+{"step": 56530, "dynamics_loss_avg": 0.022637307364493608}
+{"step": 56530, "action_loss_avg": 0.0008461984543828294}
+{"step": 56540, "dynamics_loss_avg": 0.035913854278624056}
+{"step": 56540, "action_loss_avg": 0.001836533285677433}
+{"step": 56550, "loss": 0.0275, "learning_rate": 4.33250878899852e-05}
+{"step": 56550, "dynamics_loss_avg": 0.03188254283741117}
+{"step": 56550, "action_loss_avg": 0.0016697928396752105}
+{"step": 56560, "dynamics_loss_avg": 0.02795396838337183}
+{"step": 56560, "action_loss_avg": 0.0017017607082379983}
+{"step": 56570, "dynamics_loss_avg": 0.028584095928817988}
+{"step": 56570, "action_loss_avg": 0.0012590608588652686}
+{"step": 56580, "dynamics_loss_avg": 0.023226056806743146}
+{"step": 56580, "action_loss_avg": 0.0010141907405341044}
+{"step": 56590, "dynamics_loss_avg": 0.024581733532249926}
+{"step": 56590, "action_loss_avg": 0.0008986483182525263}
+{"step": 56600, "loss": 0.0279, "learning_rate": 4.32431635672031e-05}
+{"step": 56600, "dynamics_loss_avg": 0.022684830147773026}
+{"step": 56600, "action_loss_avg": 0.0010713047813624144}
+{"step": 56610, "dynamics_loss_avg": 0.036878168489784}
+{"step": 56610, "action_loss_avg": 0.0021099219913594423}
+{"step": 56620, "dynamics_loss_avg": 0.022171610873192547}
+{"step": 56620, "action_loss_avg": 0.0012309660291066394}
+{"step": 56630, "dynamics_loss_avg": 0.039909392781555655}
+{"step": 56630, "action_loss_avg": 0.001897421124158427}
+{"step": 56640, "dynamics_loss_avg": 0.036582143232226375}
+{"step": 56640, "action_loss_avg": 0.0022439543216023596}
+{"step": 56650, "loss": 0.0327, "learning_rate": 4.31612577173538e-05}
+{"step": 56650, "dynamics_loss_avg": 0.03131713671609759}
+{"step": 56650, "action_loss_avg": 0.0019673568574944513}
+{"step": 56660, "dynamics_loss_avg": 0.02424373961985111}
+{"step": 56660, "action_loss_avg": 0.0012815809692256152}
+{"step": 56670, "dynamics_loss_avg": 0.028506753128021957}
+{"step": 56670, "action_loss_avg": 0.00162854163791053}
+{"step": 56680, "dynamics_loss_avg": 0.02556318901479244}
+{"step": 56680, "action_loss_avg": 0.0012130494142184034}
+{"step": 56690, "dynamics_loss_avg": 0.02731279549188912}
+{"step": 56690, "action_loss_avg": 0.0013745121657848358}
+{"step": 56700, "loss": 0.0283, "learning_rate": 4.3079370564364755e-05}
+{"step": 56700, "dynamics_loss_avg": 0.024033184722065927}
+{"step": 56700, "action_loss_avg": 0.0012339904700638727}
+{"step": 56710, "dynamics_loss_avg": 0.02370147192850709}
+{"step": 56710, "action_loss_avg": 0.0014240867138141766}
+{"step": 56720, "dynamics_loss_avg": 0.02755132419988513}
+{"step": 56720, "action_loss_avg": 0.0013980617630295455}
+{"step": 56730, "dynamics_loss_avg": 0.03416038975119591}
+{"step": 56730, "action_loss_avg": 0.002045151236234233}
+{"step": 56740, "dynamics_loss_avg": 0.03828200213611126}
+{"step": 56740, "action_loss_avg": 0.002104557154234499}
+{"step": 56750, "loss": 0.0304, "learning_rate": 4.299750233211233e-05}
+{"step": 56750, "dynamics_loss_avg": 0.026523626875132322}
+{"step": 56750, "action_loss_avg": 0.0012834422406740487}
+{"step": 56760, "dynamics_loss_avg": 0.029874706640839577}
+{"step": 56760, "action_loss_avg": 0.0017069168156012894}
+{"step": 56770, "dynamics_loss_avg": 0.027680124063044785}
+{"step": 56770, "action_loss_avg": 0.0013074288319330663}
+{"step": 56780, "dynamics_loss_avg": 0.016813725186511874}
+{"step": 56780, "action_loss_avg": 0.0010090933297760784}
+{"step": 56790, "dynamics_loss_avg": 0.032970793452113865}
+{"step": 56790, "action_loss_avg": 0.0018840671837097034}
+{"step": 56800, "loss": 0.03, "learning_rate": 4.291565324442115e-05}
+{"step": 56800, "dynamics_loss_avg": 0.032356871943920854}
+{"step": 56800, "action_loss_avg": 0.001725889288354665}
+{"step": 56810, "dynamics_loss_avg": 0.034938014857470986}
+{"step": 56810, "action_loss_avg": 0.00176456471090205}
+{"step": 56820, "dynamics_loss_avg": 0.032944902498275044}
+{"step": 56820, "action_loss_avg": 0.0016144847148098051}
+{"step": 56830, "dynamics_loss_avg": 0.03696092497557402}
+{"step": 56830, "action_loss_avg": 0.0016793911054264754}
+{"step": 56840, "dynamics_loss_avg": 0.024479807587340474}
+{"step": 56840, "action_loss_avg": 0.0014001624134834857}
+{"step": 56850, "loss": 0.0355, "learning_rate": 4.283382352506347e-05}
+{"step": 56850, "dynamics_loss_avg": 0.031131326220929623}
+{"step": 56850, "action_loss_avg": 0.0017845386464614421}
+{"step": 56860, "dynamics_loss_avg": 0.023139890888705848}
+{"step": 56860, "action_loss_avg": 0.0012288415149669164}
+{"step": 56870, "dynamics_loss_avg": 0.0245549856685102}
+{"step": 56870, "action_loss_avg": 0.0011311234527966007}
+{"step": 56880, "dynamics_loss_avg": 0.027937480434775352}
+{"step": 56880, "action_loss_avg": 0.00131326699629426}
+{"step": 56890, "dynamics_loss_avg": 0.027893891930580138}
+{"step": 56890, "action_loss_avg": 0.0012973570497706532}
+{"step": 56900, "loss": 0.0293, "learning_rate": 4.275201339775864e-05}
+{"step": 56900, "dynamics_loss_avg": 0.029680917970836163}
+{"step": 56900, "action_loss_avg": 0.0012779937853338197}
+{"step": 56910, "dynamics_loss_avg": 0.03285446064546704}
+{"step": 56910, "action_loss_avg": 0.0021805502474308014}
+{"step": 56920, "dynamics_loss_avg": 0.03021503333002329}
+{"step": 56920, "action_loss_avg": 0.002256724354811013}
+{"step": 56930, "dynamics_loss_avg": 0.03560861758887768}
+{"step": 56930, "action_loss_avg": 0.001230372628197074}
+{"step": 56940, "dynamics_loss_avg": 0.04297567196190357}
+{"step": 56940, "action_loss_avg": 0.0026267167937476187}
+{"step": 56950, "loss": 0.0322, "learning_rate": 4.267022308617241e-05}
+{"step": 56950, "dynamics_loss_avg": 0.02662078971043229}
+{"step": 56950, "action_loss_avg": 0.0009600687713827938}
+{"step": 56960, "dynamics_loss_avg": 0.025488861091434955}
+{"step": 56960, "action_loss_avg": 0.001360820251284167}
+{"step": 56970, "dynamics_loss_avg": 0.03451181100681424}
+{"step": 56970, "action_loss_avg": 0.0013121162774041295}
+{"step": 56980, "dynamics_loss_avg": 0.039536824263632295}
+{"step": 56980, "action_loss_avg": 0.0019216356537071987}
+{"step": 56990, "dynamics_loss_avg": 0.02763206036761403}
+{"step": 56990, "action_loss_avg": 0.0014340761437779293}
+{"step": 57000, "loss": 0.0298, "learning_rate": 4.258845281391638e-05}
+{"step": 57000, "dynamics_loss_avg": 0.027801874466240405}
+{"step": 57000, "action_loss_avg": 0.00188042328809388}
+{"step": 57010, "dynamics_loss_avg": 0.028656833339482546}
+{"step": 57010, "action_loss_avg": 0.0019535933213774117}
+{"step": 57020, "dynamics_loss_avg": 0.023855503741651775}
+{"step": 57020, "action_loss_avg": 0.001659725996432826}
+{"step": 57030, "dynamics_loss_avg": 0.03138732220977545}
+{"step": 57030, "action_loss_avg": 0.0015871221548877656}
+{"step": 57040, "dynamics_loss_avg": 0.023738948907703162}
+{"step": 57040, "action_loss_avg": 0.0010565259610302747}
+{"step": 57050, "loss": 0.0277, "learning_rate": 4.2506702804547356e-05}
+{"step": 57050, "dynamics_loss_avg": 0.030936272954568265}
+{"step": 57050, "action_loss_avg": 0.001788345433305949}
+{"step": 57060, "dynamics_loss_avg": 0.03221940416842699}
+{"step": 57060, "action_loss_avg": 0.002094476850470528}
+{"step": 57070, "dynamics_loss_avg": 0.032102198153734204}
+{"step": 57070, "action_loss_avg": 0.001957856270018965}
+{"step": 57080, "dynamics_loss_avg": 0.028213997557759284}
+{"step": 57080, "action_loss_avg": 0.0015296310477424413}
+{"step": 57090, "dynamics_loss_avg": 0.024784868769347667}
+{"step": 57090, "action_loss_avg": 0.0011738339584553615}
+{"step": 57100, "loss": 0.0305, "learning_rate": 4.242497328156672e-05}
+{"step": 57100, "dynamics_loss_avg": 0.03751949779689312}
+{"step": 57100, "action_loss_avg": 0.0016914613952394575}
+{"step": 57110, "dynamics_loss_avg": 0.03854365609586239}
+{"step": 57110, "action_loss_avg": 0.0024753509904257955}
+{"step": 57120, "dynamics_loss_avg": 0.03444763207808137}
+{"step": 57120, "action_loss_avg": 0.0022029381478205325}
+{"step": 57130, "dynamics_loss_avg": 0.0241378590464592}
+{"step": 57130, "action_loss_avg": 0.0014479065139312297}
+{"step": 57140, "dynamics_loss_avg": 0.027568758744746447}
+{"step": 57140, "action_loss_avg": 0.0015157267276663332}
+{"step": 57150, "loss": 0.0301, "learning_rate": 4.2343264468419885e-05}
+{"step": 57150, "dynamics_loss_avg": 0.029828548338264226}
+{"step": 57150, "action_loss_avg": 0.0016778717719716952}
+{"step": 57160, "dynamics_loss_avg": 0.02449635211378336}
+{"step": 57160, "action_loss_avg": 0.0010120913793798536}
+{"step": 57170, "dynamics_loss_avg": 0.020332599803805352}
+{"step": 57170, "action_loss_avg": 0.0008210938947740942}
+{"step": 57180, "dynamics_loss_avg": 0.02930151456966996}
+{"step": 57180, "action_loss_avg": 0.0017639646830502898}
+{"step": 57190, "dynamics_loss_avg": 0.029637012630701065}
+{"step": 57190, "action_loss_avg": 0.0013060191529802978}
+{"step": 57200, "loss": 0.0293, "learning_rate": 4.226157658849562e-05}
+{"step": 57200, "dynamics_loss_avg": 0.035453051794320345}
+{"step": 57200, "action_loss_avg": 0.0019639798876596613}
+{"step": 57210, "dynamics_loss_avg": 0.029428181424736976}
+{"step": 57210, "action_loss_avg": 0.0013821861415635795}
+{"step": 57220, "dynamics_loss_avg": 0.02919336948543787}
+{"step": 57220, "action_loss_avg": 0.0014057487569516525}
+{"step": 57230, "dynamics_loss_avg": 0.02793260905891657}
+{"step": 57230, "action_loss_avg": 0.0013768831922789104}
+{"step": 57240, "dynamics_loss_avg": 0.038291335478425025}
+{"step": 57240, "action_loss_avg": 0.002113060688134283}
+{"step": 57250, "loss": 0.0303, "learning_rate": 4.217990986512548e-05}
+{"step": 57250, "dynamics_loss_avg": 0.030794070940464734}
+{"step": 57250, "action_loss_avg": 0.0017970264132600277}
+{"step": 57260, "dynamics_loss_avg": 0.03217402128502726}
+{"step": 57260, "action_loss_avg": 0.0015340236539486795}
+{"step": 57270, "dynamics_loss_avg": 0.028627904411405326}
+{"step": 57270, "action_loss_avg": 0.0020976644940674306}
+{"step": 57280, "dynamics_loss_avg": 0.02979206293821335}
+{"step": 57280, "action_loss_avg": 0.0015148592297919094}
+{"step": 57290, "dynamics_loss_avg": 0.023937203641980886}
+{"step": 57290, "action_loss_avg": 0.0012785091123078019}
+{"step": 57300, "loss": 0.0303, "learning_rate": 4.209826452158315e-05}
+{"step": 57300, "dynamics_loss_avg": 0.028226119000464678}
+{"step": 57300, "action_loss_avg": 0.0010932735545793547}
+{"step": 57310, "dynamics_loss_avg": 0.04353569354861975}
+{"step": 57310, "action_loss_avg": 0.0024109853664413096}
+{"step": 57320, "dynamics_loss_avg": 0.031196577381342648}
+{"step": 57320, "action_loss_avg": 0.0013395013695117087}
+{"step": 57330, "dynamics_loss_avg": 0.023078371491283178}
+{"step": 57330, "action_loss_avg": 0.0012459625606425107}
+{"step": 57340, "dynamics_loss_avg": 0.02596345152705908}
+{"step": 57340, "action_loss_avg": 0.0015686220314819366}
+{"step": 57350, "loss": 0.0282, "learning_rate": 4.2016640781083887e-05}
+{"step": 57350, "dynamics_loss_avg": 0.024358227010816337}
+{"step": 57350, "action_loss_avg": 0.0010982111911289395}
+{"step": 57360, "dynamics_loss_avg": 0.041091113723814486}
+{"step": 57360, "action_loss_avg": 0.00223042878205888}
+{"step": 57370, "dynamics_loss_avg": 0.029033167054876685}
+{"step": 57370, "action_loss_avg": 0.0015724873810540885}
+{"step": 57380, "dynamics_loss_avg": 0.02716175904497504}
+{"step": 57380, "action_loss_avg": 0.001452233106829226}
+{"step": 57390, "dynamics_loss_avg": 0.02750602215528488}
+{"step": 57390, "action_loss_avg": 0.0011849501228425653}
+{"step": 57400, "loss": 0.031, "learning_rate": 4.1935038866783894e-05}
+{"step": 57400, "dynamics_loss_avg": 0.029422833956778048}
+{"step": 57400, "action_loss_avg": 0.001459961332147941}
+{"step": 57410, "dynamics_loss_avg": 0.0349779442884028}
+{"step": 57410, "action_loss_avg": 0.0014846761478111148}
+{"step": 57420, "dynamics_loss_avg": 0.0253379775211215}
+{"step": 57420, "action_loss_avg": 0.001703494309913367}
+{"step": 57430, "dynamics_loss_avg": 0.029582222737371922}
+{"step": 57430, "action_loss_avg": 0.0011793444806244223}
+{"step": 57440, "dynamics_loss_avg": 0.02753589954227209}
+{"step": 57440, "action_loss_avg": 0.001405105835874565}
+{"step": 57450, "loss": 0.0309, "learning_rate": 4.185345900177967e-05}
+{"step": 57450, "dynamics_loss_avg": 0.032025070115923884}
+{"step": 57450, "action_loss_avg": 0.001234815569478087}
+{"step": 57460, "dynamics_loss_avg": 0.024208647198975086}
+{"step": 57460, "action_loss_avg": 0.0012811150518245995}
+{"step": 57470, "dynamics_loss_avg": 0.026442390913143755}
+{"step": 57470, "action_loss_avg": 0.001656732111587189}
+{"step": 57480, "dynamics_loss_avg": 0.029536639992147683}
+{"step": 57480, "action_loss_avg": 0.0017841051158029586}
+{"step": 57490, "dynamics_loss_avg": 0.022474358882755043}
+{"step": 57490, "action_loss_avg": 0.0010080316249513998}
+{"step": 57500, "loss": 0.029, "learning_rate": 4.1771901409107476e-05}
+{"step": 57500, "dynamics_loss_avg": 0.03243404049426317}
+{"step": 57500, "action_loss_avg": 0.0018440243031363935}
+{"step": 57510, "dynamics_loss_avg": 0.020829432969912888}
+{"step": 57510, "action_loss_avg": 0.0010805416794028133}
+{"step": 57520, "dynamics_loss_avg": 0.02051603142172098}
+{"step": 57520, "action_loss_avg": 0.0010917622945271432}
+{"step": 57530, "dynamics_loss_avg": 0.03176115863025188}
+{"step": 57530, "action_loss_avg": 0.0017318846366833895}
+{"step": 57540, "dynamics_loss_avg": 0.03621810926124454}
+{"step": 57540, "action_loss_avg": 0.0019249470031354576}
+{"step": 57550, "loss": 0.0296, "learning_rate": 4.1690366311742626e-05}
+{"step": 57550, "dynamics_loss_avg": 0.02554965317249298}
+{"step": 57550, "action_loss_avg": 0.0010416190023534}
+{"step": 57560, "dynamics_loss_avg": 0.027116154599934817}
+{"step": 57560, "action_loss_avg": 0.0011609071691054851}
+{"step": 57570, "dynamics_loss_avg": 0.0314154495485127}
+{"step": 57570, "action_loss_avg": 0.0015825658629182726}
+{"step": 57580, "dynamics_loss_avg": 0.03067748243920505}
+{"step": 57580, "action_loss_avg": 0.001581533395801671}
+{"step": 57590, "dynamics_loss_avg": 0.031380790378898384}
+{"step": 57590, "action_loss_avg": 0.0017530141456518322}
+{"step": 57600, "loss": 0.0294, "learning_rate": 4.160885393259899e-05}
+{"step": 57600, "dynamics_loss_avg": 0.031449392158538106}
+{"step": 57600, "action_loss_avg": 0.0017905421671457588}
+{"step": 57610, "dynamics_loss_avg": 0.027306208573281764}
+{"step": 57610, "action_loss_avg": 0.0011471344419987871}
+{"step": 57620, "dynamics_loss_avg": 0.02136164139956236}
+{"step": 57620, "action_loss_avg": 0.0012048296513967216}
+{"step": 57630, "dynamics_loss_avg": 0.03072846159338951}
+{"step": 57630, "action_loss_avg": 0.001294073008466512}
+{"step": 57640, "dynamics_loss_avg": 0.02228744691237807}
+{"step": 57640, "action_loss_avg": 0.0013789922406431288}
+{"step": 57650, "loss": 0.0264, "learning_rate": 4.152736449452827e-05}
+{"step": 57650, "dynamics_loss_avg": 0.022213069372810423}
+{"step": 57650, "action_loss_avg": 0.0011432462415541522}
+{"step": 57660, "dynamics_loss_avg": 0.030797364935278893}
+{"step": 57660, "action_loss_avg": 0.001555829870630987}
+{"step": 57670, "dynamics_loss_avg": 0.028885360341519117}
+{"step": 57670, "action_loss_avg": 0.001373762107687071}
+{"step": 57680, "dynamics_loss_avg": 0.027306057466194033}
+{"step": 57680, "action_loss_avg": 0.001665938744554296}
+{"step": 57690, "dynamics_loss_avg": 0.023374314047396184}
+{"step": 57690, "action_loss_avg": 0.0011504686379339546}
+{"step": 57700, "loss": 0.0298, "learning_rate": 4.14458982203195e-05}
+{"step": 57700, "dynamics_loss_avg": 0.033055799547582865}
+{"step": 57700, "action_loss_avg": 0.0016795921197626739}
+{"step": 57710, "dynamics_loss_avg": 0.02132700951769948}
+{"step": 57710, "action_loss_avg": 0.0011063206766266376}
+{"step": 57720, "dynamics_loss_avg": 0.029432992171496152}
+{"step": 57720, "action_loss_avg": 0.0016337676672264934}
+{"step": 57730, "dynamics_loss_avg": 0.02271016836166382}
+{"step": 57730, "action_loss_avg": 0.0011034035211196168}
+{"step": 57740, "dynamics_loss_avg": 0.02562665343284607}
+{"step": 57740, "action_loss_avg": 0.0011865310370922089}
+{"step": 57750, "loss": 0.0288, "learning_rate": 4.136445533269837e-05}
+{"step": 57750, "dynamics_loss_avg": 0.019260451663285494}
+{"step": 57750, "action_loss_avg": 0.0009678471047664061}
+{"step": 57760, "dynamics_loss_avg": 0.026072110515087843}
+{"step": 57760, "action_loss_avg": 0.0013379034528043122}
+{"step": 57770, "dynamics_loss_avg": 0.032100990787148474}
+{"step": 57770, "action_loss_avg": 0.0015974134032148868}
+{"step": 57780, "dynamics_loss_avg": 0.02828067308291793}
+{"step": 57780, "action_loss_avg": 0.0018605788907734677}
+{"step": 57790, "dynamics_loss_avg": 0.03656426370143891}
+{"step": 57790, "action_loss_avg": 0.002020835340954363}
+{"step": 57800, "loss": 0.0313, "learning_rate": 4.128303605432661e-05}
+{"step": 57800, "dynamics_loss_avg": 0.045854154601693155}
+{"step": 57800, "action_loss_avg": 0.0020897613489069045}
+{"step": 57810, "dynamics_loss_avg": 0.023880977230146528}
+{"step": 57810, "action_loss_avg": 0.00117285764135886}
+{"step": 57820, "dynamics_loss_avg": 0.02876635091379285}
+{"step": 57820, "action_loss_avg": 0.0019238130538724364}
+{"step": 57830, "dynamics_loss_avg": 0.02949867593124509}
+{"step": 57830, "action_loss_avg": 0.00148529369616881}
+{"step": 57840, "dynamics_loss_avg": 0.021318131033331154}
+{"step": 57840, "action_loss_avg": 0.0016408125666202977}
+{"step": 57850, "loss": 0.0315, "learning_rate": 4.120164060780141e-05}
+{"step": 57850, "dynamics_loss_avg": 0.031342402659356595}
+{"step": 57850, "action_loss_avg": 0.0015137254551518709}
+{"step": 57860, "dynamics_loss_avg": 0.032406623708084226}
+{"step": 57860, "action_loss_avg": 0.0017504268995253368}
+{"step": 57870, "dynamics_loss_avg": 0.03403615206480026}
+{"step": 57870, "action_loss_avg": 0.0019953825045377015}
+{"step": 57880, "dynamics_loss_avg": 0.02870825482532382}
+{"step": 57880, "action_loss_avg": 0.0014532766828779132}
+{"step": 57890, "dynamics_loss_avg": 0.02669760687276721}
+{"step": 57890, "action_loss_avg": 0.0013353552261833102}
+{"step": 57900, "loss": 0.0296, "learning_rate": 4.112026921565483e-05}
+{"step": 57900, "dynamics_loss_avg": 0.03636642098426819}
+{"step": 57900, "action_loss_avg": 0.0018835532013326884}
+{"step": 57910, "dynamics_loss_avg": 0.03284393912181258}
+{"step": 57910, "action_loss_avg": 0.001533162803389132}
+{"step": 57920, "dynamics_loss_avg": 0.027468331158161163}
+{"step": 57920, "action_loss_avg": 0.0012867678276961669}
+{"step": 57930, "dynamics_loss_avg": 0.030039805080741645}
+{"step": 57930, "action_loss_avg": 0.0013967016973765567}
+{"step": 57940, "dynamics_loss_avg": 0.02180937137454748}
+{"step": 57940, "action_loss_avg": 0.0012082100482075475}
+{"step": 57950, "loss": 0.0306, "learning_rate": 4.103892210035315e-05}
+{"step": 57950, "dynamics_loss_avg": 0.02736666575074196}
+{"step": 57950, "action_loss_avg": 0.0013282827800139784}
+{"step": 57960, "dynamics_loss_avg": 0.02998244445770979}
+{"step": 57960, "action_loss_avg": 0.0013017581281019376}
+{"step": 57970, "dynamics_loss_avg": 0.035865125991404054}
+{"step": 57970, "action_loss_avg": 0.0018920196511317045}
+{"step": 57980, "dynamics_loss_avg": 0.026167074451223016}
+{"step": 57980, "action_loss_avg": 0.001395226301974617}
+{"step": 57990, "dynamics_loss_avg": 0.019210395868867636}
+{"step": 57990, "action_loss_avg": 0.0009656742971856147}
+{"step": 58000, "loss": 0.03, "learning_rate": 4.095759948429626e-05}
+{"step": 58000, "dynamics_loss_avg": 0.02782716155052185}
+{"step": 58000, "action_loss_avg": 0.0014872832165565343}
+{"step": 58010, "dynamics_loss_avg": 0.03273821948096156}
+{"step": 58010, "action_loss_avg": 0.001774429777287878}
+{"step": 58020, "dynamics_loss_avg": 0.01987907667644322}
+{"step": 58020, "action_loss_avg": 0.0011946856160648168}
+{"step": 58030, "dynamics_loss_avg": 0.024819064233452082}
+{"step": 58030, "action_loss_avg": 0.0014831549880909734}
+{"step": 58040, "dynamics_loss_avg": 0.023629739740863444}
+{"step": 58040, "action_loss_avg": 0.0011398755596019328}
+{"step": 58050, "loss": 0.0269, "learning_rate": 4.08763015898171e-05}
+{"step": 58050, "dynamics_loss_avg": 0.033035583421587945}
+{"step": 58050, "action_loss_avg": 0.0016322179057169706}
+{"step": 58060, "dynamics_loss_avg": 0.024983224272727967}
+{"step": 58060, "action_loss_avg": 0.0014413953351322562}
+{"step": 58070, "dynamics_loss_avg": 0.037668749783188106}
+{"step": 58070, "action_loss_avg": 0.002204154949868098}
+{"step": 58080, "dynamics_loss_avg": 0.028700839914381503}
+{"step": 58080, "action_loss_avg": 0.0014368289441335947}
+{"step": 58090, "dynamics_loss_avg": 0.036893943604081866}
+{"step": 58090, "action_loss_avg": 0.002183189301285893}
+{"step": 58100, "loss": 0.0313, "learning_rate": 4.0795028639181e-05}
+{"step": 58100, "dynamics_loss_avg": 0.03108413051813841}
+{"step": 58100, "action_loss_avg": 0.00199567083036527}
+{"step": 58110, "dynamics_loss_avg": 0.036447249352931976}
+{"step": 58110, "action_loss_avg": 0.0018035283603239805}
+{"step": 58120, "dynamics_loss_avg": 0.030421211710199715}
+{"step": 58120, "action_loss_avg": 0.001442897436209023}
+{"step": 58130, "dynamics_loss_avg": 0.027459146780893208}
+{"step": 58130, "action_loss_avg": 0.0024585130013292655}
+{"step": 58140, "dynamics_loss_avg": 0.028219601884484292}
+{"step": 58140, "action_loss_avg": 0.0015335546515416354}
+{"step": 58150, "loss": 0.0308, "learning_rate": 4.0713780854585115e-05}
+{"step": 58150, "dynamics_loss_avg": 0.0230328974314034}
+{"step": 58150, "action_loss_avg": 0.0010852950159460305}
+{"step": 58160, "dynamics_loss_avg": 0.027671122550964357}
+{"step": 58160, "action_loss_avg": 0.001476878224639222}
+{"step": 58170, "dynamics_loss_avg": 0.025836515706032515}
+{"step": 58170, "action_loss_avg": 0.0011066750215832145}
+{"step": 58180, "dynamics_loss_avg": 0.033195291133597496}
+{"step": 58180, "action_loss_avg": 0.0019496930239256472}
+{"step": 58190, "dynamics_loss_avg": 0.030528036365285515}
+{"step": 58190, "action_loss_avg": 0.0014990125840995462}
+{"step": 58200, "loss": 0.0323, "learning_rate": 4.063255845815779e-05}
+{"step": 58200, "dynamics_loss_avg": 0.022727188747376205}
+{"step": 58200, "action_loss_avg": 0.0011827852940768935}
+{"step": 58210, "dynamics_loss_avg": 0.033368803653866054}
+{"step": 58210, "action_loss_avg": 0.0015870265080593527}
+{"step": 58220, "dynamics_loss_avg": 0.029402477061375977}
+{"step": 58220, "action_loss_avg": 0.0016187298140721395}
+{"step": 58230, "dynamics_loss_avg": 0.021153062907978894}
+{"step": 58230, "action_loss_avg": 0.0012673809222178533}
+{"step": 58240, "dynamics_loss_avg": 0.030006314907222987}
+{"step": 58240, "action_loss_avg": 0.0014183048042468727}
+{"step": 58250, "loss": 0.0292, "learning_rate": 4.055136167195793e-05}
+{"step": 58250, "dynamics_loss_avg": 0.029126551933586597}
+{"step": 58250, "action_loss_avg": 0.0018467047426383941}
+{"step": 58260, "dynamics_loss_avg": 0.031194480089470743}
+{"step": 58260, "action_loss_avg": 0.0019976739407866263}
+{"step": 58270, "dynamics_loss_avg": 0.030565508548170327}
+{"step": 58270, "action_loss_avg": 0.0015523263224167748}
+{"step": 58280, "dynamics_loss_avg": 0.02740015331655741}
+{"step": 58280, "action_loss_avg": 0.0011914090486243368}
+{"step": 58290, "dynamics_loss_avg": 0.02794434535317123}
+{"step": 58290, "action_loss_avg": 0.0011724403477273882}
+{"step": 58300, "loss": 0.0294, "learning_rate": 4.0470190717974464e-05}
+{"step": 58300, "dynamics_loss_avg": 0.018439981248229743}
+{"step": 58300, "action_loss_avg": 0.0008365080429939553}
+{"step": 58310, "dynamics_loss_avg": 0.036601791204884646}
+{"step": 58310, "action_loss_avg": 0.0021726150996983053}
+{"step": 58320, "dynamics_loss_avg": 0.02646351382136345}
+{"step": 58320, "action_loss_avg": 0.001205961825326085}
+{"step": 58330, "dynamics_loss_avg": 0.030151065532118083}
+{"step": 58330, "action_loss_avg": 0.002096100558992475}
+{"step": 58340, "dynamics_loss_avg": 0.027082030847668647}
+{"step": 58340, "action_loss_avg": 0.0011950140935368836}
+{"step": 58350, "loss": 0.0292, "learning_rate": 4.038904581812569e-05}
+{"step": 58350, "dynamics_loss_avg": 0.03142833700403571}
+{"step": 58350, "action_loss_avg": 0.002253734559053555}
+{"step": 58360, "dynamics_loss_avg": 0.022327068913727998}
+{"step": 58360, "action_loss_avg": 0.001499613403575495}
+{"step": 58370, "dynamics_loss_avg": 0.03407451072707772}
+{"step": 58370, "action_loss_avg": 0.002266563125886023}
+{"step": 58380, "dynamics_loss_avg": 0.02837455328553915}
+{"step": 58380, "action_loss_avg": 0.0014880575996357947}
+{"step": 58390, "dynamics_loss_avg": 0.031678847037255764}
+{"step": 58390, "action_loss_avg": 0.0014444352098507806}
+{"step": 58400, "loss": 0.0308, "learning_rate": 4.0307927194258646e-05}
+{"step": 58400, "dynamics_loss_avg": 0.02994624003767967}
+{"step": 58400, "action_loss_avg": 0.0015856671874644236}
+{"step": 58410, "dynamics_loss_avg": 0.0231838820502162}
+{"step": 58410, "action_loss_avg": 0.0013690746069187298}
+{"step": 58420, "dynamics_loss_avg": 0.0290058396756649}
+{"step": 58420, "action_loss_avg": 0.001579735436826013}
+{"step": 58430, "dynamics_loss_avg": 0.027971109934151174}
+{"step": 58430, "action_loss_avg": 0.0016699462867109105}
+{"step": 58440, "dynamics_loss_avg": 0.02671595271676779}
+{"step": 58440, "action_loss_avg": 0.001173492887755856}
+{"step": 58450, "loss": 0.0306, "learning_rate": 4.022683506814858e-05}
+{"step": 58450, "dynamics_loss_avg": 0.03527457565069199}
+{"step": 58450, "action_loss_avg": 0.0016695493017323316}
+{"step": 58460, "dynamics_loss_avg": 0.034243205655366184}
+{"step": 58460, "action_loss_avg": 0.0017914052994456142}
+{"step": 58470, "dynamics_loss_avg": 0.029357208963483573}
+{"step": 58470, "action_loss_avg": 0.0015855367935728281}
+{"step": 58480, "dynamics_loss_avg": 0.02890866412781179}
+{"step": 58480, "action_loss_avg": 0.0014624068018747494}
+{"step": 58490, "dynamics_loss_avg": 0.030361990816891192}
+{"step": 58490, "action_loss_avg": 0.0011787518800701947}
+{"step": 58500, "loss": 0.0319, "learning_rate": 4.0145769661498233e-05}
+{"step": 58500, "dynamics_loss_avg": 0.030638564843684435}
+{"step": 58500, "action_loss_avg": 0.0014926033094525338}
+{"step": 58510, "dynamics_loss_avg": 0.026679079979658127}
+{"step": 58510, "action_loss_avg": 0.0010899916029302402}
+{"step": 58520, "dynamics_loss_avg": 0.03602217775769532}
+{"step": 58520, "action_loss_avg": 0.0014053429360501469}
+{"step": 58530, "dynamics_loss_avg": 0.028641273314133287}
+{"step": 58530, "action_loss_avg": 0.0013743757706834003}
+{"step": 58540, "dynamics_loss_avg": 0.03173557566478848}
+{"step": 58540, "action_loss_avg": 0.0018536304065492003}
+{"step": 58550, "loss": 0.0288, "learning_rate": 4.006473119593735e-05}
+{"step": 58550, "dynamics_loss_avg": 0.029236619267612694}
+{"step": 58550, "action_loss_avg": 0.001698459213366732}
+{"step": 58560, "dynamics_loss_avg": 0.026975513156503438}
+{"step": 58560, "action_loss_avg": 0.0013342199148610235}
+{"step": 58570, "dynamics_loss_avg": 0.02977519351989031}
+{"step": 58570, "action_loss_avg": 0.0013655964052304626}
+{"step": 58580, "dynamics_loss_avg": 0.02872869689017534}
+{"step": 58580, "action_loss_avg": 0.0014283693861216306}
+{"step": 58590, "dynamics_loss_avg": 0.02878845911473036}
+{"step": 58590, "action_loss_avg": 0.001551717153051868}
+{"step": 58600, "loss": 0.0315, "learning_rate": 3.9983719893022e-05}
+{"step": 58600, "dynamics_loss_avg": 0.02942010099068284}
+{"step": 58600, "action_loss_avg": 0.001588256750255823}
+{"step": 58610, "dynamics_loss_avg": 0.01951640220358968}
+{"step": 58610, "action_loss_avg": 0.0010218604758847505}
+{"step": 58620, "dynamics_loss_avg": 0.029897862952202557}
+{"step": 58620, "action_loss_avg": 0.001293844450265169}
+{"step": 58630, "dynamics_loss_avg": 0.02713395617902279}
+{"step": 58630, "action_loss_avg": 0.0012856249028118326}
+{"step": 58640, "dynamics_loss_avg": 0.031373757123947146}
+{"step": 58640, "action_loss_avg": 0.0016865896235685796}
+{"step": 58650, "loss": 0.0292, "learning_rate": 3.990273597423401e-05}
+{"step": 58650, "dynamics_loss_avg": 0.024214087054133415}
+{"step": 58650, "action_loss_avg": 0.0012370619748253374}
+{"step": 58660, "dynamics_loss_avg": 0.03375260345637798}
+{"step": 58660, "action_loss_avg": 0.0018494041985832154}
+{"step": 58670, "dynamics_loss_avg": 0.029882816318422555}
+{"step": 58670, "action_loss_avg": 0.001065392856253311}
+{"step": 58680, "dynamics_loss_avg": 0.028206829447299242}
+{"step": 58680, "action_loss_avg": 0.0018784721120027824}
+{"step": 58690, "dynamics_loss_avg": 0.02434028419665992}
+{"step": 58690, "action_loss_avg": 0.0010941108834231273}
+{"step": 58700, "loss": 0.0276, "learning_rate": 3.982177966098028e-05}
+{"step": 58700, "dynamics_loss_avg": 0.02392344535328448}
+{"step": 58700, "action_loss_avg": 0.0011240260675549508}
+{"step": 58710, "dynamics_loss_avg": 0.02729868795722723}
+{"step": 58710, "action_loss_avg": 0.0011631191475316883}
+{"step": 58720, "dynamics_loss_avg": 0.024680340848863124}
+{"step": 58720, "action_loss_avg": 0.001580948440823704}
+{"step": 58730, "dynamics_loss_avg": 0.03121950654312968}
+{"step": 58730, "action_loss_avg": 0.002027650224044919}
+{"step": 58740, "dynamics_loss_avg": 0.02617172207683325}
+{"step": 58740, "action_loss_avg": 0.0014251232816604898}
+{"step": 58750, "loss": 0.0294, "learning_rate": 3.974085117459231e-05}
+{"step": 58750, "dynamics_loss_avg": 0.034418389573693274}
+{"step": 58750, "action_loss_avg": 0.0015575966390315443}
+{"step": 58760, "dynamics_loss_avg": 0.03270610459148884}
+{"step": 58760, "action_loss_avg": 0.0017386040126439184}
+{"step": 58770, "dynamics_loss_avg": 0.026152271311730146}
+{"step": 58770, "action_loss_avg": 0.0012939029140397907}
+{"step": 58780, "dynamics_loss_avg": 0.031140131689608098}
+{"step": 58780, "action_loss_avg": 0.001490868051769212}
+{"step": 58790, "dynamics_loss_avg": 0.045726354513317344}
+{"step": 58790, "action_loss_avg": 0.0025712207658216356}
+{"step": 58800, "loss": 0.0328, "learning_rate": 3.9659950736325476e-05}
+{"step": 58800, "dynamics_loss_avg": 0.026752789970487356}
+{"step": 58800, "action_loss_avg": 0.0014102008717600256}
+{"step": 58810, "dynamics_loss_avg": 0.038126862980425356}
+{"step": 58810, "action_loss_avg": 0.0021549967117607594}
+{"step": 58820, "dynamics_loss_avg": 0.02393780816346407}
+{"step": 58820, "action_loss_avg": 0.0009789487041416578}
+{"step": 58830, "dynamics_loss_avg": 0.03126825913786888}
+{"step": 58830, "action_loss_avg": 0.0019026259367819875}
+{"step": 58840, "dynamics_loss_avg": 0.03220434403046966}
+{"step": 58840, "action_loss_avg": 0.002048718351579737}
+{"step": 58850, "loss": 0.0326, "learning_rate": 3.9579078567358506e-05}
+{"step": 58850, "dynamics_loss_avg": 0.03212885125540197}
+{"step": 58850, "action_loss_avg": 0.001272563316160813}
+{"step": 58860, "dynamics_loss_avg": 0.02779968734830618}
+{"step": 58860, "action_loss_avg": 0.0012613050639629364}
+{"step": 58870, "dynamics_loss_avg": 0.032637184485793114}
+{"step": 58870, "action_loss_avg": 0.0015444350836332887}
+{"step": 58880, "dynamics_loss_avg": 0.03219637656584382}
+{"step": 58880, "action_loss_avg": 0.0015096749411895871}
+{"step": 58890, "dynamics_loss_avg": 0.03199562667869031}
+{"step": 58890, "action_loss_avg": 0.0018419452768284827}
+{"step": 58900, "loss": 0.033, "learning_rate": 3.949823488879282e-05}
+{"step": 58900, "dynamics_loss_avg": 0.028801596164703368}
+{"step": 58900, "action_loss_avg": 0.0012137738900491967}
+{"step": 58910, "dynamics_loss_avg": 0.022441187920048834}
+{"step": 58910, "action_loss_avg": 0.0012697363417828456}
+{"step": 58920, "dynamics_loss_avg": 0.02624664083123207}
+{"step": 58920, "action_loss_avg": 0.0013427535130176693}
+{"step": 58930, "dynamics_loss_avg": 0.029007964441552757}
+{"step": 58930, "action_loss_avg": 0.001491968205664307}
+{"step": 58940, "dynamics_loss_avg": 0.028917865734547375}
+{"step": 58940, "action_loss_avg": 0.0015410552907269448}
+{"step": 58950, "loss": 0.0311, "learning_rate": 3.941741992165193e-05}
+{"step": 58950, "dynamics_loss_avg": 0.024620595248416068}
+{"step": 58950, "action_loss_avg": 0.0013735703047132119}
+{"step": 58960, "dynamics_loss_avg": 0.03910581646487117}
+{"step": 58960, "action_loss_avg": 0.002047095523448661}
+{"step": 58970, "dynamics_loss_avg": 0.028695988887920975}
+{"step": 58970, "action_loss_avg": 0.0015856935788178816}
+{"step": 58980, "dynamics_loss_avg": 0.032817249000072476}
+{"step": 58980, "action_loss_avg": 0.0017228063021320849}
+{"step": 58990, "dynamics_loss_avg": 0.029452286660671234}
+{"step": 58990, "action_loss_avg": 0.0015969069383572787}
+{"step": 59000, "loss": 0.0334, "learning_rate": 3.933663388688087e-05}
+{"step": 59000, "dynamics_loss_avg": 0.03176042973063886}
+{"step": 59000, "action_loss_avg": 0.0017333076160866768}
+{"step": 59010, "dynamics_loss_avg": 0.028866572119295598}
+{"step": 59010, "action_loss_avg": 0.0016442765947431326}
+{"step": 59020, "dynamics_loss_avg": 0.026277825701981783}
+{"step": 59020, "action_loss_avg": 0.0012784929131157696}
+{"step": 59030, "dynamics_loss_avg": 0.026612391881644725}
+{"step": 59030, "action_loss_avg": 0.0008747103769565001}
+{"step": 59040, "dynamics_loss_avg": 0.02102329023182392}
+{"step": 59040, "action_loss_avg": 0.001146983148646541}
+{"step": 59050, "loss": 0.0285, "learning_rate": 3.9255877005345586e-05}
+{"step": 59050, "dynamics_loss_avg": 0.03191229961812496}
+{"step": 59050, "action_loss_avg": 0.0018611411738675087}
+{"step": 59060, "dynamics_loss_avg": 0.026884548645466567}
+{"step": 59060, "action_loss_avg": 0.0017175651038996876}
+{"step": 59070, "dynamics_loss_avg": 0.03662663027644157}
+{"step": 59070, "action_loss_avg": 0.0016635946958558634}
+{"step": 59080, "dynamics_loss_avg": 0.020661445520818233}
+{"step": 59080, "action_loss_avg": 0.001047570409718901}
+{"step": 59090, "dynamics_loss_avg": 0.02892186911776662}
+{"step": 59090, "action_loss_avg": 0.0013258213526569306}
+{"step": 59100, "loss": 0.0311, "learning_rate": 3.9175149497832316e-05}
+{"step": 59100, "dynamics_loss_avg": 0.025818164460361004}
+{"step": 59100, "action_loss_avg": 0.0012337744468823076}
+{"step": 59110, "dynamics_loss_avg": 0.03483220720663667}
+{"step": 59110, "action_loss_avg": 0.0013943243655376136}
+{"step": 59120, "dynamics_loss_avg": 0.02865694803185761}
+{"step": 59120, "action_loss_avg": 0.001716152619337663}
+{"step": 59130, "dynamics_loss_avg": 0.025818637385964394}
+{"step": 59130, "action_loss_avg": 0.0014088120020460337}
+{"step": 59140, "dynamics_loss_avg": 0.030405625142157076}
+{"step": 59140, "action_loss_avg": 0.0014753875555470585}
+{"step": 59150, "loss": 0.0295, "learning_rate": 3.9094451585046974e-05}
+{"step": 59150, "dynamics_loss_avg": 0.02683807732537389}
+{"step": 59150, "action_loss_avg": 0.0016739459708333016}
+{"step": 59160, "dynamics_loss_avg": 0.020431416900828482}
+{"step": 59160, "action_loss_avg": 0.000994442292721942}
+{"step": 59170, "dynamics_loss_avg": 0.03014654815196991}
+{"step": 59170, "action_loss_avg": 0.0011969487415626646}
+{"step": 59180, "dynamics_loss_avg": 0.027053031604737043}
+{"step": 59180, "action_loss_avg": 0.0011704089061822741}
+{"step": 59190, "dynamics_loss_avg": 0.0303733313921839}
+{"step": 59190, "action_loss_avg": 0.0016189026471693068}
+{"step": 59200, "loss": 0.03, "learning_rate": 3.901378348761456e-05}
+{"step": 59200, "dynamics_loss_avg": 0.023225331399589776}
+{"step": 59200, "action_loss_avg": 0.001160809640714433}
+{"step": 59210, "dynamics_loss_avg": 0.023888711258769034}
+{"step": 59210, "action_loss_avg": 0.0010427875036839395}
+{"step": 59220, "dynamics_loss_avg": 0.03256704173982143}
+{"step": 59220, "action_loss_avg": 0.0016279400850180536}
+{"step": 59230, "dynamics_loss_avg": 0.021270181564614177}
+{"step": 59230, "action_loss_avg": 0.0009872027963865548}
+{"step": 59240, "dynamics_loss_avg": 0.02954133367165923}
+{"step": 59240, "action_loss_avg": 0.0015089224063558504}
+{"step": 59250, "loss": 0.0302, "learning_rate": 3.893314542607859e-05}
+{"step": 59250, "dynamics_loss_avg": 0.03193825744092464}
+{"step": 59250, "action_loss_avg": 0.0013675066293217242}
+{"step": 59260, "dynamics_loss_avg": 0.028642327059060335}
+{"step": 59260, "action_loss_avg": 0.0017568727402249352}
+{"step": 59270, "dynamics_loss_avg": 0.03137480271980166}
+{"step": 59270, "action_loss_avg": 0.0012980360887013375}
+{"step": 59280, "dynamics_loss_avg": 0.027160355355590582}
+{"step": 59280, "action_loss_avg": 0.0014814791007665916}
+{"step": 59290, "dynamics_loss_avg": 0.032795844180509445}
+{"step": 59290, "action_loss_avg": 0.0013257878890726715}
+{"step": 59300, "loss": 0.0276, "learning_rate": 3.885253762090043e-05}
+{"step": 59300, "dynamics_loss_avg": 0.025915717985481024}
+{"step": 59300, "action_loss_avg": 0.0012112048381823115}
+{"step": 59310, "dynamics_loss_avg": 0.02702406868338585}
+{"step": 59310, "action_loss_avg": 0.0012546839425340295}
+{"step": 59320, "dynamics_loss_avg": 0.03419086243957281}
+{"step": 59320, "action_loss_avg": 0.0011819991574157029}
+{"step": 59330, "dynamics_loss_avg": 0.01974664363078773}
+{"step": 59330, "action_loss_avg": 0.0010488444822840393}
+{"step": 59340, "dynamics_loss_avg": 0.027576271537691356}
+{"step": 59340, "action_loss_avg": 0.0010049277305370196}
+{"step": 59350, "loss": 0.0287, "learning_rate": 3.877196029245877e-05}
+{"step": 59350, "dynamics_loss_avg": 0.03237865269184113}
+{"step": 59350, "action_loss_avg": 0.001550409896299243}
+{"step": 59360, "dynamics_loss_avg": 0.0419975989498198}
+{"step": 59360, "action_loss_avg": 0.002453582745511085}
+{"step": 59370, "dynamics_loss_avg": 0.023897661361843348}
+{"step": 59370, "action_loss_avg": 0.0011372677399776876}
+{"step": 59380, "dynamics_loss_avg": 0.03317670114338398}
+{"step": 59380, "action_loss_avg": 0.0016151467862073332}
+{"step": 59390, "dynamics_loss_avg": 0.03240733146667481}
+{"step": 59390, "action_loss_avg": 0.0022123241738881915}
+{"step": 59400, "loss": 0.0341, "learning_rate": 3.8691413661048916e-05}
+{"step": 59400, "dynamics_loss_avg": 0.02630577180534601}
+{"step": 59400, "action_loss_avg": 0.0012596425105584786}
+{"step": 59410, "dynamics_loss_avg": 0.032320949342101814}
+{"step": 59410, "action_loss_avg": 0.0012742394057568163}
+{"step": 59420, "dynamics_loss_avg": 0.024428109312430023}
+{"step": 59420, "action_loss_avg": 0.0015448597958311438}
+{"step": 59430, "dynamics_loss_avg": 0.028784328140318394}
+{"step": 59430, "action_loss_avg": 0.0014591211336664855}
+{"step": 59440, "dynamics_loss_avg": 0.02390209324657917}
+{"step": 59440, "action_loss_avg": 0.001658178394427523}
+{"step": 59450, "loss": 0.0294, "learning_rate": 3.8610897946882294e-05}
+{"step": 59450, "dynamics_loss_avg": 0.032993084471672776}
+{"step": 59450, "action_loss_avg": 0.0016576861846260727}
+{"step": 59460, "dynamics_loss_avg": 0.03259320436045528}
+{"step": 59460, "action_loss_avg": 0.0018334604916162788}
+{"step": 59470, "dynamics_loss_avg": 0.022868684399873017}
+{"step": 59470, "action_loss_avg": 0.0011225579684833065}
+{"step": 59480, "dynamics_loss_avg": 0.02703186050057411}
+{"step": 59480, "action_loss_avg": 0.0011079315125243738}
+{"step": 59490, "dynamics_loss_avg": 0.026322862040251492}
+{"step": 59490, "action_loss_avg": 0.001509235944831744}
+{"step": 59500, "loss": 0.0304, "learning_rate": 3.8530413370085786e-05}
+{"step": 59500, "dynamics_loss_avg": 0.03361483234912157}
+{"step": 59500, "action_loss_avg": 0.0017922316561453044}
+{"step": 59510, "dynamics_loss_avg": 0.02489146767184138}
+{"step": 59510, "action_loss_avg": 0.001469815691234544}
+{"step": 59520, "dynamics_loss_avg": 0.026824506651610135}
+{"step": 59520, "action_loss_avg": 0.0011262405663728715}
+{"step": 59530, "dynamics_loss_avg": 0.02959888046607375}
+{"step": 59530, "action_loss_avg": 0.0013844777771737427}
+{"step": 59540, "dynamics_loss_avg": 0.026377643970772625}
+{"step": 59540, "action_loss_avg": 0.0015674539303290659}
+{"step": 59550, "loss": 0.0293, "learning_rate": 3.844996015070117e-05}
+{"step": 59550, "dynamics_loss_avg": 0.031064214184880257}
+{"step": 59550, "action_loss_avg": 0.0019491752958856524}
+{"step": 59560, "dynamics_loss_avg": 0.02675979435443878}
+{"step": 59560, "action_loss_avg": 0.0013736479973886161}
+{"step": 59570, "dynamics_loss_avg": 0.025807587057352067}
+{"step": 59570, "action_loss_avg": 0.0008476057133520954}
+{"step": 59580, "dynamics_loss_avg": 0.021986901480704545}
+{"step": 59580, "action_loss_avg": 0.0008167233201675117}
+{"step": 59590, "dynamics_loss_avg": 0.030282725021243094}
+{"step": 59590, "action_loss_avg": 0.0012568959238706157}
+{"step": 59600, "loss": 0.028, "learning_rate": 3.836953850868447e-05}
+{"step": 59600, "dynamics_loss_avg": 0.029869330860674382}
+{"step": 59600, "action_loss_avg": 0.001671135885408148}
+{"step": 59610, "dynamics_loss_avg": 0.03582679582759738}
+{"step": 59610, "action_loss_avg": 0.0019975335046183316}
+{"step": 59620, "dynamics_loss_avg": 0.027910497784614564}
+{"step": 59620, "action_loss_avg": 0.001768981572240591}
+{"step": 59630, "dynamics_loss_avg": 0.024656153935939073}
+{"step": 59630, "action_loss_avg": 0.0010826676909346134}
+{"step": 59640, "dynamics_loss_avg": 0.02513623656705022}
+{"step": 59640, "action_loss_avg": 0.0011330172623274849}
+{"step": 59650, "loss": 0.0295, "learning_rate": 3.828914866390537e-05}
+{"step": 59650, "dynamics_loss_avg": 0.029638370033353567}
+{"step": 59650, "action_loss_avg": 0.0016460963408462704}
+{"step": 59660, "dynamics_loss_avg": 0.03369614239782095}
+{"step": 59660, "action_loss_avg": 0.0016441123909316957}
+{"step": 59670, "dynamics_loss_avg": 0.0300319068133831}
+{"step": 59670, "action_loss_avg": 0.0018467260524630547}
+{"step": 59680, "dynamics_loss_avg": 0.030987650342285632}
+{"step": 59680, "action_loss_avg": 0.0013748981000389904}
+{"step": 59690, "dynamics_loss_avg": 0.03146903538145125}
+{"step": 59690, "action_loss_avg": 0.0017572785494849087}
+{"step": 59700, "loss": 0.031, "learning_rate": 3.820879083614664e-05}
+{"step": 59700, "dynamics_loss_avg": 0.03223574515432119}
+{"step": 59700, "action_loss_avg": 0.0017683862301055343}
+{"step": 59710, "dynamics_loss_avg": 0.029954207316040992}
+{"step": 59710, "action_loss_avg": 0.001459165853157174}
+{"step": 59720, "dynamics_loss_avg": 0.02416858901269734}
+{"step": 59720, "action_loss_avg": 0.001246796900522895}
+{"step": 59730, "dynamics_loss_avg": 0.022551734000444412}
+{"step": 59730, "action_loss_avg": 0.0011971505358815194}
+{"step": 59740, "dynamics_loss_avg": 0.031157740950584413}
+{"step": 59740, "action_loss_avg": 0.002105958806350827}
+{"step": 59750, "loss": 0.0318, "learning_rate": 3.812846524510352e-05}
+{"step": 59750, "dynamics_loss_avg": 0.03934469427913427}
+{"step": 59750, "action_loss_avg": 0.0020684316172264517}
+{"step": 59760, "dynamics_loss_avg": 0.030751105584204196}
+{"step": 59760, "action_loss_avg": 0.0015764732495881617}
+{"step": 59770, "dynamics_loss_avg": 0.04352489896118641}
+{"step": 59770, "action_loss_avg": 0.0020267613115720453}
+{"step": 59780, "dynamics_loss_avg": 0.03554880674928427}
+{"step": 59780, "action_loss_avg": 0.002319549844833091}
+{"step": 59790, "dynamics_loss_avg": 0.02414758806116879}
+{"step": 59790, "action_loss_avg": 0.0011444871954154224}
+{"step": 59800, "loss": 0.0316, "learning_rate": 3.8048172110383114e-05}
+{"step": 59800, "dynamics_loss_avg": 0.029732694383710623}
+{"step": 59800, "action_loss_avg": 0.001592554732633289}
+{"step": 59810, "dynamics_loss_avg": 0.02252940870821476}
+{"step": 59810, "action_loss_avg": 0.0011039362187148071}
+{"step": 59820, "dynamics_loss_avg": 0.02989686341024935}
+{"step": 59820, "action_loss_avg": 0.002150905615417287}
+{"step": 59830, "dynamics_loss_avg": 0.025525368098169566}
+{"step": 59830, "action_loss_avg": 0.001052454870659858}
+{"step": 59840, "dynamics_loss_avg": 0.035274249501526356}
+{"step": 59840, "action_loss_avg": 0.001597959437640384}
+{"step": 59850, "loss": 0.03, "learning_rate": 3.796791165150378e-05}
+{"step": 59850, "dynamics_loss_avg": 0.027349590603262187}
+{"step": 59850, "action_loss_avg": 0.001870790496468544}
+{"step": 59860, "dynamics_loss_avg": 0.03262636670842767}
+{"step": 59860, "action_loss_avg": 0.0018294258043169975}
+{"step": 59870, "dynamics_loss_avg": 0.028854058310389518}
+{"step": 59870, "action_loss_avg": 0.0009612773428671062}
+{"step": 59880, "dynamics_loss_avg": 0.034105160273611546}
+{"step": 59880, "action_loss_avg": 0.001803658762946725}
+{"step": 59890, "dynamics_loss_avg": 0.031459057331085206}
+{"step": 59890, "action_loss_avg": 0.001458790642209351}
+{"step": 59900, "loss": 0.0285, "learning_rate": 3.7887684087894545e-05}
+{"step": 59900, "dynamics_loss_avg": 0.03191466042771936}
+{"step": 59900, "action_loss_avg": 0.0015220966335618869}
+{"step": 59910, "dynamics_loss_avg": 0.02758650705218315}
+{"step": 59910, "action_loss_avg": 0.0013783351925667376}
+{"step": 59920, "dynamics_loss_avg": 0.031100104935467242}
+{"step": 59920, "action_loss_avg": 0.0022071743558626624}
+{"step": 59930, "dynamics_loss_avg": 0.03506028102710843}
+{"step": 59930, "action_loss_avg": 0.0017667074484052137}
+{"step": 59940, "dynamics_loss_avg": 0.023289736034348606}
+{"step": 59940, "action_loss_avg": 0.0009123540425207466}
+{"step": 59950, "loss": 0.0326, "learning_rate": 3.78074896388945e-05}
+{"step": 59950, "dynamics_loss_avg": 0.03959776684641838}
+{"step": 59950, "action_loss_avg": 0.002313201536890119}
+{"step": 59960, "dynamics_loss_avg": 0.031486036442220214}
+{"step": 59960, "action_loss_avg": 0.001270414120517671}
+{"step": 59970, "dynamics_loss_avg": 0.031248852796852588}
+{"step": 59970, "action_loss_avg": 0.001521096413489431}
+{"step": 59980, "dynamics_loss_avg": 0.022939162235707043}
+{"step": 59980, "action_loss_avg": 0.0015056524745887146}
+{"step": 59990, "dynamics_loss_avg": 0.02961325631476939}
+{"step": 59990, "action_loss_avg": 0.0013661115284776316}
+{"step": 60000, "loss": 0.0283, "learning_rate": 3.7727328523752215e-05}
+{"step": 60000, "dynamics_loss_avg": 0.030003949999809265}
+{"step": 60000, "action_loss_avg": 0.001303450867999345}
+{"step": 60010, "dynamics_loss_avg": 0.028011737670749427}
+{"step": 60010, "action_loss_avg": 0.0012283410876989364}
+{"step": 60020, "dynamics_loss_avg": 0.029378798604011536}
+{"step": 60020, "action_loss_avg": 0.001830113964388147}
+{"step": 60030, "dynamics_loss_avg": 0.028394840145483612}
+{"step": 60030, "action_loss_avg": 0.0010218543524388225}
+{"step": 60040, "dynamics_loss_avg": 0.032102812081575394}
+{"step": 60040, "action_loss_avg": 0.0011694904475007205}
+{"step": 60050, "loss": 0.0301, "learning_rate": 3.764720096162512e-05}
+{"step": 60050, "dynamics_loss_avg": 0.030502041429281236}
+{"step": 60050, "action_loss_avg": 0.0013897039694711565}
+{"step": 60060, "dynamics_loss_avg": 0.03634455120190978}
+{"step": 60060, "action_loss_avg": 0.0015758776280563325}
+{"step": 60070, "dynamics_loss_avg": 0.030394936725497246}
+{"step": 60070, "action_loss_avg": 0.0019349479407537729}
+{"step": 60080, "dynamics_loss_avg": 0.022974203899502756}
+{"step": 60080, "action_loss_avg": 0.0009336119954241439}
+{"step": 60090, "dynamics_loss_avg": 0.030290865898132326}
+{"step": 60090, "action_loss_avg": 0.0011451664671767504}
+{"step": 60100, "loss": 0.0321, "learning_rate": 3.7567107171578904e-05}
+{"step": 60100, "dynamics_loss_avg": 0.033445121441036466}
+{"step": 60100, "action_loss_avg": 0.0019848711352096872}
+{"step": 60110, "dynamics_loss_avg": 0.03096318235620856}
+{"step": 60110, "action_loss_avg": 0.001316611241782084}
+{"step": 60120, "dynamics_loss_avg": 0.029243265464901923}
+{"step": 60120, "action_loss_avg": 0.0014054499886697158}
+{"step": 60130, "dynamics_loss_avg": 0.022779263136908413}
+{"step": 60130, "action_loss_avg": 0.0011463973962236196}
+{"step": 60140, "dynamics_loss_avg": 0.029611556930467485}
+{"step": 60140, "action_loss_avg": 0.0018310396349988877}
+{"step": 60150, "loss": 0.0291, "learning_rate": 3.748704737258693e-05}
+{"step": 60150, "dynamics_loss_avg": 0.02497616708278656}
+{"step": 60150, "action_loss_avg": 0.0011907808016985654}
+{"step": 60160, "dynamics_loss_avg": 0.027287098113447428}
+{"step": 60160, "action_loss_avg": 0.001200820624944754}
+{"step": 60170, "dynamics_loss_avg": 0.02875997740775347}
+{"step": 60170, "action_loss_avg": 0.0010515259928070009}
+{"step": 60180, "dynamics_loss_avg": 0.02965849582105875}
+{"step": 60180, "action_loss_avg": 0.001660342625109479}
+{"step": 60190, "dynamics_loss_avg": 0.022605467541143297}
+{"step": 60190, "action_loss_avg": 0.0009581876482116058}
+{"step": 60200, "loss": 0.0282, "learning_rate": 3.740702178352963e-05}
+{"step": 60200, "dynamics_loss_avg": 0.020641399174928667}
+{"step": 60200, "action_loss_avg": 0.001017728092847392}
+{"step": 60210, "dynamics_loss_avg": 0.03570234188809991}
+{"step": 60210, "action_loss_avg": 0.0016057353757787495}
+{"step": 60220, "dynamics_loss_avg": 0.033115200232714415}
+{"step": 60220, "action_loss_avg": 0.0016904203075682744}
+{"step": 60230, "dynamics_loss_avg": 0.029480485990643502}
+{"step": 60230, "action_loss_avg": 0.0014792819158174098}
+{"step": 60240, "dynamics_loss_avg": 0.02405815655365586}
+{"step": 60240, "action_loss_avg": 0.0012115975958295166}
+{"step": 60250, "loss": 0.0311, "learning_rate": 3.732703062319391e-05}
+{"step": 60250, "dynamics_loss_avg": 0.024248743802309035}
+{"step": 60250, "action_loss_avg": 0.0012802113022189587}
+{"step": 60260, "dynamics_loss_avg": 0.02369638131931424}
+{"step": 60260, "action_loss_avg": 0.0017078311706427486}
+{"step": 60270, "dynamics_loss_avg": 0.028017007745802402}
+{"step": 60270, "action_loss_avg": 0.0014252321037929506}
+{"step": 60280, "dynamics_loss_avg": 0.03394027724862099}
+{"step": 60280, "action_loss_avg": 0.001754290162352845}
+{"step": 60290, "dynamics_loss_avg": 0.026292803045362235}
+{"step": 60290, "action_loss_avg": 0.0012497992196585984}
+{"step": 60300, "loss": 0.0299, "learning_rate": 3.724707411027256e-05}
+{"step": 60300, "dynamics_loss_avg": 0.021918188035488128}
+{"step": 60300, "action_loss_avg": 0.0009148036944679916}
+{"step": 60310, "dynamics_loss_avg": 0.02860457105562091}
+{"step": 60310, "action_loss_avg": 0.0016920162888709456}
+{"step": 60320, "dynamics_loss_avg": 0.03241093517281115}
+{"step": 60320, "action_loss_avg": 0.0017409324122127146}
+{"step": 60330, "dynamics_loss_avg": 0.026879855990409852}
+{"step": 60330, "action_loss_avg": 0.0014069469296373426}
+{"step": 60340, "dynamics_loss_avg": 0.03891075849533081}
+{"step": 60340, "action_loss_avg": 0.001472454803297296}
+{"step": 60350, "loss": 0.0314, "learning_rate": 3.716715246336362e-05}
+{"step": 60350, "dynamics_loss_avg": 0.02750791786238551}
+{"step": 60350, "action_loss_avg": 0.0016781911195721476}
+{"step": 60360, "dynamics_loss_avg": 0.024032850610092284}
+{"step": 60360, "action_loss_avg": 0.0014891640268615447}
+{"step": 60370, "dynamics_loss_avg": 0.029492884688079358}
+{"step": 60370, "action_loss_avg": 0.0012921735091367737}
+{"step": 60380, "dynamics_loss_avg": 0.023552199406549335}
+{"step": 60380, "action_loss_avg": 0.0012321045818680433}
+{"step": 60390, "dynamics_loss_avg": 0.030161275155842306}
+{"step": 60390, "action_loss_avg": 0.0017587065638508647}
+{"step": 60400, "loss": 0.0268, "learning_rate": 3.708726590096982e-05}
+{"step": 60400, "dynamics_loss_avg": 0.021747964713722468}
+{"step": 60400, "action_loss_avg": 0.001256136375013739}
+{"step": 60410, "dynamics_loss_avg": 0.030431505851447584}
+{"step": 60410, "action_loss_avg": 0.0018512232636567205}
+{"step": 60420, "dynamics_loss_avg": 0.029561886843293906}
+{"step": 60420, "action_loss_avg": 0.001484107197029516}
+{"step": 60430, "dynamics_loss_avg": 0.030387852317653598}
+{"step": 60430, "action_loss_avg": 0.0018779494472255464}
+{"step": 60440, "dynamics_loss_avg": 0.033875192143023015}
+{"step": 60440, "action_loss_avg": 0.0019334693031851202}
+{"step": 60450, "loss": 0.0303, "learning_rate": 3.7007414641497976e-05}
+{"step": 60450, "dynamics_loss_avg": 0.027692241175100208}
+{"step": 60450, "action_loss_avg": 0.0012180482037365437}
+{"step": 60460, "dynamics_loss_avg": 0.027291400963440536}
+{"step": 60460, "action_loss_avg": 0.0012123902357416227}
+{"step": 60470, "dynamics_loss_avg": 0.02603590050712228}
+{"step": 60470, "action_loss_avg": 0.0013201271678553895}
+{"step": 60480, "dynamics_loss_avg": 0.03412591726519167}
+{"step": 60480, "action_loss_avg": 0.0018289017389179207}
+{"step": 60490, "dynamics_loss_avg": 0.027137390710413455}
+{"step": 60490, "action_loss_avg": 0.0013040021061897279}
+{"step": 60500, "loss": 0.0294, "learning_rate": 3.6927598903258374e-05}
+{"step": 60500, "dynamics_loss_avg": 0.021603235555812717}
+{"step": 60500, "action_loss_avg": 0.0014044444949831813}
+{"step": 60510, "dynamics_loss_avg": 0.030682008340954782}
+{"step": 60510, "action_loss_avg": 0.0013048374559730292}
+{"step": 60520, "dynamics_loss_avg": 0.024030884820967914}
+{"step": 60520, "action_loss_avg": 0.0009464804723393172}
+{"step": 60530, "dynamics_loss_avg": 0.027380264084786176}
+{"step": 60530, "action_loss_avg": 0.0011956576548982412}
+{"step": 60540, "dynamics_loss_avg": 0.026381260389462112}
+{"step": 60540, "action_loss_avg": 0.0012758795986883343}
+{"step": 60550, "loss": 0.0285, "learning_rate": 3.6847818904464226e-05}
+{"step": 60550, "dynamics_loss_avg": 0.03070496041327715}
+{"step": 60550, "action_loss_avg": 0.0015010622155386955}
+{"step": 60560, "dynamics_loss_avg": 0.026748753990978}
+{"step": 60560, "action_loss_avg": 0.0013516033359337598}
+{"step": 60570, "dynamics_loss_avg": 0.03393673412501812}
+{"step": 60570, "action_loss_avg": 0.001467351842438802}
+{"step": 60580, "dynamics_loss_avg": 0.03370065651834011}
+{"step": 60580, "action_loss_avg": 0.0022336372639983892}
+{"step": 60590, "dynamics_loss_avg": 0.03438778854906559}
+{"step": 60590, "action_loss_avg": 0.0016649631899781526}
+{"step": 60600, "loss": 0.0333, "learning_rate": 3.676807486323096e-05}
+{"step": 60600, "dynamics_loss_avg": 0.0279582429677248}
+{"step": 60600, "action_loss_avg": 0.0016318944399245083}
+{"step": 60610, "dynamics_loss_avg": 0.026156841404736043}
+{"step": 60610, "action_loss_avg": 0.0012798496696632355}
+{"step": 60620, "dynamics_loss_avg": 0.025207284186035395}
+{"step": 60620, "action_loss_avg": 0.0015881415136391297}
+{"step": 60630, "dynamics_loss_avg": 0.02966473074629903}
+{"step": 60630, "action_loss_avg": 0.0016272004577331245}
+{"step": 60640, "dynamics_loss_avg": 0.028379956167191266}
+{"step": 60640, "action_loss_avg": 0.0017315229924861342}
+{"step": 60650, "loss": 0.0301, "learning_rate": 3.668836699757576e-05}
+{"step": 60650, "dynamics_loss_avg": 0.02839616108685732}
+{"step": 60650, "action_loss_avg": 0.0012635840219445526}
+{"step": 60660, "dynamics_loss_avg": 0.041444160230457786}
+{"step": 60660, "action_loss_avg": 0.0019050395640078932}
+{"step": 60670, "dynamics_loss_avg": 0.025779948383569718}
+{"step": 60670, "action_loss_avg": 0.0015990369953215121}
+{"step": 60680, "dynamics_loss_avg": 0.026343861501663922}
+{"step": 60680, "action_loss_avg": 0.0011150484468089416}
+{"step": 60690, "dynamics_loss_avg": 0.02599030677229166}
+{"step": 60690, "action_loss_avg": 0.001425191288581118}
+{"step": 60700, "loss": 0.0302, "learning_rate": 3.660869552541689e-05}
+{"step": 60700, "dynamics_loss_avg": 0.03410049406811595}
+{"step": 60700, "action_loss_avg": 0.0016976846061879769}
+{"step": 60710, "dynamics_loss_avg": 0.027049580216407777}
+{"step": 60710, "action_loss_avg": 0.0011693278065649793}
+{"step": 60720, "dynamics_loss_avg": 0.02553430078551173}
+{"step": 60720, "action_loss_avg": 0.0012019549496471882}
+{"step": 60730, "dynamics_loss_avg": 0.022437606239691377}
+{"step": 60730, "action_loss_avg": 0.0013736386055825279}
+{"step": 60740, "dynamics_loss_avg": 0.032997652608901265}
+{"step": 60740, "action_loss_avg": 0.0014847170969005674}
+{"step": 60750, "loss": 0.0289, "learning_rate": 3.6529060664573126e-05}
+{"step": 60750, "dynamics_loss_avg": 0.03461189102381468}
+{"step": 60750, "action_loss_avg": 0.0019109874730929733}
+{"step": 60760, "dynamics_loss_avg": 0.023988522123545408}
+{"step": 60760, "action_loss_avg": 0.0011554909346159548}
+{"step": 60770, "dynamics_loss_avg": 0.037454563193023205}
+{"step": 60770, "action_loss_avg": 0.0015272495103999973}
+{"step": 60780, "dynamics_loss_avg": 0.028507710713893176}
+{"step": 60780, "action_loss_avg": 0.0014868762576952578}
+{"step": 60790, "dynamics_loss_avg": 0.02048548371531069}
+{"step": 60790, "action_loss_avg": 0.0013437101151794195}
+{"step": 60800, "loss": 0.031, "learning_rate": 3.6449462632763075e-05}
+{"step": 60800, "dynamics_loss_avg": 0.029967621341347693}
+{"step": 60800, "action_loss_avg": 0.0015291067596990616}
+{"step": 60810, "dynamics_loss_avg": 0.032144006062299016}
+{"step": 60810, "action_loss_avg": 0.0017679619762930089}
+{"step": 60820, "dynamics_loss_avg": 0.026548737846314906}
+{"step": 60820, "action_loss_avg": 0.0014013163541676476}
+{"step": 60830, "dynamics_loss_avg": 0.033907697349786756}
+{"step": 60830, "action_loss_avg": 0.001817190699512139}
+{"step": 60840, "dynamics_loss_avg": 0.03012383314780891}
+{"step": 60840, "action_loss_avg": 0.0011717183573637159}
+{"step": 60850, "loss": 0.0324, "learning_rate": 3.636990164760479e-05}
+{"step": 60850, "dynamics_loss_avg": 0.03314559683203697}
+{"step": 60850, "action_loss_avg": 0.001453987613786012}
+{"step": 60860, "dynamics_loss_avg": 0.030736412294209002}
+{"step": 60860, "action_loss_avg": 0.0011254789205850102}
+{"step": 60870, "dynamics_loss_avg": 0.024843656923621893}
+{"step": 60870, "action_loss_avg": 0.0012194324692245573}
+{"step": 60880, "dynamics_loss_avg": 0.024422759562730788}
+{"step": 60880, "action_loss_avg": 0.0012864216114394367}
+{"step": 60890, "dynamics_loss_avg": 0.035884036449715495}
+{"step": 60890, "action_loss_avg": 0.0016761637874878944}
+{"step": 60900, "loss": 0.0301, "learning_rate": 3.629037792661492e-05}
+{"step": 60900, "dynamics_loss_avg": 0.039822681434452535}
+{"step": 60900, "action_loss_avg": 0.0021938057616353035}
+{"step": 60910, "dynamics_loss_avg": 0.024039081949740648}
+{"step": 60910, "action_loss_avg": 0.0011194410268217324}
+{"step": 60920, "dynamics_loss_avg": 0.027851508930325508}
+{"step": 60920, "action_loss_avg": 0.0009369703911943361}
+{"step": 60930, "dynamics_loss_avg": 0.029182609263807537}
+{"step": 60930, "action_loss_avg": 0.0009092815074836835}
+{"step": 60940, "dynamics_loss_avg": 0.026495202165096998}
+{"step": 60940, "action_loss_avg": 0.0015737560956040398}
+{"step": 60950, "loss": 0.0295, "learning_rate": 3.6210891687208304e-05}
+{"step": 60950, "dynamics_loss_avg": 0.025425040908157826}
+{"step": 60950, "action_loss_avg": 0.0013539734194637277}
+{"step": 60960, "dynamics_loss_avg": 0.02612589276395738}
+{"step": 60960, "action_loss_avg": 0.0013105446589179337}
+{"step": 60970, "dynamics_loss_avg": 0.027239332720637322}
+{"step": 60970, "action_loss_avg": 0.0013771034369710832}
+{"step": 60980, "dynamics_loss_avg": 0.0274798640049994}
+{"step": 60980, "action_loss_avg": 0.0012987172696739436}
+{"step": 60990, "dynamics_loss_avg": 0.02308588596060872}
+{"step": 60990, "action_loss_avg": 0.0009432044782442972}
+{"step": 61000, "loss": 0.0314, "learning_rate": 3.6131443146697306e-05}
+{"step": 61000, "dynamics_loss_avg": 0.03363788994029164}
+{"step": 61000, "action_loss_avg": 0.001419007347431034}
+{"step": 61010, "dynamics_loss_avg": 0.0316143412142992}
+{"step": 61010, "action_loss_avg": 0.001439725828822702}
+{"step": 61020, "dynamics_loss_avg": 0.033635297790169716}
+{"step": 61020, "action_loss_avg": 0.0014966062852181494}
+{"step": 61030, "dynamics_loss_avg": 0.03574352711439133}
+{"step": 61030, "action_loss_avg": 0.0019227733253501355}
+{"step": 61040, "dynamics_loss_avg": 0.02828209907747805}
+{"step": 61040, "action_loss_avg": 0.0014226731611415744}
+{"step": 61050, "loss": 0.0323, "learning_rate": 3.6052032522291134e-05}
+{"step": 61050, "dynamics_loss_avg": 0.028894939832389353}
+{"step": 61050, "action_loss_avg": 0.0015924458217341452}
+{"step": 61060, "dynamics_loss_avg": 0.029849631153047083}
+{"step": 61060, "action_loss_avg": 0.0016124132205732166}
+{"step": 61070, "dynamics_loss_avg": 0.033000426227226855}
+{"step": 61070, "action_loss_avg": 0.001323976315325126}
+{"step": 61080, "dynamics_loss_avg": 0.025425205938518047}
+{"step": 61080, "action_loss_avg": 0.0012093401688616722}
+{"step": 61090, "dynamics_loss_avg": 0.033885812107473615}
+{"step": 61090, "action_loss_avg": 0.0017299739876762033}
+{"step": 61100, "loss": 0.0315, "learning_rate": 3.597266003109546e-05}
+{"step": 61100, "dynamics_loss_avg": 0.029129207832738757}
+{"step": 61100, "action_loss_avg": 0.001757049176376313}
+{"step": 61110, "dynamics_loss_avg": 0.028908004751428962}
+{"step": 61110, "action_loss_avg": 0.0019043521708226763}
+{"step": 61120, "dynamics_loss_avg": 0.021335775777697564}
+{"step": 61120, "action_loss_avg": 0.0009745001385454089}
+{"step": 61130, "dynamics_loss_avg": 0.03108975142240524}
+{"step": 61130, "action_loss_avg": 0.0014303196017863228}
+{"step": 61140, "dynamics_loss_avg": 0.027325640432536602}
+{"step": 61140, "action_loss_avg": 0.0015683838981203734}
+{"step": 61150, "loss": 0.0279, "learning_rate": 3.5893325890111626e-05}
+{"step": 61150, "dynamics_loss_avg": 0.025913850963115694}
+{"step": 61150, "action_loss_avg": 0.001713823335012421}
+{"step": 61160, "dynamics_loss_avg": 0.025611029658466577}
+{"step": 61160, "action_loss_avg": 0.0019830256496788934}
+{"step": 61170, "dynamics_loss_avg": 0.028776226798072457}
+{"step": 61170, "action_loss_avg": 0.001442982576554641}
+{"step": 61180, "dynamics_loss_avg": 0.03844148721545935}
+{"step": 61180, "action_loss_avg": 0.0014679458399768919}
+{"step": 61190, "dynamics_loss_avg": 0.0470676863566041}
+{"step": 61190, "action_loss_avg": 0.0024992609047330915}
+{"step": 61200, "loss": 0.0318, "learning_rate": 3.581403031623616e-05}
+{"step": 61200, "dynamics_loss_avg": 0.03214750848710537}
+{"step": 61200, "action_loss_avg": 0.0017206699994858354}
+{"step": 61210, "dynamics_loss_avg": 0.03127110097557306}
+{"step": 61210, "action_loss_avg": 0.0013450788886984811}
+{"step": 61220, "dynamics_loss_avg": 0.02270429488271475}
+{"step": 61220, "action_loss_avg": 0.0014683873552712612}
+{"step": 61230, "dynamics_loss_avg": 0.03388700867071748}
+{"step": 61230, "action_loss_avg": 0.0015516264946199953}
+{"step": 61240, "dynamics_loss_avg": 0.025984912179410458}
+{"step": 61240, "action_loss_avg": 0.001387572509702295}
+{"step": 61250, "loss": 0.0294, "learning_rate": 3.5734773526260115e-05}
+{"step": 61250, "dynamics_loss_avg": 0.02890573926270008}
+{"step": 61250, "action_loss_avg": 0.0016792221314972267}
+{"step": 61260, "dynamics_loss_avg": 0.03469339511357248}
+{"step": 61260, "action_loss_avg": 0.0016495371746714227}
+{"step": 61270, "dynamics_loss_avg": 0.041064010187983516}
+{"step": 61270, "action_loss_avg": 0.0022690327430609615}
+{"step": 61280, "dynamics_loss_avg": 0.028260092623531817}
+{"step": 61280, "action_loss_avg": 0.0015050889982376249}
+{"step": 61290, "dynamics_loss_avg": 0.024195614363998176}
+{"step": 61290, "action_loss_avg": 0.0010029957949882374}
+{"step": 61300, "loss": 0.0319, "learning_rate": 3.565555573686853e-05}
+{"step": 61300, "dynamics_loss_avg": 0.029349540919065477}
+{"step": 61300, "action_loss_avg": 0.0015904951200354845}
+{"step": 61310, "dynamics_loss_avg": 0.030540645215660335}
+{"step": 61310, "action_loss_avg": 0.0018392022873740643}
+{"step": 61320, "dynamics_loss_avg": 0.0218899748288095}
+{"step": 61320, "action_loss_avg": 0.0010871353733818978}
+{"step": 61330, "dynamics_loss_avg": 0.021692372485995294}
+{"step": 61330, "action_loss_avg": 0.0009309466229751706}
+{"step": 61340, "dynamics_loss_avg": 0.028048163931816816}
+{"step": 61340, "action_loss_avg": 0.002249334822408855}
+{"step": 61350, "loss": 0.0289, "learning_rate": 3.557637716463981e-05}
+{"step": 61350, "dynamics_loss_avg": 0.02472475739195943}
+{"step": 61350, "action_loss_avg": 0.0013321047008503228}
+{"step": 61360, "dynamics_loss_avg": 0.02901791865006089}
+{"step": 61360, "action_loss_avg": 0.001322729283128865}
+{"step": 61370, "dynamics_loss_avg": 0.028364104917272925}
+{"step": 61370, "action_loss_avg": 0.0010046721959952264}
+{"step": 61380, "dynamics_loss_avg": 0.03710349816828966}
+{"step": 61380, "action_loss_avg": 0.0015110524342162534}
+{"step": 61390, "dynamics_loss_avg": 0.028058802848681806}
+{"step": 61390, "action_loss_avg": 0.0013636500982102007}
+{"step": 61400, "loss": 0.0296, "learning_rate": 3.5497238026045166e-05}
+{"step": 61400, "dynamics_loss_avg": 0.023948483960703017}
+{"step": 61400, "action_loss_avg": 0.001006145915016532}
+{"step": 61410, "dynamics_loss_avg": 0.029986874759197236}
+{"step": 61410, "action_loss_avg": 0.0018609496211865917}
+{"step": 61420, "dynamics_loss_avg": 0.028451786492951214}
+{"step": 61420, "action_loss_avg": 0.001088985276874155}
+{"step": 61430, "dynamics_loss_avg": 0.025347807770594956}
+{"step": 61430, "action_loss_avg": 0.0012969653122127055}
+{"step": 61440, "dynamics_loss_avg": 0.0310868501663208}
+{"step": 61440, "action_loss_avg": 0.0013580787752289325}
+{"step": 61450, "loss": 0.0327, "learning_rate": 3.5418138537447985e-05}
+{"step": 61450, "dynamics_loss_avg": 0.03928780220448971}
+{"step": 61450, "action_loss_avg": 0.0016254620277322829}
+{"step": 61460, "dynamics_loss_avg": 0.023736520390957593}
+{"step": 61460, "action_loss_avg": 0.0009762619796674698}
+{"step": 61470, "dynamics_loss_avg": 0.0333147032186389}
+{"step": 61470, "action_loss_avg": 0.0015569568902719765}
+{"step": 61480, "dynamics_loss_avg": 0.03694732654839754}
+{"step": 61480, "action_loss_avg": 0.002112610632320866}
+{"step": 61490, "dynamics_loss_avg": 0.02825373481027782}
+{"step": 61490, "action_loss_avg": 0.0012080381304258481}
+{"step": 61500, "loss": 0.0305, "learning_rate": 3.5339078915103214e-05}
+{"step": 61500, "dynamics_loss_avg": 0.02537420904263854}
+{"step": 61500, "action_loss_avg": 0.0009130988997640088}
+{"step": 61510, "dynamics_loss_avg": 0.03531677545979619}
+{"step": 61510, "action_loss_avg": 0.0013201227993704379}
+{"step": 61520, "dynamics_loss_avg": 0.028791493736207485}
+{"step": 61520, "action_loss_avg": 0.0014231331268092617}
+{"step": 61530, "dynamics_loss_avg": 0.02834843760356307}
+{"step": 61530, "action_loss_avg": 0.0014625444979174062}
+{"step": 61540, "dynamics_loss_avg": 0.021708156960085035}
+{"step": 61540, "action_loss_avg": 0.0010387259331764652}
+{"step": 61550, "loss": 0.0298, "learning_rate": 3.526005937515687e-05}
+{"step": 61550, "dynamics_loss_avg": 0.02425737036392093}
+{"step": 61550, "action_loss_avg": 0.00112369378330186}
+{"step": 61560, "dynamics_loss_avg": 0.037214125506579876}
+{"step": 61560, "action_loss_avg": 0.001795021741418168}
+{"step": 61570, "dynamics_loss_avg": 0.023131915647536517}
+{"step": 61570, "action_loss_avg": 0.0010747181018814444}
+{"step": 61580, "dynamics_loss_avg": 0.038080612383782866}
+{"step": 61580, "action_loss_avg": 0.001542915392201394}
+{"step": 61590, "dynamics_loss_avg": 0.02272937325760722}
+{"step": 61590, "action_loss_avg": 0.0010958867642330006}
+{"step": 61600, "loss": 0.0298, "learning_rate": 3.518108013364535e-05}
+{"step": 61600, "dynamics_loss_avg": 0.02548023322597146}
+{"step": 61600, "action_loss_avg": 0.0011096322443336249}
+{"step": 61610, "dynamics_loss_avg": 0.03044349099509418}
+{"step": 61610, "action_loss_avg": 0.0012080635468009859}
+{"step": 61620, "dynamics_loss_avg": 0.019268305879086255}
+{"step": 61620, "action_loss_avg": 0.0012435400189133362}
+{"step": 61630, "dynamics_loss_avg": 0.026834514643996953}
+{"step": 61630, "action_loss_avg": 0.0012418613012414425}
+{"step": 61640, "dynamics_loss_avg": 0.024457608954980968}
+{"step": 61640, "action_loss_avg": 0.000859002338256687}
+{"step": 61650, "loss": 0.0261, "learning_rate": 3.510214140649488e-05}
+{"step": 61650, "dynamics_loss_avg": 0.027471409388817848}
+{"step": 61650, "action_loss_avg": 0.0015473407387617045}
+{"step": 61660, "dynamics_loss_avg": 0.0411361520178616}
+{"step": 61660, "action_loss_avg": 0.002229868748690933}
+{"step": 61670, "dynamics_loss_avg": 0.030450833681970834}
+{"step": 61670, "action_loss_avg": 0.0016126146510941908}
+{"step": 61680, "dynamics_loss_avg": 0.03379869684576988}
+{"step": 61680, "action_loss_avg": 0.0010954662109725177}
+{"step": 61690, "dynamics_loss_avg": 0.0340073817409575}
+{"step": 61690, "action_loss_avg": 0.0018416557635646314}
+{"step": 61700, "loss": 0.0322, "learning_rate": 3.502324340952095e-05}
+{"step": 61700, "dynamics_loss_avg": 0.028039525169879197}
+{"step": 61700, "action_loss_avg": 0.0015176013199379667}
+{"step": 61710, "dynamics_loss_avg": 0.029655756521970035}
+{"step": 61710, "action_loss_avg": 0.001541824368177913}
+{"step": 61720, "dynamics_loss_avg": 0.03430763967335224}
+{"step": 61720, "action_loss_avg": 0.0015204736031591893}
+{"step": 61730, "dynamics_loss_avg": 0.025630055461078882}
+{"step": 61730, "action_loss_avg": 0.0009661853720899672}
+{"step": 61740, "dynamics_loss_avg": 0.027538937190547584}
+{"step": 61740, "action_loss_avg": 0.0010092926386278123}
+{"step": 61750, "loss": 0.0315, "learning_rate": 3.494438635842764e-05}
+{"step": 61750, "dynamics_loss_avg": 0.031441100686788556}
+{"step": 61750, "action_loss_avg": 0.0015649034321540967}
+{"step": 61760, "dynamics_loss_avg": 0.031051708199083806}
+{"step": 61760, "action_loss_avg": 0.0013247747760033236}
+{"step": 61770, "dynamics_loss_avg": 0.025818326883018015}
+{"step": 61770, "action_loss_avg": 0.0015801366302184761}
+{"step": 61780, "dynamics_loss_avg": 0.02637103646993637}
+{"step": 61780, "action_loss_avg": 0.0014722509833518416}
+{"step": 61790, "dynamics_loss_avg": 0.03673674413003027}
+{"step": 61790, "action_loss_avg": 0.0024262056045699864}
+{"step": 61800, "loss": 0.033, "learning_rate": 3.486557046880713e-05}
+{"step": 61800, "dynamics_loss_avg": 0.03735107826068997}
+{"step": 61800, "action_loss_avg": 0.0018185235385317355}
+{"step": 61810, "dynamics_loss_avg": 0.024997004587203265}
+{"step": 61810, "action_loss_avg": 0.0015147806087043136}
+{"step": 61820, "dynamics_loss_avg": 0.035344527661800386}
+{"step": 61820, "action_loss_avg": 0.0016847790859173984}
+{"step": 61830, "dynamics_loss_avg": 0.0459701320156455}
+{"step": 61830, "action_loss_avg": 0.001718257475295104}
+{"step": 61840, "dynamics_loss_avg": 0.022983199916779995}
+{"step": 61840, "action_loss_avg": 0.0011877170589286834}
+{"step": 61850, "loss": 0.0298, "learning_rate": 3.478679595613905e-05}
+{"step": 61850, "dynamics_loss_avg": 0.026093914732337}
+{"step": 61850, "action_loss_avg": 0.0013626694708364084}
+{"step": 61860, "dynamics_loss_avg": 0.024049540422856806}
+{"step": 61860, "action_loss_avg": 0.000992249755654484}
+{"step": 61870, "dynamics_loss_avg": 0.025039604026824237}
+{"step": 61870, "action_loss_avg": 0.0011818984494311735}
+{"step": 61880, "dynamics_loss_avg": 0.03003087267279625}
+{"step": 61880, "action_loss_avg": 0.001686697272816673}
+{"step": 61890, "dynamics_loss_avg": 0.036781076714396475}
+{"step": 61890, "action_loss_avg": 0.0016600024566287175}
+{"step": 61900, "loss": 0.0302, "learning_rate": 3.4708063035789906e-05}
+{"step": 61900, "dynamics_loss_avg": 0.024140637973323463}
+{"step": 61900, "action_loss_avg": 0.0010741246907855384}
+{"step": 61910, "dynamics_loss_avg": 0.030840099044144153}
+{"step": 61910, "action_loss_avg": 0.001388977890019305}
+{"step": 61920, "dynamics_loss_avg": 0.03186364006251097}
+{"step": 61920, "action_loss_avg": 0.002279145419015549}
+{"step": 61930, "dynamics_loss_avg": 0.02310877772979438}
+{"step": 61930, "action_loss_avg": 0.0010681040643248708}
+{"step": 61940, "dynamics_loss_avg": 0.01945134550333023}
+{"step": 61940, "action_loss_avg": 0.0011305616702884437}
+{"step": 61950, "loss": 0.0295, "learning_rate": 3.4629371923012526e-05}
+{"step": 61950, "dynamics_loss_avg": 0.01943214228376746}
+{"step": 61950, "action_loss_avg": 0.0009793161822017281}
+{"step": 61960, "dynamics_loss_avg": 0.03534932155162096}
+{"step": 61960, "action_loss_avg": 0.0018157958227675408}
+{"step": 61970, "dynamics_loss_avg": 0.03308409517630935}
+{"step": 61970, "action_loss_avg": 0.0020121094305068253}
+{"step": 61980, "dynamics_loss_avg": 0.028421790804713964}
+{"step": 61980, "action_loss_avg": 0.0015354252769611775}
+{"step": 61990, "dynamics_loss_avg": 0.01893203631043434}
+{"step": 61990, "action_loss_avg": 0.0010666900227079168}
+{"step": 62000, "loss": 0.03, "learning_rate": 3.4550722832945354e-05}
+{"step": 62000, "dynamics_loss_avg": 0.03178451666608453}
+{"step": 62000, "action_loss_avg": 0.0014609171426855027}
+{"step": 62010, "dynamics_loss_avg": 0.029548729257658123}
+{"step": 62010, "action_loss_avg": 0.001986292004585266}
+{"step": 62020, "dynamics_loss_avg": 0.023782573547214268}
+{"step": 62020, "action_loss_avg": 0.0010503739584237337}
+{"step": 62030, "dynamics_loss_avg": 0.03722887900657952}
+{"step": 62030, "action_loss_avg": 0.001505729090422392}
+{"step": 62040, "dynamics_loss_avg": 0.03243118072859943}
+{"step": 62040, "action_loss_avg": 0.0015941444842610508}
+{"step": 62050, "loss": 0.0319, "learning_rate": 3.4472115980612034e-05}
+{"step": 62050, "dynamics_loss_avg": 0.032341414503753184}
+{"step": 62050, "action_loss_avg": 0.0014636029372923076}
+{"step": 62060, "dynamics_loss_avg": 0.026744503155350687}
+{"step": 62060, "action_loss_avg": 0.0008490738371619954}
+{"step": 62070, "dynamics_loss_avg": 0.03221060149371624}
+{"step": 62070, "action_loss_avg": 0.0019385744293686003}
+{"step": 62080, "dynamics_loss_avg": 0.029092835169285534}
+{"step": 62080, "action_loss_avg": 0.001330486602091696}
+{"step": 62090, "dynamics_loss_avg": 0.029934318643063305}
+{"step": 62090, "action_loss_avg": 0.0013796095037832857}
+{"step": 62100, "loss": 0.0276, "learning_rate": 3.439355158092069e-05}
+{"step": 62100, "dynamics_loss_avg": 0.024368248414248228}
+{"step": 62100, "action_loss_avg": 0.0014183807477820664}
+{"step": 62110, "dynamics_loss_avg": 0.024543080385774373}
+{"step": 62110, "action_loss_avg": 0.0011231745418626815}
+{"step": 62120, "dynamics_loss_avg": 0.034971279464662074}
+{"step": 62120, "action_loss_avg": 0.001328918369836174}
+{"step": 62130, "dynamics_loss_avg": 0.026484717801213264}
+{"step": 62130, "action_loss_avg": 0.0010795348469400778}
+{"step": 62140, "dynamics_loss_avg": 0.024102236796170472}
+{"step": 62140, "action_loss_avg": 0.0008813765613012947}
+{"step": 62150, "loss": 0.0288, "learning_rate": 3.431502984866343e-05}
+{"step": 62150, "dynamics_loss_avg": 0.03031745124608278}
+{"step": 62150, "action_loss_avg": 0.0011122469819383695}
+{"step": 62160, "dynamics_loss_avg": 0.021167423529550432}
+{"step": 62160, "action_loss_avg": 0.000973643729230389}
+{"step": 62170, "dynamics_loss_avg": 0.03333081351593137}
+{"step": 62170, "action_loss_avg": 0.0019144182529998942}
+{"step": 62180, "dynamics_loss_avg": 0.025383719615638255}
+{"step": 62180, "action_loss_avg": 0.0012629865435883404}
+{"step": 62190, "dynamics_loss_avg": 0.03959407014772296}
+{"step": 62190, "action_loss_avg": 0.001770635199500248}
+{"step": 62200, "loss": 0.0295, "learning_rate": 3.4236550998515595e-05}
+{"step": 62200, "dynamics_loss_avg": 0.025817914120852947}
+{"step": 62200, "action_loss_avg": 0.001258781913202256}
+{"step": 62210, "dynamics_loss_avg": 0.031551561877131463}
+{"step": 62210, "action_loss_avg": 0.0015966234379447997}
+{"step": 62220, "dynamics_loss_avg": 0.02694764854386449}
+{"step": 62220, "action_loss_avg": 0.0012269963510334492}
+{"step": 62230, "dynamics_loss_avg": 0.025459952373057603}
+{"step": 62230, "action_loss_avg": 0.00104520813038107}
+{"step": 62240, "dynamics_loss_avg": 0.034309190697968006}
+{"step": 62240, "action_loss_avg": 0.0013896150747314095}
+{"step": 62250, "loss": 0.0308, "learning_rate": 3.41581152450354e-05}
+{"step": 62250, "dynamics_loss_avg": 0.034975618589669466}
+{"step": 62250, "action_loss_avg": 0.0016161663283128292}
+{"step": 62260, "dynamics_loss_avg": 0.034359144419431685}
+{"step": 62260, "action_loss_avg": 0.001528916833922267}
+{"step": 62270, "dynamics_loss_avg": 0.037799740210175514}
+{"step": 62270, "action_loss_avg": 0.00187369167979341}
+{"step": 62280, "dynamics_loss_avg": 0.02796279462054372}
+{"step": 62280, "action_loss_avg": 0.001164405804593116}
+{"step": 62290, "dynamics_loss_avg": 0.0277194295078516}
+{"step": 62290, "action_loss_avg": 0.002028012397931889}
+{"step": 62300, "loss": 0.0336, "learning_rate": 3.407972280266322e-05}
+{"step": 62300, "dynamics_loss_avg": 0.02262570010498166}
+{"step": 62300, "action_loss_avg": 0.0009724732575705275}
+{"step": 62310, "dynamics_loss_avg": 0.022898356523364784}
+{"step": 62310, "action_loss_avg": 0.0009176934690913185}
+{"step": 62320, "dynamics_loss_avg": 0.02469185097143054}
+{"step": 62320, "action_loss_avg": 0.0012813299719709903}
+{"step": 62330, "dynamics_loss_avg": 0.03255750210955739}
+{"step": 62330, "action_loss_avg": 0.0015132806758629159}
+{"step": 62340, "dynamics_loss_avg": 0.025558901485055685}
+{"step": 62340, "action_loss_avg": 0.0013161933165974915}
+{"step": 62350, "loss": 0.0286, "learning_rate": 3.4001373885720976e-05}
+{"step": 62350, "dynamics_loss_avg": 0.041205015406012534}
+{"step": 62350, "action_loss_avg": 0.0016938543209107592}
+{"step": 62360, "dynamics_loss_avg": 0.02201637760736048}
+{"step": 62360, "action_loss_avg": 0.0008119432503008283}
+{"step": 62370, "dynamics_loss_avg": 0.023953381553292276}
+{"step": 62370, "action_loss_avg": 0.0011736716027371586}
+{"step": 62380, "dynamics_loss_avg": 0.03182887537404895}
+{"step": 62380, "action_loss_avg": 0.0012381472857668995}
+{"step": 62390, "dynamics_loss_avg": 0.021552278054878117}
+{"step": 62390, "action_loss_avg": 0.0009619670978281647}
+{"step": 62400, "loss": 0.0289, "learning_rate": 3.392306870841164e-05}
+{"step": 62400, "dynamics_loss_avg": 0.03315110672265291}
+{"step": 62400, "action_loss_avg": 0.0016085059702163561}
+{"step": 62410, "dynamics_loss_avg": 0.022888973727822302}
+{"step": 62410, "action_loss_avg": 0.0011388426348275971}
+{"step": 62420, "dynamics_loss_avg": 0.030202666576951743}
+{"step": 62420, "action_loss_avg": 0.0016880899551324547}
+{"step": 62430, "dynamics_loss_avg": 0.03061894103884697}
+{"step": 62430, "action_loss_avg": 0.0014220330922398716}
+{"step": 62440, "dynamics_loss_avg": 0.023610977362841366}
+{"step": 62440, "action_loss_avg": 0.000995769421570003}
+{"step": 62450, "loss": 0.0284, "learning_rate": 3.384480748481855e-05}
+{"step": 62450, "dynamics_loss_avg": 0.028380894800648093}
+{"step": 62450, "action_loss_avg": 0.0012191462898044846}
+{"step": 62460, "dynamics_loss_avg": 0.02400520946830511}
+{"step": 62460, "action_loss_avg": 0.0014402837783563881}
+{"step": 62470, "dynamics_loss_avg": 0.03714943155646324}
+{"step": 62470, "action_loss_avg": 0.001775647938484326}
+{"step": 62480, "dynamics_loss_avg": 0.02958921268582344}
+{"step": 62480, "action_loss_avg": 0.0013709763821680098}
+{"step": 62490, "dynamics_loss_avg": 0.03474948685616255}
+{"step": 62490, "action_loss_avg": 0.0019460652081761509}
+{"step": 62500, "loss": 0.0309, "learning_rate": 3.376659042890489e-05}
+{"step": 62500, "dynamics_loss_avg": 0.02882357221096754}
+{"step": 62500, "action_loss_avg": 0.0014075974468141794}
+{"step": 62510, "dynamics_loss_avg": 0.030814807489514352}
+{"step": 62510, "action_loss_avg": 0.001973835937678814}
+{"step": 62520, "dynamics_loss_avg": 0.02661219174042344}
+{"step": 62520, "action_loss_avg": 0.0011136294197058305}
+{"step": 62530, "dynamics_loss_avg": 0.025346444640308618}
+{"step": 62530, "action_loss_avg": 0.0009892479341942818}
+{"step": 62540, "dynamics_loss_avg": 0.02541863895021379}
+{"step": 62540, "action_loss_avg": 0.0012286447250517084}
+{"step": 62550, "loss": 0.0282, "learning_rate": 3.3688417754513145e-05}
+{"step": 62550, "dynamics_loss_avg": 0.027655163872987033}
+{"step": 62550, "action_loss_avg": 0.0015128105616895482}
+{"step": 62560, "dynamics_loss_avg": 0.027510474808514117}
+{"step": 62560, "action_loss_avg": 0.0012273598171304912}
+{"step": 62570, "dynamics_loss_avg": 0.022479155240580438}
+{"step": 62570, "action_loss_avg": 0.0012020611204206944}
+{"step": 62580, "dynamics_loss_avg": 0.029022741550579666}
+{"step": 62580, "action_loss_avg": 0.0009265369255444967}
+{"step": 62590, "dynamics_loss_avg": 0.027373382076621055}
+{"step": 62590, "action_loss_avg": 0.0014924393093679101}
+{"step": 62600, "loss": 0.0297, "learning_rate": 3.36102896753644e-05}
+{"step": 62600, "dynamics_loss_avg": 0.03334381878376007}
+{"step": 62600, "action_loss_avg": 0.0018459045531926677}
+{"step": 62610, "dynamics_loss_avg": 0.03012082464993}
+{"step": 62610, "action_loss_avg": 0.0012542964366730302}
+{"step": 62620, "dynamics_loss_avg": 0.025282971654087306}
+{"step": 62620, "action_loss_avg": 0.0015405440470203757}
+{"step": 62630, "dynamics_loss_avg": 0.03258737530559301}
+{"step": 62630, "action_loss_avg": 0.0015907553752185777}
+{"step": 62640, "dynamics_loss_avg": 0.040313795953989026}
+{"step": 62640, "action_loss_avg": 0.0020840040233451873}
+{"step": 62650, "loss": 0.0326, "learning_rate": 3.3532206405057864e-05}
+{"step": 62650, "dynamics_loss_avg": 0.02933265557512641}
+{"step": 62650, "action_loss_avg": 0.0015210655401460826}
+{"step": 62660, "dynamics_loss_avg": 0.038971738424152136}
+{"step": 62660, "action_loss_avg": 0.0017668731859885156}
+{"step": 62670, "dynamics_loss_avg": 0.031992372777313}
+{"step": 62670, "action_loss_avg": 0.0013944233010988682}
+{"step": 62680, "dynamics_loss_avg": 0.040648013539612296}
+{"step": 62680, "action_loss_avg": 0.0018865416815970093}
+{"step": 62690, "dynamics_loss_avg": 0.028657739330083132}
+{"step": 62690, "action_loss_avg": 0.001191683011711575}
+{"step": 62700, "loss": 0.0344, "learning_rate": 3.345416815707017e-05}
+{"step": 62700, "dynamics_loss_avg": 0.02584028746932745}
+{"step": 62700, "action_loss_avg": 0.0012245995400007813}
+{"step": 62710, "dynamics_loss_avg": 0.03745271870866418}
+{"step": 62710, "action_loss_avg": 0.0015412737207952886}
+{"step": 62720, "dynamics_loss_avg": 0.02451805560849607}
+{"step": 62720, "action_loss_avg": 0.0011065591534134}
+{"step": 62730, "dynamics_loss_avg": 0.026910968311131}
+{"step": 62730, "action_loss_avg": 0.0015951165711157954}
+{"step": 62740, "dynamics_loss_avg": 0.03770392369478941}
+{"step": 62740, "action_loss_avg": 0.0017427591781597584}
+{"step": 62750, "loss": 0.0296, "learning_rate": 3.3376175144754935e-05}
+{"step": 62750, "dynamics_loss_avg": 0.02360323751345277}
+{"step": 62750, "action_loss_avg": 0.0010604058770695701}
+{"step": 62760, "dynamics_loss_avg": 0.027137185260653496}
+{"step": 62760, "action_loss_avg": 0.0014669778232928366}
+{"step": 62770, "dynamics_loss_avg": 0.02065333602949977}
+{"step": 62770, "action_loss_avg": 0.0009422723960597068}
+{"step": 62780, "dynamics_loss_avg": 0.0280095967464149}
+{"step": 62780, "action_loss_avg": 0.0010524377343244852}
+{"step": 62790, "dynamics_loss_avg": 0.02343006697483361}
+{"step": 62790, "action_loss_avg": 0.0008709184941835702}
+{"step": 62800, "loss": 0.0267, "learning_rate": 3.3298227581342076e-05}
+{"step": 62800, "dynamics_loss_avg": 0.028189334971830248}
+{"step": 62800, "action_loss_avg": 0.0010899693472310901}
+{"step": 62810, "dynamics_loss_avg": 0.028214854560792445}
+{"step": 62810, "action_loss_avg": 0.0011402395408367737}
+{"step": 62820, "dynamics_loss_avg": 0.03072429560124874}
+{"step": 62820, "action_loss_avg": 0.0016975422913674265}
+{"step": 62830, "dynamics_loss_avg": 0.02579905418679118}
+{"step": 62830, "action_loss_avg": 0.001123557728715241}
+{"step": 62840, "dynamics_loss_avg": 0.031853648088872435}
+{"step": 62840, "action_loss_avg": 0.0018139790947316215}
+{"step": 62850, "loss": 0.0296, "learning_rate": 3.322032567993728e-05}
+{"step": 62850, "dynamics_loss_avg": 0.03005405804142356}
+{"step": 62850, "action_loss_avg": 0.0012387930590193718}
+{"step": 62860, "dynamics_loss_avg": 0.024538334645330905}
+{"step": 62860, "action_loss_avg": 0.0019427417893894017}
+{"step": 62870, "dynamics_loss_avg": 0.022359315305948257}
+{"step": 62870, "action_loss_avg": 0.0012388027244014665}
+{"step": 62880, "dynamics_loss_avg": 0.0343999195843935}
+{"step": 62880, "action_loss_avg": 0.0016339136986061932}
+{"step": 62890, "dynamics_loss_avg": 0.03662027781829238}
+{"step": 62890, "action_loss_avg": 0.0015151396335568279}
+{"step": 62900, "loss": 0.0305, "learning_rate": 3.3142469653521316e-05}
+{"step": 62900, "dynamics_loss_avg": 0.03558059893548489}
+{"step": 62900, "action_loss_avg": 0.00170067481813021}
+{"step": 62910, "dynamics_loss_avg": 0.03721916871145368}
+{"step": 62910, "action_loss_avg": 0.0014894355175783859}
+{"step": 62920, "dynamics_loss_avg": 0.019542363192886113}
+{"step": 62920, "action_loss_avg": 0.0007882347126724198}
+{"step": 62930, "dynamics_loss_avg": 0.027976910769939422}
+{"step": 62930, "action_loss_avg": 0.000943787259166129}
+{"step": 62940, "dynamics_loss_avg": 0.0267030855640769}
+{"step": 62940, "action_loss_avg": 0.001048851665109396}
+{"step": 62950, "loss": 0.0311, "learning_rate": 3.306465971494963e-05}
+{"step": 62950, "dynamics_loss_avg": 0.04374781921505928}
+{"step": 62950, "action_loss_avg": 0.0018396536586806178}
+{"step": 62960, "dynamics_loss_avg": 0.029000855330377818}
+{"step": 62960, "action_loss_avg": 0.0013516080158296972}
+{"step": 62970, "dynamics_loss_avg": 0.025229794019833208}
+{"step": 62970, "action_loss_avg": 0.001203130854992196}
+{"step": 62980, "dynamics_loss_avg": 0.029069746378809214}
+{"step": 62980, "action_loss_avg": 0.0011923076788662}
+{"step": 62990, "dynamics_loss_avg": 0.02629288174211979}
+{"step": 62990, "action_loss_avg": 0.0010166943946387618}
+{"step": 63000, "loss": 0.0299, "learning_rate": 3.2986896076951585e-05}
+{"step": 63000, "dynamics_loss_avg": 0.03259753631427884}
+{"step": 63000, "action_loss_avg": 0.0016486106964293868}
+{"step": 63010, "dynamics_loss_avg": 0.025490264315158127}
+{"step": 63010, "action_loss_avg": 0.000844622208387591}
+{"step": 63020, "dynamics_loss_avg": 0.025470016151666643}
+{"step": 63020, "action_loss_avg": 0.0006950733368285}
+{"step": 63030, "dynamics_loss_avg": 0.025924627482891083}
+{"step": 63030, "action_loss_avg": 0.0009831549017690123}
+{"step": 63040, "dynamics_loss_avg": 0.021051747212186455}
+{"step": 63040, "action_loss_avg": 0.0010313648104784078}
+{"step": 63050, "loss": 0.0299, "learning_rate": 3.290917895213004e-05}
+{"step": 63050, "dynamics_loss_avg": 0.03279829453676939}
+{"step": 63050, "action_loss_avg": 0.0019833717145957054}
+{"step": 63060, "dynamics_loss_avg": 0.04086634740233421}
+{"step": 63060, "action_loss_avg": 0.002226731140399352}
+{"step": 63070, "dynamics_loss_avg": 0.02821445297449827}
+{"step": 63070, "action_loss_avg": 0.0015195275598671287}
+{"step": 63080, "dynamics_loss_avg": 0.03295390428975224}
+{"step": 63080, "action_loss_avg": 0.0018614414031617344}
+{"step": 63090, "dynamics_loss_avg": 0.03521224167197943}
+{"step": 63090, "action_loss_avg": 0.0015443963056895882}
+{"step": 63100, "loss": 0.0353, "learning_rate": 3.2831508552960646e-05}
+{"step": 63100, "dynamics_loss_avg": 0.02483532764017582}
+{"step": 63100, "action_loss_avg": 0.001554164828849025}
+{"step": 63110, "dynamics_loss_avg": 0.027565721608698367}
+{"step": 63110, "action_loss_avg": 0.0013344156846869736}
+{"step": 63120, "dynamics_loss_avg": 0.020000784285366537}
+{"step": 63120, "action_loss_avg": 0.001336361959693022}
+{"step": 63130, "dynamics_loss_avg": 0.031908543221652506}
+{"step": 63130, "action_loss_avg": 0.0012494858092395589}
+{"step": 63140, "dynamics_loss_avg": 0.022375822300091386}
+{"step": 63140, "action_loss_avg": 0.0009168484000838361}
+{"step": 63150, "loss": 0.0267, "learning_rate": 3.275388509179127e-05}
+{"step": 63150, "dynamics_loss_avg": 0.019933936349116266}
+{"step": 63150, "action_loss_avg": 0.0009702433948405087}
+{"step": 63160, "dynamics_loss_avg": 0.02927679815329611}
+{"step": 63160, "action_loss_avg": 0.0014459803118370474}
+{"step": 63170, "dynamics_loss_avg": 0.02781398519873619}
+{"step": 63170, "action_loss_avg": 0.0010679772647563368}
+{"step": 63180, "dynamics_loss_avg": 0.01746422229334712}
+{"step": 63180, "action_loss_avg": 0.0009314587368862703}
+{"step": 63190, "dynamics_loss_avg": 0.03370000896975398}
+{"step": 63190, "action_loss_avg": 0.0023059714527335017}
+{"step": 63200, "loss": 0.028, "learning_rate": 3.2676308780841516e-05}
+{"step": 63200, "dynamics_loss_avg": 0.029014464374631642}
+{"step": 63200, "action_loss_avg": 0.0014894926454871893}
+{"step": 63210, "dynamics_loss_avg": 0.027029472496360542}
+{"step": 63210, "action_loss_avg": 0.0011588615525397472}
+{"step": 63220, "dynamics_loss_avg": 0.028750758059322833}
+{"step": 63220, "action_loss_avg": 0.000924040551763028}
+{"step": 63230, "dynamics_loss_avg": 0.032560191676020624}
+{"step": 63230, "action_loss_avg": 0.0017332993913441897}
+{"step": 63240, "dynamics_loss_avg": 0.033755137026309966}
+{"step": 63240, "action_loss_avg": 0.001424881149432622}
+{"step": 63250, "loss": 0.0306, "learning_rate": 3.259877983220203e-05}
+{"step": 63250, "dynamics_loss_avg": 0.027622742252424358}
+{"step": 63250, "action_loss_avg": 0.0013865508080925792}
+{"step": 63260, "dynamics_loss_avg": 0.026402153726667165}
+{"step": 63260, "action_loss_avg": 0.0014401475375052542}
+{"step": 63270, "dynamics_loss_avg": 0.02628156766295433}
+{"step": 63270, "action_loss_avg": 0.0011547622212674468}
+{"step": 63280, "dynamics_loss_avg": 0.03300513494759798}
+{"step": 63280, "action_loss_avg": 0.0014947808347642421}
+{"step": 63290, "dynamics_loss_avg": 0.031088010780513285}
+{"step": 63290, "action_loss_avg": 0.0016337130800820887}
+{"step": 63300, "loss": 0.0297, "learning_rate": 3.252129845783404e-05}
+{"step": 63300, "dynamics_loss_avg": 0.036067925626412034}
+{"step": 63300, "action_loss_avg": 0.0023434131289832294}
+{"step": 63310, "dynamics_loss_avg": 0.024582924973219632}
+{"step": 63310, "action_loss_avg": 0.0008970485156169161}
+{"step": 63320, "dynamics_loss_avg": 0.024559974670410156}
+{"step": 63320, "action_loss_avg": 0.0010968730552121998}
+{"step": 63330, "dynamics_loss_avg": 0.02665288429707289}
+{"step": 63330, "action_loss_avg": 0.0013889731402741746}
+{"step": 63340, "dynamics_loss_avg": 0.03701770189218223}
+{"step": 63340, "action_loss_avg": 0.0016447061090730131}
+{"step": 63350, "loss": 0.0303, "learning_rate": 3.244386486956866e-05}
+{"step": 63350, "dynamics_loss_avg": 0.03619501879438758}
+{"step": 63350, "action_loss_avg": 0.0012727173743769526}
+{"step": 63360, "dynamics_loss_avg": 0.037422113679349424}
+{"step": 63360, "action_loss_avg": 0.0015252111275913193}
+{"step": 63370, "dynamics_loss_avg": 0.0254554633051157}
+{"step": 63370, "action_loss_avg": 0.001011501671746373}
+{"step": 63380, "dynamics_loss_avg": 0.021451579593122005}
+{"step": 63380, "action_loss_avg": 0.0010492062545381486}
+{"step": 63390, "dynamics_loss_avg": 0.030846509151160717}
+{"step": 63390, "action_loss_avg": 0.0018476962723070756}
+{"step": 63400, "loss": 0.03, "learning_rate": 3.236647927910633e-05}
+{"step": 63400, "dynamics_loss_avg": 0.02636134633794427}
+{"step": 63400, "action_loss_avg": 0.001403316343203187}
+{"step": 63410, "dynamics_loss_avg": 0.03281267732381821}
+{"step": 63410, "action_loss_avg": 0.0013094300869852305}
+{"step": 63420, "dynamics_loss_avg": 0.025968923093751074}
+{"step": 63420, "action_loss_avg": 0.0010710552844102495}
+{"step": 63430, "dynamics_loss_avg": 0.023894920479506254}
+{"step": 63430, "action_loss_avg": 0.0012495787639636546}
+{"step": 63440, "dynamics_loss_avg": 0.02854955056682229}
+{"step": 63440, "action_loss_avg": 0.0015562320651952178}
+{"step": 63450, "loss": 0.0289, "learning_rate": 3.2289141898016315e-05}
+{"step": 63450, "dynamics_loss_avg": 0.028625154215842486}
+{"step": 63450, "action_loss_avg": 0.0014515602786559611}
+{"step": 63460, "dynamics_loss_avg": 0.024752088589593768}
+{"step": 63460, "action_loss_avg": 0.001134108757833019}
+{"step": 63470, "dynamics_loss_avg": 0.03006874807178974}
+{"step": 63470, "action_loss_avg": 0.001454351839493029}
+{"step": 63480, "dynamics_loss_avg": 0.03074529580771923}
+{"step": 63480, "action_loss_avg": 0.0013979405863210558}
+{"step": 63490, "dynamics_loss_avg": 0.027663250919431448}
+{"step": 63490, "action_loss_avg": 0.0014230332570150494}
+{"step": 63500, "loss": 0.0275, "learning_rate": 3.221185293773605e-05}
+{"step": 63500, "dynamics_loss_avg": 0.02934596296399832}
+{"step": 63500, "action_loss_avg": 0.001123204192845151}
+{"step": 63510, "dynamics_loss_avg": 0.026197651773691176}
+{"step": 63510, "action_loss_avg": 0.0016956533334450796}
+{"step": 63520, "dynamics_loss_avg": 0.04175486913882196}
+{"step": 63520, "action_loss_avg": 0.002074965013889596}
+{"step": 63530, "dynamics_loss_avg": 0.02920456975698471}
+{"step": 63530, "action_loss_avg": 0.0013263340573757888}
+{"step": 63540, "dynamics_loss_avg": 0.0302771620452404}
+{"step": 63540, "action_loss_avg": 0.0016497795819304883}
+{"step": 63550, "loss": 0.0317, "learning_rate": 3.2134612609570644e-05}
+{"step": 63550, "dynamics_loss_avg": 0.02534234318882227}
+{"step": 63550, "action_loss_avg": 0.0012277502217330038}
+{"step": 63560, "dynamics_loss_avg": 0.02514269817620516}
+{"step": 63560, "action_loss_avg": 0.0014519293530611322}
+{"step": 63570, "dynamics_loss_avg": 0.015936964377760886}
+{"step": 63570, "action_loss_avg": 0.0009849898720858618}
+{"step": 63580, "dynamics_loss_avg": 0.03398914095014334}
+{"step": 63580, "action_loss_avg": 0.0017877857317216694}
+{"step": 63590, "dynamics_loss_avg": 0.033833360951393845}
+{"step": 63590, "action_loss_avg": 0.0010551189247053117}
+{"step": 63600, "loss": 0.028, "learning_rate": 3.205742112469217e-05}
+{"step": 63600, "dynamics_loss_avg": 0.028902312088757754}
+{"step": 63600, "action_loss_avg": 0.0018673849728656933}
+{"step": 63610, "dynamics_loss_avg": 0.028143747337162496}
+{"step": 63610, "action_loss_avg": 0.0013477452535880729}
+{"step": 63620, "dynamics_loss_avg": 0.038360292091965675}
+{"step": 63620, "action_loss_avg": 0.0014971712516853586}
+{"step": 63630, "dynamics_loss_avg": 0.026432410068809985}
+{"step": 63630, "action_loss_avg": 0.0012668317431234755}
+{"step": 63640, "dynamics_loss_avg": 0.03238297705538571}
+{"step": 63640, "action_loss_avg": 0.0018610005703521893}
+{"step": 63650, "loss": 0.032, "learning_rate": 3.1980278694139186e-05}
+{"step": 63650, "dynamics_loss_avg": 0.023015118716284633}
+{"step": 63650, "action_loss_avg": 0.001040077701327391}
+{"step": 63660, "dynamics_loss_avg": 0.027291761990636588}
+{"step": 63660, "action_loss_avg": 0.0011759263288695365}
+{"step": 63670, "dynamics_loss_avg": 0.03278485052287579}
+{"step": 63670, "action_loss_avg": 0.0015723753545898943}
+{"step": 63680, "dynamics_loss_avg": 0.025268696062266827}
+{"step": 63680, "action_loss_avg": 0.0012447703076759354}
+{"step": 63690, "dynamics_loss_avg": 0.02400953574106097}
+{"step": 63690, "action_loss_avg": 0.0007923402721644379}
+{"step": 63700, "loss": 0.0294, "learning_rate": 3.190318552881618e-05}
+{"step": 63700, "dynamics_loss_avg": 0.02955583157017827}
+{"step": 63700, "action_loss_avg": 0.0015542024746537208}
+{"step": 63710, "dynamics_loss_avg": 0.0237966257147491}
+{"step": 63710, "action_loss_avg": 0.0013575500808656216}
+{"step": 63720, "dynamics_loss_avg": 0.020198148023337126}
+{"step": 63720, "action_loss_avg": 0.0009089120285352692}
+{"step": 63730, "dynamics_loss_avg": 0.03246285552158952}
+{"step": 63730, "action_loss_avg": 0.0013350997061934323}
+{"step": 63740, "dynamics_loss_avg": 0.025051282672211527}
+{"step": 63740, "action_loss_avg": 0.0013416635687462986}
+{"step": 63750, "loss": 0.0298, "learning_rate": 3.1826141839492906e-05}
+{"step": 63750, "dynamics_loss_avg": 0.03689596094191074}
+{"step": 63750, "action_loss_avg": 0.0020359363057650625}
+{"step": 63760, "dynamics_loss_avg": 0.036109608691185714}
+{"step": 63760, "action_loss_avg": 0.0018343322270084172}
+{"step": 63770, "dynamics_loss_avg": 0.03290044665336609}
+{"step": 63770, "action_loss_avg": 0.0011914797796634957}
+{"step": 63780, "dynamics_loss_avg": 0.025495617557317017}
+{"step": 63780, "action_loss_avg": 0.0011057763709686696}
+{"step": 63790, "dynamics_loss_avg": 0.03032034868374467}
+{"step": 63790, "action_loss_avg": 0.0012689001829130574}
+{"step": 63800, "loss": 0.0303, "learning_rate": 3.17491478368039e-05}
+{"step": 63800, "dynamics_loss_avg": 0.03179236671421677}
+{"step": 63800, "action_loss_avg": 0.0016433520533610136}
+{"step": 63810, "dynamics_loss_avg": 0.031253216043114665}
+{"step": 63810, "action_loss_avg": 0.0014630231948103757}
+{"step": 63820, "dynamics_loss_avg": 0.030746570648625494}
+{"step": 63820, "action_loss_avg": 0.0013325292675290257}
+{"step": 63830, "dynamics_loss_avg": 0.040035197883844374}
+{"step": 63830, "action_loss_avg": 0.0019485484837787226}
+{"step": 63840, "dynamics_loss_avg": 0.02924554287455976}
+{"step": 63840, "action_loss_avg": 0.0014509509055642411}
+{"step": 63850, "loss": 0.0314, "learning_rate": 3.1672203731247785e-05}
+{"step": 63850, "dynamics_loss_avg": 0.028789204219356178}
+{"step": 63850, "action_loss_avg": 0.001062287192326039}
+{"step": 63860, "dynamics_loss_avg": 0.0209989556344226}
+{"step": 63860, "action_loss_avg": 0.0012423104402842}
+{"step": 63870, "dynamics_loss_avg": 0.028808170836418866}
+{"step": 63870, "action_loss_avg": 0.0012013361614663155}
+{"step": 63880, "dynamics_loss_avg": 0.03680191952735186}
+{"step": 63880, "action_loss_avg": 0.00154672633507289}
+{"step": 63890, "dynamics_loss_avg": 0.025420664437115194}
+{"step": 63890, "action_loss_avg": 0.0011663653538562357}
+{"step": 63900, "loss": 0.0276, "learning_rate": 3.159530973318682e-05}
+{"step": 63900, "dynamics_loss_avg": 0.02718020984902978}
+{"step": 63900, "action_loss_avg": 0.0014165752480039373}
+{"step": 63910, "dynamics_loss_avg": 0.024409179482609032}
+{"step": 63910, "action_loss_avg": 0.000950174022000283}
+{"step": 63920, "dynamics_loss_avg": 0.018895241664722562}
+{"step": 63920, "action_loss_avg": 0.0009806035814108327}
+{"step": 63930, "dynamics_loss_avg": 0.03588065151125193}
+{"step": 63930, "action_loss_avg": 0.0016995940823107958}
+{"step": 63940, "dynamics_loss_avg": 0.024302607122808694}
+{"step": 63940, "action_loss_avg": 0.0009418174624443055}
+{"step": 63950, "loss": 0.0272, "learning_rate": 3.1518466052846264e-05}
+{"step": 63950, "dynamics_loss_avg": 0.03429205343127251}
+{"step": 63950, "action_loss_avg": 0.001949810583028011}
+{"step": 63960, "dynamics_loss_avg": 0.026895005162805317}
+{"step": 63960, "action_loss_avg": 0.0017674594826530665}
+{"step": 63970, "dynamics_loss_avg": 0.029043025569990277}
+{"step": 63970, "action_loss_avg": 0.0019590847543440757}
+{"step": 63980, "dynamics_loss_avg": 0.031236513424664734}
+{"step": 63980, "action_loss_avg": 0.0018427687580697238}
+{"step": 63990, "dynamics_loss_avg": 0.03531767120584846}
+{"step": 63990, "action_loss_avg": 0.0022532051894813775}
+{"step": 64000, "loss": 0.0303, "learning_rate": 3.144167290031382e-05}
+{"step": 64000, "dynamics_loss_avg": 0.02400052035227418}
+{"step": 64000, "action_loss_avg": 0.0010345824004616589}
+{"step": 64010, "dynamics_loss_avg": 0.034790578810498116}
+{"step": 64010, "action_loss_avg": 0.0013835031248163431}
+{"step": 64020, "dynamics_loss_avg": 0.023822603281587362}
+{"step": 64020, "action_loss_avg": 0.0009788287919946016}
+{"step": 64030, "dynamics_loss_avg": 0.036107117775827646}
+{"step": 64030, "action_loss_avg": 0.0017263323941733688}
+{"step": 64040, "dynamics_loss_avg": 0.028115852549672127}
+{"step": 64040, "action_loss_avg": 0.0013342000456759706}
+{"step": 64050, "loss": 0.0301, "learning_rate": 3.1364930485539e-05}
+{"step": 64050, "dynamics_loss_avg": 0.027083200961351396}
+{"step": 64050, "action_loss_avg": 0.0011761928995838388}
+{"step": 64060, "dynamics_loss_avg": 0.023120094649493696}
+{"step": 64060, "action_loss_avg": 0.0011916909395949915}
+{"step": 64070, "dynamics_loss_avg": 0.028042519697919488}
+{"step": 64070, "action_loss_avg": 0.0015752501814858988}
+{"step": 64080, "dynamics_loss_avg": 0.02938496428541839}
+{"step": 64080, "action_loss_avg": 0.0012112691809306852}
+{"step": 64090, "dynamics_loss_avg": 0.028908459935337305}
+{"step": 64090, "action_loss_avg": 0.0017970485525438562}
+{"step": 64100, "loss": 0.028, "learning_rate": 3.1288239018332656e-05}
+{"step": 64100, "dynamics_loss_avg": 0.025047409534454345}
+{"step": 64100, "action_loss_avg": 0.0009608956621377729}
+{"step": 64110, "dynamics_loss_avg": 0.036368805915117264}
+{"step": 64110, "action_loss_avg": 0.0016654985840432346}
+{"step": 64120, "dynamics_loss_avg": 0.021076214010827245}
+{"step": 64120, "action_loss_avg": 0.0008195338261430152}
+{"step": 64130, "dynamics_loss_avg": 0.026296899188309908}
+{"step": 64130, "action_loss_avg": 0.0009385464974911884}
+{"step": 64140, "dynamics_loss_avg": 0.024093175400048496}
+{"step": 64140, "action_loss_avg": 0.0010086546884849668}
+{"step": 64150, "loss": 0.029, "learning_rate": 3.121159870836633e-05}
+{"step": 64150, "dynamics_loss_avg": 0.032924150489270686}
+{"step": 64150, "action_loss_avg": 0.0015953879075823352}
+{"step": 64160, "dynamics_loss_avg": 0.02783865756355226}
+{"step": 64160, "action_loss_avg": 0.0011267420894000679}
+{"step": 64170, "dynamics_loss_avg": 0.03441509827971458}
+{"step": 64170, "action_loss_avg": 0.0017512133345007896}
+{"step": 64180, "dynamics_loss_avg": 0.02875524144619703}
+{"step": 64180, "action_loss_avg": 0.0014584960939828307}
+{"step": 64190, "dynamics_loss_avg": 0.030138341803103687}
+{"step": 64190, "action_loss_avg": 0.0012939811451360584}
+{"step": 64200, "loss": 0.0315, "learning_rate": 3.1135009765171696e-05}
+{"step": 64200, "dynamics_loss_avg": 0.03151304498314857}
+{"step": 64200, "action_loss_avg": 0.0014130370662314817}
+{"step": 64210, "dynamics_loss_avg": 0.02560387710109353}
+{"step": 64210, "action_loss_avg": 0.0011042188969440758}
+{"step": 64220, "dynamics_loss_avg": 0.02991463034413755}
+{"step": 64220, "action_loss_avg": 0.001649892597924918}
+{"step": 64230, "dynamics_loss_avg": 0.026347020640969276}
+{"step": 64230, "action_loss_avg": 0.00122804265411105}
+{"step": 64240, "dynamics_loss_avg": 0.029512006044387817}
+{"step": 64240, "action_loss_avg": 0.0013476613617967813}
+{"step": 64250, "loss": 0.0281, "learning_rate": 3.1058472398140035e-05}
+{"step": 64250, "dynamics_loss_avg": 0.02338719563558698}
+{"step": 64250, "action_loss_avg": 0.0011382966476958245}
+{"step": 64260, "dynamics_loss_avg": 0.03254924183711409}
+{"step": 64260, "action_loss_avg": 0.001978087506722659}
+{"step": 64270, "dynamics_loss_avg": 0.012118556257337331}
+{"step": 64270, "action_loss_avg": 0.0006387828558217734}
+{"step": 64280, "dynamics_loss_avg": 0.02664178190752864}
+{"step": 64280, "action_loss_avg": 0.000821745692519471}
+{"step": 64290, "dynamics_loss_avg": 0.02271601352840662}
+{"step": 64290, "action_loss_avg": 0.0010678861741325817}
+{"step": 64300, "loss": 0.027, "learning_rate": 3.098198681652154e-05}
+{"step": 64300, "dynamics_loss_avg": 0.031218719203025103}
+{"step": 64300, "action_loss_avg": 0.0012464337574783712}
+{"step": 64310, "dynamics_loss_avg": 0.02384496768936515}
+{"step": 64310, "action_loss_avg": 0.0010693798889406026}
+{"step": 64320, "dynamics_loss_avg": 0.035717771667987105}
+{"step": 64320, "action_loss_avg": 0.0017507140524685382}
+{"step": 64330, "dynamics_loss_avg": 0.028115368727594615}
+{"step": 64330, "action_loss_avg": 0.0010231081920210271}
+{"step": 64340, "dynamics_loss_avg": 0.02489977879449725}
+{"step": 64340, "action_loss_avg": 0.00096587962761987}
+{"step": 64350, "loss": 0.0291, "learning_rate": 3.090555322942488e-05}
+{"step": 64350, "dynamics_loss_avg": 0.025415004324167968}
+{"step": 64350, "action_loss_avg": 0.0009553002513712272}
+{"step": 64360, "dynamics_loss_avg": 0.024027789151296018}
+{"step": 64360, "action_loss_avg": 0.0010331771103665234}
+{"step": 64370, "dynamics_loss_avg": 0.03232184457592666}
+{"step": 64370, "action_loss_avg": 0.0011805882735643537}
+{"step": 64380, "dynamics_loss_avg": 0.030934103345498443}
+{"step": 64380, "action_loss_avg": 0.0018253706657560542}
+{"step": 64390, "dynamics_loss_avg": 0.03066964605823159}
+{"step": 64390, "action_loss_avg": 0.001636008929926902}
+{"step": 64400, "loss": 0.0315, "learning_rate": 3.082917184581657e-05}
+{"step": 64400, "dynamics_loss_avg": 0.03621292435564101}
+{"step": 64400, "action_loss_avg": 0.0016737077094148844}
+{"step": 64410, "dynamics_loss_avg": 0.02945763459429145}
+{"step": 64410, "action_loss_avg": 0.0012238482071552426}
+{"step": 64420, "dynamics_loss_avg": 0.02708813492208719}
+{"step": 64420, "action_loss_avg": 0.001152253762120381}
+{"step": 64430, "dynamics_loss_avg": 0.018700592033565045}
+{"step": 64430, "action_loss_avg": 0.0011557813340914436}
+{"step": 64440, "dynamics_loss_avg": 0.034548154659569265}
+{"step": 64440, "action_loss_avg": 0.001768307707970962}
+{"step": 64450, "loss": 0.0287, "learning_rate": 3.0752842874520396e-05}
+{"step": 64450, "dynamics_loss_avg": 0.03730275640264154}
+{"step": 64450, "action_loss_avg": 0.001956112837069668}
+{"step": 64460, "dynamics_loss_avg": 0.030224061012268065}
+{"step": 64460, "action_loss_avg": 0.0013878686644602568}
+{"step": 64470, "dynamics_loss_avg": 0.031096012331545353}
+{"step": 64470, "action_loss_avg": 0.0014557587914168836}
+{"step": 64480, "dynamics_loss_avg": 0.03231158228591084}
+{"step": 64480, "action_loss_avg": 0.0015901855804258958}
+{"step": 64490, "dynamics_loss_avg": 0.02478615827858448}
+{"step": 64490, "action_loss_avg": 0.0011098813673015683}
+{"step": 64500, "loss": 0.0306, "learning_rate": 3.067656652421687e-05}
+{"step": 64500, "dynamics_loss_avg": 0.02509498279541731}
+{"step": 64500, "action_loss_avg": 0.0013159939786419272}
+{"step": 64510, "dynamics_loss_avg": 0.02636756682768464}
+{"step": 64510, "action_loss_avg": 0.0012467086315155029}
+{"step": 64520, "dynamics_loss_avg": 0.028656268119812013}
+{"step": 64520, "action_loss_avg": 0.0012544886849354953}
+{"step": 64530, "dynamics_loss_avg": 0.024552768934518097}
+{"step": 64530, "action_loss_avg": 0.000911280105356127}
+{"step": 64540, "dynamics_loss_avg": 0.03573228884488344}
+{"step": 64540, "action_loss_avg": 0.0018169922870583833}
+{"step": 64550, "loss": 0.0273, "learning_rate": 3.060034300344259e-05}
+{"step": 64550, "dynamics_loss_avg": 0.02295816093683243}
+{"step": 64550, "action_loss_avg": 0.0010477130825165659}
+{"step": 64560, "dynamics_loss_avg": 0.02829575538635254}
+{"step": 64560, "action_loss_avg": 0.001488322639488615}
+{"step": 64570, "dynamics_loss_avg": 0.021485938783735038}
+{"step": 64570, "action_loss_avg": 0.0008491262269672006}
+{"step": 64580, "dynamics_loss_avg": 0.03016943847760558}
+{"step": 64580, "action_loss_avg": 0.0017009871691698209}
+{"step": 64590, "dynamics_loss_avg": 0.02878792737610638}
+{"step": 64590, "action_loss_avg": 0.001644897738879081}
+{"step": 64600, "loss": 0.0286, "learning_rate": 3.052417252058977e-05}
+{"step": 64600, "dynamics_loss_avg": 0.03194294115528464}
+{"step": 64600, "action_loss_avg": 0.001511205278802663}
+{"step": 64610, "dynamics_loss_avg": 0.030159343779087067}
+{"step": 64610, "action_loss_avg": 0.0012336958257947116}
+{"step": 64620, "dynamics_loss_avg": 0.031191833876073362}
+{"step": 64620, "action_loss_avg": 0.0018209620233392344}
+{"step": 64630, "dynamics_loss_avg": 0.027073457092046737}
+{"step": 64630, "action_loss_avg": 0.001395594427594915}
+{"step": 64640, "dynamics_loss_avg": 0.02931965794414282}
+{"step": 64640, "action_loss_avg": 0.0020016318245325237}
+{"step": 64650, "loss": 0.0303, "learning_rate": 3.0448055283905587e-05}
+{"step": 64650, "dynamics_loss_avg": 0.027485771756619214}
+{"step": 64650, "action_loss_avg": 0.0014124196371994913}
+{"step": 64660, "dynamics_loss_avg": 0.031100064981728792}
+{"step": 64660, "action_loss_avg": 0.00157197795342654}
+{"step": 64670, "dynamics_loss_avg": 0.022793265338987113}
+{"step": 64670, "action_loss_avg": 0.0009689809099654667}
+{"step": 64680, "dynamics_loss_avg": 0.028164761094376444}
+{"step": 64680, "action_loss_avg": 0.0014309804741060362}
+{"step": 64690, "dynamics_loss_avg": 0.029608349408954383}
+{"step": 64690, "action_loss_avg": 0.0011509240604937077}
+{"step": 64700, "loss": 0.0285, "learning_rate": 3.0371991501491683e-05}
+{"step": 64700, "dynamics_loss_avg": 0.028989903070032595}
+{"step": 64700, "action_loss_avg": 0.0019325027969898656}
+{"step": 64710, "dynamics_loss_avg": 0.02487025116570294}
+{"step": 64710, "action_loss_avg": 0.0013803803070914001}
+{"step": 64720, "dynamics_loss_avg": 0.03325054822489619}
+{"step": 64720, "action_loss_avg": 0.001955678767990321}
+{"step": 64730, "dynamics_loss_avg": 0.024194336123764516}
+{"step": 64730, "action_loss_avg": 0.0009994670108426362}
+{"step": 64740, "dynamics_loss_avg": 0.030098317097872494}
+{"step": 64740, "action_loss_avg": 0.0016651647223625333}
+{"step": 64750, "loss": 0.0308, "learning_rate": 3.0295981381303513e-05}
+{"step": 64750, "dynamics_loss_avg": 0.034647677466273306}
+{"step": 64750, "action_loss_avg": 0.001288932008901611}
+{"step": 64760, "dynamics_loss_avg": 0.03570907758548856}
+{"step": 64760, "action_loss_avg": 0.0022298689116723837}
+{"step": 64770, "dynamics_loss_avg": 0.02924614860676229}
+{"step": 64770, "action_loss_avg": 0.0012762583617586642}
+{"step": 64780, "dynamics_loss_avg": 0.03209271859377623}
+{"step": 64780, "action_loss_avg": 0.0012656976614380255}
+{"step": 64790, "dynamics_loss_avg": 0.025146153382956983}
+{"step": 64790, "action_loss_avg": 0.0011705696757417171}
+{"step": 64800, "loss": 0.0319, "learning_rate": 3.0220025131149842e-05}
+{"step": 64800, "dynamics_loss_avg": 0.03505754880607128}
+{"step": 64800, "action_loss_avg": 0.001955764484591782}
+{"step": 64810, "dynamics_loss_avg": 0.02270778752863407}
+{"step": 64810, "action_loss_avg": 0.0009808796690776943}
+{"step": 64820, "dynamics_loss_avg": 0.02392775667831302}
+{"step": 64820, "action_loss_avg": 0.0008638464438263327}
+{"step": 64830, "dynamics_loss_avg": 0.03245663708075881}
+{"step": 64830, "action_loss_avg": 0.0017137411574367433}
+{"step": 64840, "dynamics_loss_avg": 0.03755960101261735}
+{"step": 64840, "action_loss_avg": 0.0022169125324580817}
+{"step": 64850, "loss": 0.0305, "learning_rate": 3.014412295869218e-05}
+{"step": 64850, "dynamics_loss_avg": 0.029616529494524}
+{"step": 64850, "action_loss_avg": 0.001563660058309324}
+{"step": 64860, "dynamics_loss_avg": 0.029108127905055882}
+{"step": 64860, "action_loss_avg": 0.0012086827278835698}
+{"step": 64870, "dynamics_loss_avg": 0.03314528055489063}
+{"step": 64870, "action_loss_avg": 0.0012416107128956355}
+{"step": 64880, "dynamics_loss_avg": 0.02505848594009876}
+{"step": 64880, "action_loss_avg": 0.0013573773030657321}
+{"step": 64890, "dynamics_loss_avg": 0.024295058008283375}
+{"step": 64890, "action_loss_avg": 0.000990591719164513}
+{"step": 64900, "loss": 0.0297, "learning_rate": 3.0068275071444142e-05}
+{"step": 64900, "dynamics_loss_avg": 0.026219492964446544}
+{"step": 64900, "action_loss_avg": 0.0009413450170541182}
+{"step": 64910, "dynamics_loss_avg": 0.03275765059515834}
+{"step": 64910, "action_loss_avg": 0.0017514139181002975}
+{"step": 64920, "dynamics_loss_avg": 0.029921863274648786}
+{"step": 64920, "action_loss_avg": 0.0013218733860412613}
+{"step": 64930, "dynamics_loss_avg": 0.03111871308647096}
+{"step": 64930, "action_loss_avg": 0.0013343499507755042}
+{"step": 64940, "dynamics_loss_avg": 0.03207941977307201}
+{"step": 64940, "action_loss_avg": 0.0018410336371744052}
+{"step": 64950, "loss": 0.0285, "learning_rate": 2.999248167677098e-05}
+{"step": 64950, "dynamics_loss_avg": 0.02820335770957172}
+{"step": 64950, "action_loss_avg": 0.001164365650038235}
+{"step": 64960, "dynamics_loss_avg": 0.02538209902122617}
+{"step": 64960, "action_loss_avg": 0.001006844756193459}
+{"step": 64970, "dynamics_loss_avg": 0.030162698589265347}
+{"step": 64970, "action_loss_avg": 0.0013956269074697047}
+{"step": 64980, "dynamics_loss_avg": 0.028323454782366753}
+{"step": 64980, "action_loss_avg": 0.0012540446943603456}
+{"step": 64990, "dynamics_loss_avg": 0.03990807384252548}
+{"step": 64990, "action_loss_avg": 0.001749521493911743}
+{"step": 65000, "loss": 0.0298, "learning_rate": 2.9916742981888923e-05}
+{"step": 65000, "dynamics_loss_avg": 0.02094311024993658}
+{"step": 65000, "action_loss_avg": 0.0011483469133963808}
+{"step": 65010, "dynamics_loss_avg": 0.0339972585439682}
+{"step": 65010, "action_loss_avg": 0.001422103022923693}
+{"step": 65020, "dynamics_loss_avg": 0.03644166486337781}
+{"step": 65020, "action_loss_avg": 0.0014659791835583747}
+{"step": 65030, "dynamics_loss_avg": 0.03676259852945805}
+{"step": 65030, "action_loss_avg": 0.0015411399770528078}
+{"step": 65040, "dynamics_loss_avg": 0.028149144910275935}
+{"step": 65040, "action_loss_avg": 0.001155856683908496}
+{"step": 65050, "loss": 0.0302, "learning_rate": 2.9841059193864672e-05}
+{"step": 65050, "dynamics_loss_avg": 0.02999561307951808}
+{"step": 65050, "action_loss_avg": 0.0014732334573636762}
+{"step": 65060, "dynamics_loss_avg": 0.02305458690971136}
+{"step": 65060, "action_loss_avg": 0.0010724020045017823}
+{"step": 65070, "dynamics_loss_avg": 0.033798841293901205}
+{"step": 65070, "action_loss_avg": 0.0016042612813180312}
+{"step": 65080, "dynamics_loss_avg": 0.03128735665231943}
+{"step": 65080, "action_loss_avg": 0.0015466471784748137}
+{"step": 65090, "dynamics_loss_avg": 0.02909184470772743}
+{"step": 65090, "action_loss_avg": 0.001486409266362898}
+{"step": 65100, "loss": 0.031, "learning_rate": 2.9765430519614825e-05}
+{"step": 65100, "dynamics_loss_avg": 0.034248859900981185}
+{"step": 65100, "action_loss_avg": 0.0015123172575840726}
+{"step": 65110, "dynamics_loss_avg": 0.024908557557500897}
+{"step": 65110, "action_loss_avg": 0.0012331320875091478}
+{"step": 65120, "dynamics_loss_avg": 0.02750890739262104}
+{"step": 65120, "action_loss_avg": 0.0011471027333755045}
+{"step": 65130, "dynamics_loss_avg": 0.03470193785615265}
+{"step": 65130, "action_loss_avg": 0.0011349352760589681}
+{"step": 65140, "dynamics_loss_avg": 0.02485813805833459}
+{"step": 65140, "action_loss_avg": 0.0011016914562787861}
+{"step": 65150, "loss": 0.028, "learning_rate": 2.968985716590527e-05}
+{"step": 65150, "dynamics_loss_avg": 0.022131905984133483}
+{"step": 65150, "action_loss_avg": 0.001247519410389941}
+{"step": 65160, "dynamics_loss_avg": 0.02720554107800126}
+{"step": 65160, "action_loss_avg": 0.0014976535661844538}
+{"step": 65170, "dynamics_loss_avg": 0.02867143526673317}
+{"step": 65170, "action_loss_avg": 0.0012843338277889415}
+{"step": 65180, "dynamics_loss_avg": 0.02849015351384878}
+{"step": 65180, "action_loss_avg": 0.0013381791824940592}
+{"step": 65190, "dynamics_loss_avg": 0.03157532960176468}
+{"step": 65190, "action_loss_avg": 0.0012786974519258365}
+{"step": 65200, "loss": 0.0275, "learning_rate": 2.9614339339350698e-05}
+{"step": 65200, "dynamics_loss_avg": 0.022747704200446604}
+{"step": 65200, "action_loss_avg": 0.0010674250370357186}
+{"step": 65210, "dynamics_loss_avg": 0.024890469294041394}
+{"step": 65210, "action_loss_avg": 0.0009952104301191866}
+{"step": 65220, "dynamics_loss_avg": 0.03422248661518097}
+{"step": 65220, "action_loss_avg": 0.0014448994013946503}
+{"step": 65230, "dynamics_loss_avg": 0.025423013884574176}
+{"step": 65230, "action_loss_avg": 0.0010110187431564555}
+{"step": 65240, "dynamics_loss_avg": 0.025645343214273454}
+{"step": 65240, "action_loss_avg": 0.0010888795222854242}
+{"step": 65250, "loss": 0.0288, "learning_rate": 2.9538877246413943e-05}
+{"step": 65250, "dynamics_loss_avg": 0.020282761473208667}
+{"step": 65250, "action_loss_avg": 0.0007952150277560577}
+{"step": 65260, "dynamics_loss_avg": 0.03289675936102867}
+{"step": 65260, "action_loss_avg": 0.001763623207807541}
+{"step": 65270, "dynamics_loss_avg": 0.03318257937207818}
+{"step": 65270, "action_loss_avg": 0.001899180538021028}
+{"step": 65280, "dynamics_loss_avg": 0.02542158905416727}
+{"step": 65280, "action_loss_avg": 0.0012727552559226752}
+{"step": 65290, "dynamics_loss_avg": 0.027166867256164552}
+{"step": 65290, "action_loss_avg": 0.0010448858054587617}
+{"step": 65300, "loss": 0.0283, "learning_rate": 2.946347109340548e-05}
+{"step": 65300, "dynamics_loss_avg": 0.021022907737642527}
+{"step": 65300, "action_loss_avg": 0.0014212700538337232}
+{"step": 65310, "dynamics_loss_avg": 0.019210361363366246}
+{"step": 65310, "action_loss_avg": 0.0009232792042894288}
+{"step": 65320, "dynamics_loss_avg": 0.02346145352348685}
+{"step": 65320, "action_loss_avg": 0.0012341510242549702}
+{"step": 65330, "dynamics_loss_avg": 0.025347385415807368}
+{"step": 65330, "action_loss_avg": 0.0008555088832508772}
+{"step": 65340, "dynamics_loss_avg": 0.02918373220600188}
+{"step": 65340, "action_loss_avg": 0.0016046606877353042}
+{"step": 65350, "loss": 0.0274, "learning_rate": 2.938812108648287e-05}
+{"step": 65350, "dynamics_loss_avg": 0.031252973899245265}
+{"step": 65350, "action_loss_avg": 0.0016683352150721475}
+{"step": 65360, "dynamics_loss_avg": 0.03568460186943412}
+{"step": 65360, "action_loss_avg": 0.0012853681982960552}
+{"step": 65370, "dynamics_loss_avg": 0.034129731450229885}
+{"step": 65370, "action_loss_avg": 0.0018012096115853637}
+{"step": 65380, "dynamics_loss_avg": 0.024783114530146123}
+{"step": 65380, "action_loss_avg": 0.0011521116364747285}
+{"step": 65390, "dynamics_loss_avg": 0.026166743226349355}
+{"step": 65390, "action_loss_avg": 0.0011101400828920304}
+{"step": 65400, "loss": 0.0294, "learning_rate": 2.9312827431650157e-05}
+{"step": 65400, "dynamics_loss_avg": 0.0283059598878026}
+{"step": 65400, "action_loss_avg": 0.001265738729853183}
+{"step": 65410, "dynamics_loss_avg": 0.03340251422487199}
+{"step": 65410, "action_loss_avg": 0.001934838695160579}
+{"step": 65420, "dynamics_loss_avg": 0.034978535305708644}
+{"step": 65420, "action_loss_avg": 0.0014882993418723345}
+{"step": 65430, "dynamics_loss_avg": 0.041753643471747634}
+{"step": 65430, "action_loss_avg": 0.001786100957542658}
+{"step": 65440, "dynamics_loss_avg": 0.02395862592384219}
+{"step": 65440, "action_loss_avg": 0.0008317025669384748}
+{"step": 65450, "loss": 0.0302, "learning_rate": 2.9237590334757292e-05}
+{"step": 65450, "dynamics_loss_avg": 0.02118831193074584}
+{"step": 65450, "action_loss_avg": 0.0009449741002754309}
+{"step": 65460, "dynamics_loss_avg": 0.036498404759913686}
+{"step": 65460, "action_loss_avg": 0.002259976684581488}
+{"step": 65470, "dynamics_loss_avg": 0.0241206050850451}
+{"step": 65470, "action_loss_avg": 0.0008650470903376117}
+{"step": 65480, "dynamics_loss_avg": 0.0341504879295826}
+{"step": 65480, "action_loss_avg": 0.0013200891145970673}
+{"step": 65490, "dynamics_loss_avg": 0.02969492841511965}
+{"step": 65490, "action_loss_avg": 0.0016599626309471206}
+{"step": 65500, "loss": 0.0305, "learning_rate": 2.916241000149964e-05}
+{"step": 65500, "dynamics_loss_avg": 0.029445001389831305}
+{"step": 65500, "action_loss_avg": 0.0016787320259027184}
+{"step": 65510, "dynamics_loss_avg": 0.03158349329605699}
+{"step": 65510, "action_loss_avg": 0.001427878430695273}
+{"step": 65520, "dynamics_loss_avg": 0.028349564876407385}
+{"step": 65520, "action_loss_avg": 0.0012243472214322538}
+{"step": 65530, "dynamics_loss_avg": 0.018343349266797305}
+{"step": 65530, "action_loss_avg": 0.0009028864078572951}
+{"step": 65540, "dynamics_loss_avg": 0.027023493219166993}
+{"step": 65540, "action_loss_avg": 0.0011464198236353696}
+{"step": 65550, "loss": 0.0281, "learning_rate": 2.9087286637417375e-05}
+{"step": 65550, "dynamics_loss_avg": 0.03192722136154771}
+{"step": 65550, "action_loss_avg": 0.001133257188485004}
+{"step": 65560, "dynamics_loss_avg": 0.031983651127666234}
+{"step": 65560, "action_loss_avg": 0.001668651110958308}
+{"step": 65570, "dynamics_loss_avg": 0.025696854339912534}
+{"step": 65570, "action_loss_avg": 0.001353226648643613}
+{"step": 65580, "dynamics_loss_avg": 0.019149055308662354}
+{"step": 65580, "action_loss_avg": 0.0008921574641135521}
+{"step": 65590, "dynamics_loss_avg": 0.028401927091181278}
+{"step": 65590, "action_loss_avg": 0.0010786420083604754}
+{"step": 65600, "loss": 0.0285, "learning_rate": 2.901222044789488e-05}
+{"step": 65600, "dynamics_loss_avg": 0.021705638943240048}
+{"step": 65600, "action_loss_avg": 0.0008274793217424303}
+{"step": 65610, "dynamics_loss_avg": 0.02352679707109928}
+{"step": 65610, "action_loss_avg": 0.0009914585098158568}
+{"step": 65620, "dynamics_loss_avg": 0.021254987362772225}
+{"step": 65620, "action_loss_avg": 0.0012261223368113861}
+{"step": 65630, "dynamics_loss_avg": 0.027493930608034133}
+{"step": 65630, "action_loss_avg": 0.0010235630674287678}
+{"step": 65640, "dynamics_loss_avg": 0.02848691400140524}
+{"step": 65640, "action_loss_avg": 0.0011525389185408131}
+{"step": 65650, "loss": 0.0257, "learning_rate": 2.89372116381603e-05}
+{"step": 65650, "dynamics_loss_avg": 0.02665525018237531}
+{"step": 65650, "action_loss_avg": 0.0013347885222174227}
+{"step": 65660, "dynamics_loss_avg": 0.025047601386904716}
+{"step": 65660, "action_loss_avg": 0.0012683636188739911}
+{"step": 65670, "dynamics_loss_avg": 0.01698845732025802}
+{"step": 65670, "action_loss_avg": 0.0007261444843607023}
+{"step": 65680, "dynamics_loss_avg": 0.025426238728687166}
+{"step": 65680, "action_loss_avg": 0.0012381623600958847}
+{"step": 65690, "dynamics_loss_avg": 0.03279756819829345}
+{"step": 65690, "action_loss_avg": 0.001195573335280642}
+{"step": 65700, "loss": 0.0269, "learning_rate": 2.886226041328478e-05}
+{"step": 65700, "dynamics_loss_avg": 0.03231332115828991}
+{"step": 65700, "action_loss_avg": 0.0018372013932093979}
+{"step": 65710, "dynamics_loss_avg": 0.03581587197259069}
+{"step": 65710, "action_loss_avg": 0.002191566617693752}
+{"step": 65720, "dynamics_loss_avg": 0.02200239188969135}
+{"step": 65720, "action_loss_avg": 0.001024671972845681}
+{"step": 65730, "dynamics_loss_avg": 0.03070436678826809}
+{"step": 65730, "action_loss_avg": 0.0012923844362376258}
+{"step": 65740, "dynamics_loss_avg": 0.022762519679963587}
+{"step": 65740, "action_loss_avg": 0.00106158000708092}
+{"step": 65750, "loss": 0.029, "learning_rate": 2.878736697818215e-05}
+{"step": 65750, "dynamics_loss_avg": 0.022776189865544437}
+{"step": 65750, "action_loss_avg": 0.0012436574761522934}
+{"step": 65760, "dynamics_loss_avg": 0.031044657342135906}
+{"step": 65760, "action_loss_avg": 0.0011596410651691258}
+{"step": 65770, "dynamics_loss_avg": 0.023446491500362755}
+{"step": 65770, "action_loss_avg": 0.0010227159917121753}
+{"step": 65780, "dynamics_loss_avg": 0.031024166429415346}
+{"step": 65780, "action_loss_avg": 0.0015876593824941665}
+{"step": 65790, "dynamics_loss_avg": 0.03794445544481277}
+{"step": 65790, "action_loss_avg": 0.0018391443241853266}
+{"step": 65800, "loss": 0.0298, "learning_rate": 2.8712531537608218e-05}
+{"step": 65800, "dynamics_loss_avg": 0.025711323786526918}
+{"step": 65800, "action_loss_avg": 0.0012259498151252046}
+{"step": 65810, "dynamics_loss_avg": 0.02708439202979207}
+{"step": 65810, "action_loss_avg": 0.0010592113743769006}
+{"step": 65820, "dynamics_loss_avg": 0.03372596465051174}
+{"step": 65820, "action_loss_avg": 0.0016958678170340136}
+{"step": 65830, "dynamics_loss_avg": 0.025881043542176484}
+{"step": 65830, "action_loss_avg": 0.0012633251724764704}
+{"step": 65840, "dynamics_loss_avg": 0.04377989750355482}
+{"step": 65840, "action_loss_avg": 0.002001788385678083}
+{"step": 65850, "loss": 0.0333, "learning_rate": 2.863775429616018e-05}
+{"step": 65850, "dynamics_loss_avg": 0.034166273381561044}
+{"step": 65850, "action_loss_avg": 0.001611857459647581}
+{"step": 65860, "dynamics_loss_avg": 0.030663990508764984}
+{"step": 65860, "action_loss_avg": 0.00125102304155007}
+{"step": 65870, "dynamics_loss_avg": 0.02852913402020931}
+{"step": 65870, "action_loss_avg": 0.0009163705515675246}
+{"step": 65880, "dynamics_loss_avg": 0.029450125247240066}
+{"step": 65880, "action_loss_avg": 0.001726880925707519}
+{"step": 65890, "dynamics_loss_avg": 0.037713033799082044}
+{"step": 65890, "action_loss_avg": 0.0014965262787882238}
+{"step": 65900, "loss": 0.0309, "learning_rate": 2.8563035458276222e-05}
+{"step": 65900, "dynamics_loss_avg": 0.03526647575199604}
+{"step": 65900, "action_loss_avg": 0.0018887851329054683}
+{"step": 65910, "dynamics_loss_avg": 0.034234956838190556}
+{"step": 65910, "action_loss_avg": 0.0012725665932521225}
+{"step": 65920, "dynamics_loss_avg": 0.026772924745455385}
+{"step": 65920, "action_loss_avg": 0.0012010489328531549}
+{"step": 65930, "dynamics_loss_avg": 0.03226587921380997}
+{"step": 65930, "action_loss_avg": 0.0014977656886912883}
+{"step": 65940, "dynamics_loss_avg": 0.02677887799218297}
+{"step": 65940, "action_loss_avg": 0.0009491557924775407}
+{"step": 65950, "loss": 0.0326, "learning_rate": 2.8488375228234716e-05}
+{"step": 65950, "dynamics_loss_avg": 0.04193358663469553}
+{"step": 65950, "action_loss_avg": 0.0017686793056782336}
+{"step": 65960, "dynamics_loss_avg": 0.029393830336630344}
+{"step": 65960, "action_loss_avg": 0.0012029686331516132}
+{"step": 65970, "dynamics_loss_avg": 0.024573940224945544}
+{"step": 65970, "action_loss_avg": 0.0011791991360951214}
+{"step": 65980, "dynamics_loss_avg": 0.019169805524870753}
+{"step": 65980, "action_loss_avg": 0.001039116560423281}
+{"step": 65990, "dynamics_loss_avg": 0.016604400379583238}
+{"step": 65990, "action_loss_avg": 0.0006933816737728193}
+{"step": 66000, "loss": 0.0258, "learning_rate": 2.841377381015391e-05}
+{"step": 66000, "dynamics_loss_avg": 0.026080067083239556}
+{"step": 66000, "action_loss_avg": 0.0016152152442373336}
+{"step": 66010, "dynamics_loss_avg": 0.025215699523687362}
+{"step": 66010, "action_loss_avg": 0.0011651999229798093}
+{"step": 66020, "dynamics_loss_avg": 0.026518783159554006}
+{"step": 66020, "action_loss_avg": 0.0015546851471299305}
+{"step": 66030, "dynamics_loss_avg": 0.03315418567508459}
+{"step": 66030, "action_loss_avg": 0.0014202350605046377}
+{"step": 66040, "dynamics_loss_avg": 0.03944284413009882}
+{"step": 66040, "action_loss_avg": 0.0022205764224054294}
+{"step": 66050, "loss": 0.031, "learning_rate": 2.8339231407991267e-05}
+{"step": 66050, "dynamics_loss_avg": 0.023638613522052765}
+{"step": 66050, "action_loss_avg": 0.001059153798269108}
+{"step": 66060, "dynamics_loss_avg": 0.01470903092995286}
+{"step": 66060, "action_loss_avg": 0.0007199422107078135}
+{"step": 66070, "dynamics_loss_avg": 0.02450362965464592}
+{"step": 66070, "action_loss_avg": 0.0011089229985373095}
+{"step": 66080, "dynamics_loss_avg": 0.02900947080925107}
+{"step": 66080, "action_loss_avg": 0.0010336639825254679}
+{"step": 66090, "dynamics_loss_avg": 0.029515213798731565}
+{"step": 66090, "action_loss_avg": 0.0012227249884745107}
+{"step": 66100, "loss": 0.0289, "learning_rate": 2.8264748225542836e-05}
+{"step": 66100, "dynamics_loss_avg": 0.03276780266314745}
+{"step": 66100, "action_loss_avg": 0.0014646787341916934}
+{"step": 66110, "dynamics_loss_avg": 0.03880361020565033}
+{"step": 66110, "action_loss_avg": 0.0020482109626755118}
+{"step": 66120, "dynamics_loss_avg": 0.02910106987692416}
+{"step": 66120, "action_loss_avg": 0.0009664522600360215}
+{"step": 66130, "dynamics_loss_avg": 0.02758113727904856}
+{"step": 66130, "action_loss_avg": 0.001321095461025834}
+{"step": 66140, "dynamics_loss_avg": 0.02760054760146886}
+{"step": 66140, "action_loss_avg": 0.0011140584538225085}
+{"step": 66150, "loss": 0.0287, "learning_rate": 2.8190324466442798e-05}
+{"step": 66150, "dynamics_loss_avg": 0.0199899063911289}
+{"step": 66150, "action_loss_avg": 0.0011327978339977563}
+{"step": 66160, "dynamics_loss_avg": 0.027791925985366107}
+{"step": 66160, "action_loss_avg": 0.001349439940531738}
+{"step": 66170, "dynamics_loss_avg": 0.02258022502064705}
+{"step": 66170, "action_loss_avg": 0.0011734492669347673}
+{"step": 66180, "dynamics_loss_avg": 0.031867175456136466}
+{"step": 66180, "action_loss_avg": 0.001427179016172886}
+{"step": 66190, "dynamics_loss_avg": 0.037533617671579124}
+{"step": 66190, "action_loss_avg": 0.00188873419247102}
+{"step": 66200, "loss": 0.0304, "learning_rate": 2.811596033416285e-05}
+{"step": 66200, "dynamics_loss_avg": 0.028051491361111403}
+{"step": 66200, "action_loss_avg": 0.0010864427487831563}
+{"step": 66210, "dynamics_loss_avg": 0.026443900633603336}
+{"step": 66210, "action_loss_avg": 0.0011017140262993053}
+{"step": 66220, "dynamics_loss_avg": 0.026951985713094474}
+{"step": 66220, "action_loss_avg": 0.0009879844030365348}
+{"step": 66230, "dynamics_loss_avg": 0.040937957167625424}
+{"step": 66230, "action_loss_avg": 0.0018988773343153297}
+{"step": 66240, "dynamics_loss_avg": 0.03478482244536281}
+{"step": 66240, "action_loss_avg": 0.0016206960950512438}
+{"step": 66250, "loss": 0.0297, "learning_rate": 2.804165603201171e-05}
+{"step": 66250, "dynamics_loss_avg": 0.023998981714248656}
+{"step": 66250, "action_loss_avg": 0.0012237934686709195}
+{"step": 66260, "dynamics_loss_avg": 0.03532676259055734}
+{"step": 66260, "action_loss_avg": 0.0018421684333588928}
+{"step": 66270, "dynamics_loss_avg": 0.027137229032814503}
+{"step": 66270, "action_loss_avg": 0.001290659507503733}
+{"step": 66280, "dynamics_loss_avg": 0.02528966683894396}
+{"step": 66280, "action_loss_avg": 0.0011544944456545636}
+{"step": 66290, "dynamics_loss_avg": 0.035482986364513636}
+{"step": 66290, "action_loss_avg": 0.0017790714307921007}
+{"step": 66300, "loss": 0.0306, "learning_rate": 2.7967411763134516e-05}
+{"step": 66300, "dynamics_loss_avg": 0.03052774085663259}
+{"step": 66300, "action_loss_avg": 0.001545808685477823}
+{"step": 66310, "dynamics_loss_avg": 0.03361808145418763}
+{"step": 66310, "action_loss_avg": 0.0015046632732264697}
+{"step": 66320, "dynamics_loss_avg": 0.024736514035612344}
+{"step": 66320, "action_loss_avg": 0.001359369669808075}
+{"step": 66330, "dynamics_loss_avg": 0.033601387729868294}
+{"step": 66330, "action_loss_avg": 0.0014990602081525139}
+{"step": 66340, "dynamics_loss_avg": 0.028292385023087264}
+{"step": 66340, "action_loss_avg": 0.0011464467635960319}
+{"step": 66350, "loss": 0.0325, "learning_rate": 2.789322773051225e-05}
+{"step": 66350, "dynamics_loss_avg": 0.030407537147402762}
+{"step": 66350, "action_loss_avg": 0.0012054632883518935}
+{"step": 66360, "dynamics_loss_avg": 0.022757988888770342}
+{"step": 66360, "action_loss_avg": 0.0010448966349940747}
+{"step": 66370, "dynamics_loss_avg": 0.030167419742792845}
+{"step": 66370, "action_loss_avg": 0.0012275948247406632}
+{"step": 66380, "dynamics_loss_avg": 0.021482340106740595}
+{"step": 66380, "action_loss_avg": 0.0008238974900450557}
+{"step": 66390, "dynamics_loss_avg": 0.028596276044845582}
+{"step": 66390, "action_loss_avg": 0.0016402865789132194}
+{"step": 66400, "loss": 0.0255, "learning_rate": 2.7819104136961226e-05}
+{"step": 66400, "dynamics_loss_avg": 0.02157341125421226}
+{"step": 66400, "action_loss_avg": 0.001098478191124741}
+{"step": 66410, "dynamics_loss_avg": 0.03924655793234706}
+{"step": 66410, "action_loss_avg": 0.0019453993620118127}
+{"step": 66420, "dynamics_loss_avg": 0.02826182935386896}
+{"step": 66420, "action_loss_avg": 0.0009003562445286661}
+{"step": 66430, "dynamics_loss_avg": 0.02473961878567934}
+{"step": 66430, "action_loss_avg": 0.0010471562738530338}
+{"step": 66440, "dynamics_loss_avg": 0.026722380705177785}
+{"step": 66440, "action_loss_avg": 0.0012480967241572216}
+{"step": 66450, "loss": 0.0285, "learning_rate": 2.7745041185132496e-05}
+{"step": 66450, "dynamics_loss_avg": 0.02304502809420228}
+{"step": 66450, "action_loss_avg": 0.0010138883226318285}
+{"step": 66460, "dynamics_loss_avg": 0.03221855154260993}
+{"step": 66460, "action_loss_avg": 0.0019183692988008262}
+{"step": 66470, "dynamics_loss_avg": 0.022628364199772478}
+{"step": 66470, "action_loss_avg": 0.0007342309865634889}
+{"step": 66480, "dynamics_loss_avg": 0.031858632899820806}
+{"step": 66480, "action_loss_avg": 0.001440947037190199}
+{"step": 66490, "dynamics_loss_avg": 0.030698190536350013}
+{"step": 66490, "action_loss_avg": 0.001373898598831147}
+{"step": 66500, "loss": 0.0299, "learning_rate": 2.767103907751136e-05}
+{"step": 66500, "dynamics_loss_avg": 0.02939535425975919}
+{"step": 66500, "action_loss_avg": 0.0012801524950191378}
+{"step": 66510, "dynamics_loss_avg": 0.024355355370789766}
+{"step": 66510, "action_loss_avg": 0.0009049618529388681}
+{"step": 66520, "dynamics_loss_avg": 0.02934954147785902}
+{"step": 66520, "action_loss_avg": 0.0013963530131150038}
+{"step": 66530, "dynamics_loss_avg": 0.029968538787215948}
+{"step": 66530, "action_loss_avg": 0.0014572293759556488}
+{"step": 66540, "dynamics_loss_avg": 0.033668773528188464}
+{"step": 66540, "action_loss_avg": 0.0009688300197012722}
+{"step": 66550, "loss": 0.03, "learning_rate": 2.7597098016416784e-05}
+{"step": 66550, "dynamics_loss_avg": 0.025797961931675672}
+{"step": 66550, "action_loss_avg": 0.0014306939992820844}
+{"step": 66560, "dynamics_loss_avg": 0.02439760658890009}
+{"step": 66560, "action_loss_avg": 0.001303588307928294}
+{"step": 66570, "dynamics_loss_avg": 0.027309941314160823}
+{"step": 66570, "action_loss_avg": 0.0009175170329399407}
+{"step": 66580, "dynamics_loss_avg": 0.025814053509384392}
+{"step": 66580, "action_loss_avg": 0.000985808936820831}
+{"step": 66590, "dynamics_loss_avg": 0.027694314438849687}
+{"step": 66590, "action_loss_avg": 0.001124935521511361}
+{"step": 66600, "loss": 0.0272, "learning_rate": 2.7523218204000774e-05}
+{"step": 66600, "dynamics_loss_avg": 0.02452089199796319}
+{"step": 66600, "action_loss_avg": 0.0014247522107325495}
+{"step": 66610, "dynamics_loss_avg": 0.026723816990852356}
+{"step": 66610, "action_loss_avg": 0.001246690217521973}
+{"step": 66620, "dynamics_loss_avg": 0.03366005830466747}
+{"step": 66620, "action_loss_avg": 0.0010789379623020068}
+{"step": 66630, "dynamics_loss_avg": 0.031750482693314555}
+{"step": 66630, "action_loss_avg": 0.0013085004349704832}
+{"step": 66640, "dynamics_loss_avg": 0.026270550768822433}
+{"step": 66640, "action_loss_avg": 0.0009675679117208347}
+{"step": 66650, "loss": 0.0313, "learning_rate": 2.7449399842247918e-05}
+{"step": 66650, "dynamics_loss_avg": 0.031110176560468973}
+{"step": 66650, "action_loss_avg": 0.001347817381611094}
+{"step": 66660, "dynamics_loss_avg": 0.03345677312463522}
+{"step": 66660, "action_loss_avg": 0.0010737966484157368}
+{"step": 66670, "dynamics_loss_avg": 0.030247958563268184}
+{"step": 66670, "action_loss_avg": 0.0014687549381051212}
+{"step": 66680, "dynamics_loss_avg": 0.028430299647152425}
+{"step": 66680, "action_loss_avg": 0.0015763909177621827}
+{"step": 66690, "dynamics_loss_avg": 0.03288066834211349}
+{"step": 66690, "action_loss_avg": 0.0015084403625223787}
+{"step": 66700, "loss": 0.0297, "learning_rate": 2.737564313297478e-05}
+{"step": 66700, "dynamics_loss_avg": 0.02082629278302193}
+{"step": 66700, "action_loss_avg": 0.0009278206387534737}
+{"step": 66710, "dynamics_loss_avg": 0.026750026270747185}
+{"step": 66710, "action_loss_avg": 0.0009490098600508645}
+{"step": 66720, "dynamics_loss_avg": 0.02271829443052411}
+{"step": 66720, "action_loss_avg": 0.0011317153868731112}
+{"step": 66730, "dynamics_loss_avg": 0.030995633779093625}
+{"step": 66730, "action_loss_avg": 0.0012098208419047296}
+{"step": 66740, "dynamics_loss_avg": 0.0344526887871325}
+{"step": 66740, "action_loss_avg": 0.0012712656171061099}
+{"step": 66750, "loss": 0.0292, "learning_rate": 2.7301948277829414e-05}
+{"step": 66750, "dynamics_loss_avg": 0.03463828177191317}
+{"step": 66750, "action_loss_avg": 0.0015704585952335038}
+{"step": 66760, "dynamics_loss_avg": 0.02894455464556813}
+{"step": 66760, "action_loss_avg": 0.0015325814427342265}
+{"step": 66770, "dynamics_loss_avg": 0.03000008761882782}
+{"step": 66770, "action_loss_avg": 0.001355242908175569}
+{"step": 66780, "dynamics_loss_avg": 0.022600088780745865}
+{"step": 66780, "action_loss_avg": 0.0010607645963318646}
+{"step": 66790, "dynamics_loss_avg": 0.02894012164324522}
+{"step": 66790, "action_loss_avg": 0.0010477433912456035}
+{"step": 66800, "loss": 0.0279, "learning_rate": 2.7228315478290766e-05}
+{"step": 66800, "dynamics_loss_avg": 0.02749657053500414}
+{"step": 66800, "action_loss_avg": 0.0012938298808876426}
+{"step": 66810, "dynamics_loss_avg": 0.027308512199670076}
+{"step": 66810, "action_loss_avg": 0.0013027342909481376}
+{"step": 66820, "dynamics_loss_avg": 0.02960516745224595}
+{"step": 66820, "action_loss_avg": 0.0014031342638190837}
+{"step": 66830, "dynamics_loss_avg": 0.030883809458464383}
+{"step": 66830, "action_loss_avg": 0.0009298824035795406}
+{"step": 66840, "dynamics_loss_avg": 0.029501018207520248}
+{"step": 66840, "action_loss_avg": 0.001394209181307815}
+{"step": 66850, "loss": 0.0298, "learning_rate": 2.715474493566803e-05}
+{"step": 66850, "dynamics_loss_avg": 0.033342469856142996}
+{"step": 66850, "action_loss_avg": 0.0013429231621557847}
+{"step": 66860, "dynamics_loss_avg": 0.02016780951526016}
+{"step": 66860, "action_loss_avg": 0.0012349763659585734}
+{"step": 66870, "dynamics_loss_avg": 0.023007105570286512}
+{"step": 66870, "action_loss_avg": 0.0012094578996766359}
+{"step": 66880, "dynamics_loss_avg": 0.029715175088495017}
+{"step": 66880, "action_loss_avg": 0.001339922082843259}
+{"step": 66890, "dynamics_loss_avg": 0.029400558024644852}
+{"step": 66890, "action_loss_avg": 0.0008699645317392424}
+{"step": 66900, "loss": 0.0294, "learning_rate": 2.708123685110032e-05}
+{"step": 66900, "dynamics_loss_avg": 0.03219355586916208}
+{"step": 66900, "action_loss_avg": 0.0010595657222438604}
+{"step": 66910, "dynamics_loss_avg": 0.032080067228525876}
+{"step": 66910, "action_loss_avg": 0.0015026267094071955}
+{"step": 66920, "dynamics_loss_avg": 0.02343236645683646}
+{"step": 66920, "action_loss_avg": 0.0010924586473265662}
+{"step": 66930, "dynamics_loss_avg": 0.02747716475278139}
+{"step": 66930, "action_loss_avg": 0.0010158510034671054}
+{"step": 66940, "dynamics_loss_avg": 0.03409187477082014}
+{"step": 66940, "action_loss_avg": 0.0014191110094543546}
+{"step": 66950, "loss": 0.0287, "learning_rate": 2.7007791425555883e-05}
+{"step": 66950, "dynamics_loss_avg": 0.016834105737507342}
+{"step": 66950, "action_loss_avg": 0.0008336062950547784}
+{"step": 66960, "dynamics_loss_avg": 0.028110917750746013}
+{"step": 66960, "action_loss_avg": 0.0014438260986935347}
+{"step": 66970, "dynamics_loss_avg": 0.031059124693274497}
+{"step": 66970, "action_loss_avg": 0.001411547843599692}
+{"step": 66980, "dynamics_loss_avg": 0.02337378179654479}
+{"step": 66980, "action_loss_avg": 0.001122542063239962}
+{"step": 66990, "dynamics_loss_avg": 0.02884259526617825}
+{"step": 66990, "action_loss_avg": 0.001048202029778622}
+{"step": 67000, "loss": 0.029, "learning_rate": 2.6934408859831733e-05}
+{"step": 67000, "dynamics_loss_avg": 0.03312842193990946}
+{"step": 67000, "action_loss_avg": 0.0016714931407477707}
+{"step": 67010, "dynamics_loss_avg": 0.01920552453957498}
+{"step": 67010, "action_loss_avg": 0.00080563554802211}
+{"step": 67020, "dynamics_loss_avg": 0.029500495176762342}
+{"step": 67020, "action_loss_avg": 0.0011810631869593636}
+{"step": 67030, "dynamics_loss_avg": 0.02195857623592019}
+{"step": 67030, "action_loss_avg": 0.001251692045480013}
+{"step": 67040, "dynamics_loss_avg": 0.028754261089488864}
+{"step": 67040, "action_loss_avg": 0.001339455266133882}
+{"step": 67050, "loss": 0.029, "learning_rate": 2.686108935455305e-05}
+{"step": 67050, "dynamics_loss_avg": 0.028987680096179247}
+{"step": 67050, "action_loss_avg": 0.0014414638513699173}
+{"step": 67060, "dynamics_loss_avg": 0.027336196787655354}
+{"step": 67060, "action_loss_avg": 0.0014523111371090637}
+{"step": 67070, "dynamics_loss_avg": 0.022543533332645894}
+{"step": 67070, "action_loss_avg": 0.0011977454727457371}
+{"step": 67080, "dynamics_loss_avg": 0.02654254073277116}
+{"step": 67080, "action_loss_avg": 0.0009723965195007622}
+{"step": 67090, "dynamics_loss_avg": 0.03508897079154849}
+{"step": 67090, "action_loss_avg": 0.001558429776923731}
+{"step": 67100, "loss": 0.0282, "learning_rate": 2.6787833110172466e-05}
+{"step": 67100, "dynamics_loss_avg": 0.02537615243345499}
+{"step": 67100, "action_loss_avg": 0.0013430486375000327}
+{"step": 67110, "dynamics_loss_avg": 0.019978851545602083}
+{"step": 67110, "action_loss_avg": 0.0009218577441060915}
+{"step": 67120, "dynamics_loss_avg": 0.023505748296156526}
+{"step": 67120, "action_loss_avg": 0.0009188043681206181}
+{"step": 67130, "dynamics_loss_avg": 0.02743958365172148}
+{"step": 67130, "action_loss_avg": 0.0010668668473954313}
+{"step": 67140, "dynamics_loss_avg": 0.031391206197440624}
+{"step": 67140, "action_loss_avg": 0.00138833518140018}
+{"step": 67150, "loss": 0.0269, "learning_rate": 2.671464032696982e-05}
+{"step": 67150, "dynamics_loss_avg": 0.028277206467464566}
+{"step": 67150, "action_loss_avg": 0.0013028085289988668}
+{"step": 67160, "dynamics_loss_avg": 0.030995888262987138}
+{"step": 67160, "action_loss_avg": 0.0014103973633609712}
+{"step": 67170, "dynamics_loss_avg": 0.025461259856820108}
+{"step": 67170, "action_loss_avg": 0.0011178116074006539}
+{"step": 67180, "dynamics_loss_avg": 0.02630165982991457}
+{"step": 67180, "action_loss_avg": 0.0013931803143350408}
+{"step": 67190, "dynamics_loss_avg": 0.02816625079140067}
+{"step": 67190, "action_loss_avg": 0.0010565631178906187}
+{"step": 67200, "loss": 0.0277, "learning_rate": 2.664151120505136e-05}
+{"step": 67200, "dynamics_loss_avg": 0.02952037686482072}
+{"step": 67200, "action_loss_avg": 0.0013652901980094612}
+{"step": 67210, "dynamics_loss_avg": 0.03178924019448459}
+{"step": 67210, "action_loss_avg": 0.001520268467720598}
+{"step": 67220, "dynamics_loss_avg": 0.02561878077685833}
+{"step": 67220, "action_loss_avg": 0.0009176871710224078}
+{"step": 67230, "dynamics_loss_avg": 0.02462913254275918}
+{"step": 67230, "action_loss_avg": 0.0009704654628876596}
+{"step": 67240, "dynamics_loss_avg": 0.021405382826924325}
+{"step": 67240, "action_loss_avg": 0.0007361698430031538}
+{"step": 67250, "loss": 0.0295, "learning_rate": 2.6568445944349323e-05}
+{"step": 67250, "dynamics_loss_avg": 0.03010819396004081}
+{"step": 67250, "action_loss_avg": 0.0015559470863081514}
+{"step": 67260, "dynamics_loss_avg": 0.021423301286995412}
+{"step": 67260, "action_loss_avg": 0.0010124604916200042}
+{"step": 67270, "dynamics_loss_avg": 0.029957647901028395}
+{"step": 67270, "action_loss_avg": 0.0013798734114971011}
+{"step": 67280, "dynamics_loss_avg": 0.046505543310195206}
+{"step": 67280, "action_loss_avg": 0.0019761007162742315}
+{"step": 67290, "dynamics_loss_avg": 0.02873028293251991}
+{"step": 67290, "action_loss_avg": 0.0013224015216110273}
+{"step": 67300, "loss": 0.0306, "learning_rate": 2.649544474462138e-05}
+{"step": 67300, "dynamics_loss_avg": 0.026458082254976034}
+{"step": 67300, "action_loss_avg": 0.0009415746171725914}
+{"step": 67310, "dynamics_loss_avg": 0.0328955446369946}
+{"step": 67310, "action_loss_avg": 0.0014150811824947596}
+{"step": 67320, "dynamics_loss_avg": 0.027737650857307016}
+{"step": 67320, "action_loss_avg": 0.0013522498338716105}
+{"step": 67330, "dynamics_loss_avg": 0.03061296548694372}
+{"step": 67330, "action_loss_avg": 0.0011797788480180315}
+{"step": 67340, "dynamics_loss_avg": 0.014143834728747607}
+{"step": 67340, "action_loss_avg": 0.0008724103652639314}
+{"step": 67350, "loss": 0.0286, "learning_rate": 2.6422507805449947e-05}
+{"step": 67350, "dynamics_loss_avg": 0.030767181981354953}
+{"step": 67350, "action_loss_avg": 0.001246902230195701}
+{"step": 67360, "dynamics_loss_avg": 0.02468674350529909}
+{"step": 67360, "action_loss_avg": 0.001380062149837613}
+{"step": 67370, "dynamics_loss_avg": 0.023026096168905497}
+{"step": 67370, "action_loss_avg": 0.0010555159911746158}
+{"step": 67380, "dynamics_loss_avg": 0.01811779337003827}
+{"step": 67380, "action_loss_avg": 0.0007878522475948558}
+{"step": 67390, "dynamics_loss_avg": 0.03371017947793007}
+{"step": 67390, "action_loss_avg": 0.001462048094253987}
+{"step": 67400, "loss": 0.0276, "learning_rate": 2.6349635326241894e-05}
+{"step": 67400, "dynamics_loss_avg": 0.03705800846219063}
+{"step": 67400, "action_loss_avg": 0.0014884076837915928}
+{"step": 67410, "dynamics_loss_avg": 0.02839118093252182}
+{"step": 67410, "action_loss_avg": 0.0012456789903808386}
+{"step": 67420, "dynamics_loss_avg": 0.02885439498350024}
+{"step": 67420, "action_loss_avg": 0.001431908385711722}
+{"step": 67430, "dynamics_loss_avg": 0.02720427680760622}
+{"step": 67430, "action_loss_avg": 0.0011861761988257058}
+{"step": 67440, "dynamics_loss_avg": 0.03951902026310563}
+{"step": 67440, "action_loss_avg": 0.0018200349411927163}
+{"step": 67450, "loss": 0.0304, "learning_rate": 2.6276827506227743e-05}
+{"step": 67450, "dynamics_loss_avg": 0.031097833812236787}
+{"step": 67450, "action_loss_avg": 0.001658067584503442}
+{"step": 67460, "dynamics_loss_avg": 0.019536374881863595}
+{"step": 67460, "action_loss_avg": 0.0013321795791853218}
+{"step": 67470, "dynamics_loss_avg": 0.026354043278843164}
+{"step": 67470, "action_loss_avg": 0.0010132173949386925}
+{"step": 67480, "dynamics_loss_avg": 0.01892312914133072}
+{"step": 67480, "action_loss_avg": 0.0008325605973368511}
+{"step": 67490, "dynamics_loss_avg": 0.03901507342234254}
+{"step": 67490, "action_loss_avg": 0.0014396292273886502}
+{"step": 67500, "loss": 0.0297, "learning_rate": 2.620408454446135e-05}
+{"step": 67500, "dynamics_loss_avg": 0.034207103028893474}
+{"step": 67500, "action_loss_avg": 0.0015329286034102552}
+{"step": 67510, "dynamics_loss_avg": 0.02607931522652507}
+{"step": 67510, "action_loss_avg": 0.0009860207879683002}
+{"step": 67520, "dynamics_loss_avg": 0.03435815554112196}
+{"step": 67520, "action_loss_avg": 0.0019004506844794377}
+{"step": 67530, "dynamics_loss_avg": 0.025465178955346345}
+{"step": 67530, "action_loss_avg": 0.0011455827654572204}
+{"step": 67540, "dynamics_loss_avg": 0.03263763622380793}
+{"step": 67540, "action_loss_avg": 0.0016733618424041197}
+{"step": 67550, "loss": 0.0301, "learning_rate": 2.6131406639819166e-05}
+{"step": 67550, "dynamics_loss_avg": 0.03216993100941181}
+{"step": 67550, "action_loss_avg": 0.0012911865313071757}
+{"step": 67560, "dynamics_loss_avg": 0.032790906634181737}
+{"step": 67560, "action_loss_avg": 0.00159111064276658}
+{"step": 67570, "dynamics_loss_avg": 0.03700967971235514}
+{"step": 67570, "action_loss_avg": 0.0012126830231864005}
+{"step": 67580, "dynamics_loss_avg": 0.02523590945638716}
+{"step": 67580, "action_loss_avg": 0.0013137812435161321}
+{"step": 67590, "dynamics_loss_avg": 0.023826364241540433}
+{"step": 67590, "action_loss_avg": 0.0012432702933438122}
+{"step": 67600, "loss": 0.0313, "learning_rate": 2.6058793990999786e-05}
+{"step": 67600, "dynamics_loss_avg": 0.024995993450284006}
+{"step": 67600, "action_loss_avg": 0.0010614982224069537}
+{"step": 67610, "dynamics_loss_avg": 0.02125373315066099}
+{"step": 67610, "action_loss_avg": 0.0009432701044715941}
+{"step": 67620, "dynamics_loss_avg": 0.02817353531718254}
+{"step": 67620, "action_loss_avg": 0.0013660207216162235}
+{"step": 67630, "dynamics_loss_avg": 0.0314128065481782}
+{"step": 67630, "action_loss_avg": 0.0013349954329896717}
+{"step": 67640, "dynamics_loss_avg": 0.026333916140720247}
+{"step": 67640, "action_loss_avg": 0.0008959871775005013}
+{"step": 67650, "loss": 0.0257, "learning_rate": 2.5986246796523462e-05}
+{"step": 67650, "dynamics_loss_avg": 0.020017935428768396}
+{"step": 67650, "action_loss_avg": 0.0008850742044160143}
+{"step": 67660, "dynamics_loss_avg": 0.03281267685815692}
+{"step": 67660, "action_loss_avg": 0.0015012650168500842}
+{"step": 67670, "dynamics_loss_avg": 0.03200163161382079}
+{"step": 67670, "action_loss_avg": 0.0019797079381532966}
+{"step": 67680, "dynamics_loss_avg": 0.024098029267042874}
+{"step": 67680, "action_loss_avg": 0.001202824545907788}
+{"step": 67690, "dynamics_loss_avg": 0.030142982443794607}
+{"step": 67690, "action_loss_avg": 0.001403707530698739}
+{"step": 67700, "loss": 0.0314, "learning_rate": 2.591376525473142e-05}
+{"step": 67700, "dynamics_loss_avg": 0.036369492672383784}
+{"step": 67700, "action_loss_avg": 0.0017152626300230623}
+{"step": 67710, "dynamics_loss_avg": 0.03636991530656815}
+{"step": 67710, "action_loss_avg": 0.0016920892288908363}
+{"step": 67720, "dynamics_loss_avg": 0.018137817457318305}
+{"step": 67720, "action_loss_avg": 0.001144329973612912}
+{"step": 67730, "dynamics_loss_avg": 0.030781253706663847}
+{"step": 67730, "action_loss_avg": 0.0009682153584435582}
+{"step": 67740, "dynamics_loss_avg": 0.031658233236521484}
+{"step": 67740, "action_loss_avg": 0.0014693450299091636}
+{"step": 67750, "loss": 0.0292, "learning_rate": 2.5841349563785455e-05}
+{"step": 67750, "dynamics_loss_avg": 0.033621396962553264}
+{"step": 67750, "action_loss_avg": 0.0010431916947709397}
+{"step": 67760, "dynamics_loss_avg": 0.02473538275808096}
+{"step": 67760, "action_loss_avg": 0.0010216321679763496}
+{"step": 67770, "dynamics_loss_avg": 0.026027074735611676}
+{"step": 67770, "action_loss_avg": 0.0015271040028892457}
+{"step": 67780, "dynamics_loss_avg": 0.02703398698940873}
+{"step": 67780, "action_loss_avg": 0.0010991932358592749}
+{"step": 67790, "dynamics_loss_avg": 0.025134943891316652}
+{"step": 67790, "action_loss_avg": 0.0011271452909568324}
+{"step": 67800, "loss": 0.0275, "learning_rate": 2.576899992166729e-05}
+{"step": 67800, "dynamics_loss_avg": 0.027486654557287694}
+{"step": 67800, "action_loss_avg": 0.002103759834426455}
+{"step": 67810, "dynamics_loss_avg": 0.03456647456623614}
+{"step": 67810, "action_loss_avg": 0.0011538429884240032}
+{"step": 67820, "dynamics_loss_avg": 0.024697084666695446}
+{"step": 67820, "action_loss_avg": 0.001086793706053868}
+{"step": 67830, "dynamics_loss_avg": 0.02463518539443612}
+{"step": 67830, "action_loss_avg": 0.0007719761779299006}
+{"step": 67840, "dynamics_loss_avg": 0.02937385318800807}
+{"step": 67840, "action_loss_avg": 0.0018686392679228448}
+{"step": 67850, "loss": 0.0277, "learning_rate": 2.5696716526178054e-05}
+{"step": 67850, "dynamics_loss_avg": 0.023526161443442106}
+{"step": 67850, "action_loss_avg": 0.0010517122631426901}
+{"step": 67860, "dynamics_loss_avg": 0.023378903698176145}
+{"step": 67860, "action_loss_avg": 0.0013699915551114827}
+{"step": 67870, "dynamics_loss_avg": 0.02354026837274432}
+{"step": 67870, "action_loss_avg": 0.00093250100617297}
+{"step": 67880, "dynamics_loss_avg": 0.027192789455875756}
+{"step": 67880, "action_loss_avg": 0.001309695973759517}
+{"step": 67890, "dynamics_loss_avg": 0.024411235097795726}
+{"step": 67890, "action_loss_avg": 0.0014240279037039728}
+{"step": 67900, "loss": 0.0273, "learning_rate": 2.5624499574937842e-05}
+{"step": 67900, "dynamics_loss_avg": 0.02810924663208425}
+{"step": 67900, "action_loss_avg": 0.0012711835064692424}
+{"step": 67910, "dynamics_loss_avg": 0.02468217834830284}
+{"step": 67910, "action_loss_avg": 0.0009858476347289979}
+{"step": 67920, "dynamics_loss_avg": 0.026452897116541862}
+{"step": 67920, "action_loss_avg": 0.001371380130876787}
+{"step": 67930, "dynamics_loss_avg": 0.025503705721348524}
+{"step": 67930, "action_loss_avg": 0.001284442312316969}
+{"step": 67940, "dynamics_loss_avg": 0.021715430822223426}
+{"step": 67940, "action_loss_avg": 0.000861716375220567}
+{"step": 67950, "loss": 0.0281, "learning_rate": 2.5552349265385e-05}
+{"step": 67950, "dynamics_loss_avg": 0.022355620842427017}
+{"step": 67950, "action_loss_avg": 0.0009740333654917777}
+{"step": 67960, "dynamics_loss_avg": 0.02939536152407527}
+{"step": 67960, "action_loss_avg": 0.0013409953622613101}
+{"step": 67970, "dynamics_loss_avg": 0.02921374123543501}
+{"step": 67970, "action_loss_avg": 0.0012173629191238433}
+{"step": 67980, "dynamics_loss_avg": 0.020337442681193352}
+{"step": 67980, "action_loss_avg": 0.0007497294514905662}
+{"step": 67990, "dynamics_loss_avg": 0.03184284428134561}
+{"step": 67990, "action_loss_avg": 0.0016014170076232403}
+{"step": 68000, "loss": 0.029, "learning_rate": 2.548026579477575e-05}
+{"step": 68000, "dynamics_loss_avg": 0.03263889197260141}
+{"step": 68000, "action_loss_avg": 0.0016450208495371044}
+{"step": 68010, "dynamics_loss_avg": 0.03438341002911329}
+{"step": 68010, "action_loss_avg": 0.0012770351197104902}
+{"step": 68020, "dynamics_loss_avg": 0.034821955393999814}
+{"step": 68020, "action_loss_avg": 0.001545076014008373}
+{"step": 68030, "dynamics_loss_avg": 0.028075011167675256}
+{"step": 68030, "action_loss_avg": 0.0012316680265939794}
+{"step": 68040, "dynamics_loss_avg": 0.023861965350806712}
+{"step": 68040, "action_loss_avg": 0.0008960304723586888}
+{"step": 68050, "loss": 0.0317, "learning_rate": 2.5408249360183535e-05}
+{"step": 68050, "dynamics_loss_avg": 0.03105550343170762}
+{"step": 68050, "action_loss_avg": 0.0010090202500578015}
+{"step": 68060, "dynamics_loss_avg": 0.02558431951329112}
+{"step": 68060, "action_loss_avg": 0.0009426656266441569}
+{"step": 68070, "dynamics_loss_avg": 0.02293796297162771}
+{"step": 68070, "action_loss_avg": 0.0009484738751780242}
+{"step": 68080, "dynamics_loss_avg": 0.025105869909748436}
+{"step": 68080, "action_loss_avg": 0.0018418440246023237}
+{"step": 68090, "dynamics_loss_avg": 0.030840882565826178}
+{"step": 68090, "action_loss_avg": 0.0014150592585792765}
+{"step": 68100, "loss": 0.0283, "learning_rate": 2.5336300158498516e-05}
+{"step": 68100, "dynamics_loss_avg": 0.02675214344635606}
+{"step": 68100, "action_loss_avg": 0.0014274342625867575}
+{"step": 68110, "dynamics_loss_avg": 0.028240597527474164}
+{"step": 68110, "action_loss_avg": 0.0012635444130864927}
+{"step": 68120, "dynamics_loss_avg": 0.026606324966996907}
+{"step": 68120, "action_loss_avg": 0.0012428128480678423}
+{"step": 68130, "dynamics_loss_avg": 0.021603665594011546}
+{"step": 68130, "action_loss_avg": 0.0008689052658155561}
+{"step": 68140, "dynamics_loss_avg": 0.03186870003119111}
+{"step": 68140, "action_loss_avg": 0.0017253940255613997}
+{"step": 68150, "loss": 0.029, "learning_rate": 2.52644183864271e-05}
+{"step": 68150, "dynamics_loss_avg": 0.02870927294716239}
+{"step": 68150, "action_loss_avg": 0.0013539313978981227}
+{"step": 68160, "dynamics_loss_avg": 0.025787508208304645}
+{"step": 68160, "action_loss_avg": 0.0011686812475090846}
+{"step": 68170, "dynamics_loss_avg": 0.02070861738175154}
+{"step": 68170, "action_loss_avg": 0.0011986154844635167}
+{"step": 68180, "dynamics_loss_avg": 0.02414712654426694}
+{"step": 68180, "action_loss_avg": 0.0009722390532260761}
+{"step": 68190, "dynamics_loss_avg": 0.03148760227486491}
+{"step": 68190, "action_loss_avg": 0.0013493014150299132}
+{"step": 68200, "loss": 0.0277, "learning_rate": 2.519260424049129e-05}
+{"step": 68200, "dynamics_loss_avg": 0.025654127076268195}
+{"step": 68200, "action_loss_avg": 0.000860068881593179}
+{"step": 68210, "dynamics_loss_avg": 0.031030932627618312}
+{"step": 68210, "action_loss_avg": 0.0011521638312842696}
+{"step": 68220, "dynamics_loss_avg": 0.024611253198236226}
+{"step": 68220, "action_loss_avg": 0.0013968730927444994}
+{"step": 68230, "dynamics_loss_avg": 0.036858012713491914}
+{"step": 68230, "action_loss_avg": 0.0013756122847553343}
+{"step": 68240, "dynamics_loss_avg": 0.029999463446438314}
+{"step": 68240, "action_loss_avg": 0.0011959785886574536}
+{"step": 68250, "loss": 0.0298, "learning_rate": 2.5120857917028207e-05}
+{"step": 68250, "dynamics_loss_avg": 0.03305217381566763}
+{"step": 68250, "action_loss_avg": 0.001265286497073248}
+{"step": 68260, "dynamics_loss_avg": 0.02788500227034092}
+{"step": 68260, "action_loss_avg": 0.0013829103962052613}
+{"step": 68270, "dynamics_loss_avg": 0.03499908917583525}
+{"step": 68270, "action_loss_avg": 0.0015598332654917612}
+{"step": 68280, "dynamics_loss_avg": 0.02349463482387364}
+{"step": 68280, "action_loss_avg": 0.001110987713036593}
+{"step": 68290, "dynamics_loss_avg": 0.03915872909128666}
+{"step": 68290, "action_loss_avg": 0.0019139591720886528}
+{"step": 68300, "loss": 0.0309, "learning_rate": 2.5049179612189576e-05}
+{"step": 68300, "dynamics_loss_avg": 0.01987608103081584}
+{"step": 68300, "action_loss_avg": 0.0008647109207231551}
+{"step": 68310, "dynamics_loss_avg": 0.030687402514740825}
+{"step": 68310, "action_loss_avg": 0.0013882162733352744}
+{"step": 68320, "dynamics_loss_avg": 0.02344439022708684}
+{"step": 68320, "action_loss_avg": 0.0009934217436239124}
+{"step": 68330, "dynamics_loss_avg": 0.02581453202292323}
+{"step": 68330, "action_loss_avg": 0.001107337517896667}
+{"step": 68340, "dynamics_loss_avg": 0.04337456747889519}
+{"step": 68340, "action_loss_avg": 0.002156092567020096}
+{"step": 68350, "loss": 0.0278, "learning_rate": 2.4977569521941134e-05}
+{"step": 68350, "dynamics_loss_avg": 0.024855205789208412}
+{"step": 68350, "action_loss_avg": 0.000987761779106222}
+{"step": 68360, "dynamics_loss_avg": 0.028332083858549593}
+{"step": 68360, "action_loss_avg": 0.0010489923268323764}
+{"step": 68370, "dynamics_loss_avg": 0.02801063833758235}
+{"step": 68370, "action_loss_avg": 0.0011680699535645545}
+{"step": 68380, "dynamics_loss_avg": 0.026288828533142804}
+{"step": 68380, "action_loss_avg": 0.0009222559892805293}
+{"step": 68390, "dynamics_loss_avg": 0.03637678408995271}
+{"step": 68390, "action_loss_avg": 0.001573476381599903}
+{"step": 68400, "loss": 0.0307, "learning_rate": 2.4906027842062137e-05}
+{"step": 68400, "dynamics_loss_avg": 0.02248844113200903}
+{"step": 68400, "action_loss_avg": 0.000948011755826883}
+{"step": 68410, "dynamics_loss_avg": 0.03136970242485404}
+{"step": 68410, "action_loss_avg": 0.0014503990765661}
+{"step": 68420, "dynamics_loss_avg": 0.026313916593790055}
+{"step": 68420, "action_loss_avg": 0.0013367790845222772}
+{"step": 68430, "dynamics_loss_avg": 0.032583683636039494}
+{"step": 68430, "action_loss_avg": 0.0015064434905070812}
+{"step": 68440, "dynamics_loss_avg": 0.028925482742488386}
+{"step": 68440, "action_loss_avg": 0.0010470814915606752}
+{"step": 68450, "loss": 0.0306, "learning_rate": 2.483455476814484e-05}
+{"step": 68450, "dynamics_loss_avg": 0.0346919403411448}
+{"step": 68450, "action_loss_avg": 0.001487191574415192}
+{"step": 68460, "dynamics_loss_avg": 0.028736823238432407}
+{"step": 68460, "action_loss_avg": 0.001623376499628648}
+{"step": 68470, "dynamics_loss_avg": 0.03973102197051048}
+{"step": 68470, "action_loss_avg": 0.0013430339720798656}
+{"step": 68480, "dynamics_loss_avg": 0.03797464738599956}
+{"step": 68480, "action_loss_avg": 0.0017329160458757543}
+{"step": 68490, "dynamics_loss_avg": 0.03980702813714743}
+{"step": 68490, "action_loss_avg": 0.0014712414529640227}
+{"step": 68500, "loss": 0.0339, "learning_rate": 2.476315049559384e-05}
+{"step": 68500, "dynamics_loss_avg": 0.025775453448295592}
+{"step": 68500, "action_loss_avg": 0.0010072990640765055}
+{"step": 68510, "dynamics_loss_avg": 0.02914181835949421}
+{"step": 68510, "action_loss_avg": 0.001298957981634885}
+{"step": 68520, "dynamics_loss_avg": 0.03322198130190372}
+{"step": 68520, "action_loss_avg": 0.001580736000323668}
+{"step": 68530, "dynamics_loss_avg": 0.031467395927757026}
+{"step": 68530, "action_loss_avg": 0.001310019171796739}
+{"step": 68540, "dynamics_loss_avg": 0.036592282727360724}
+{"step": 68540, "action_loss_avg": 0.0016838534269481898}
+{"step": 68550, "loss": 0.034, "learning_rate": 2.469181521962573e-05}
+{"step": 68550, "dynamics_loss_avg": 0.029221989586949347}
+{"step": 68550, "action_loss_avg": 0.0010200995282502844}
+{"step": 68560, "dynamics_loss_avg": 0.023047055024653672}
+{"step": 68560, "action_loss_avg": 0.0012178046046756208}
+{"step": 68570, "dynamics_loss_avg": 0.027684227842837573}
+{"step": 68570, "action_loss_avg": 0.0014288194273831324}
+{"step": 68580, "dynamics_loss_avg": 0.03172306423075497}
+{"step": 68580, "action_loss_avg": 0.0020137349143624305}
+{"step": 68590, "dynamics_loss_avg": 0.024930836725980045}
+{"step": 68590, "action_loss_avg": 0.001122647093143314}
+{"step": 68600, "loss": 0.0288, "learning_rate": 2.46205491352684e-05}
+{"step": 68600, "dynamics_loss_avg": 0.025645864102989434}
+{"step": 68600, "action_loss_avg": 0.0014361016626935452}
+{"step": 68610, "dynamics_loss_avg": 0.027990764938294888}
+{"step": 68610, "action_loss_avg": 0.0010502442513825373}
+{"step": 68620, "dynamics_loss_avg": 0.023594061937183143}
+{"step": 68620, "action_loss_avg": 0.0013415669032838195}
+{"step": 68630, "dynamics_loss_avg": 0.02838450949639082}
+{"step": 68630, "action_loss_avg": 0.001461624671355821}
+{"step": 68640, "dynamics_loss_avg": 0.036100035160779954}
+{"step": 68640, "action_loss_avg": 0.001987505776924081}
+{"step": 68650, "loss": 0.0301, "learning_rate": 2.4549352437360622e-05}
+{"step": 68650, "dynamics_loss_avg": 0.0300368707627058}
+{"step": 68650, "action_loss_avg": 0.0012923457485157996}
+{"step": 68660, "dynamics_loss_avg": 0.028225994529202582}
+{"step": 68660, "action_loss_avg": 0.0013962535187602044}
+{"step": 68670, "dynamics_loss_avg": 0.03220137162134051}
+{"step": 68670, "action_loss_avg": 0.0015043007442727685}
+{"step": 68680, "dynamics_loss_avg": 0.02653122050687671}
+{"step": 68680, "action_loss_avg": 0.0014551880391081794}
+{"step": 68690, "dynamics_loss_avg": 0.035818283911794424}
+{"step": 68690, "action_loss_avg": 0.0016084337286883966}
+{"step": 68700, "loss": 0.0304, "learning_rate": 2.447822532055149e-05}
+{"step": 68700, "dynamics_loss_avg": 0.023841640539467336}
+{"step": 68700, "action_loss_avg": 0.0010444725252455101}
+{"step": 68710, "dynamics_loss_avg": 0.029199903644621373}
+{"step": 68710, "action_loss_avg": 0.0011861841543577612}
+{"step": 68720, "dynamics_loss_avg": 0.03072200985625386}
+{"step": 68720, "action_loss_avg": 0.00112219198490493}
+{"step": 68730, "dynamics_loss_avg": 0.02884484799578786}
+{"step": 68730, "action_loss_avg": 0.0012676854530582204}
+{"step": 68740, "dynamics_loss_avg": 0.019090878870338203}
+{"step": 68740, "action_loss_avg": 0.0011206118389964104}
+{"step": 68750, "loss": 0.0278, "learning_rate": 2.440716797929975e-05}
+{"step": 68750, "dynamics_loss_avg": 0.02294537639245391}
+{"step": 68750, "action_loss_avg": 0.0011740953981643544}
+{"step": 68760, "dynamics_loss_avg": 0.03480767626315355}
+{"step": 68760, "action_loss_avg": 0.001414118066895753}
+{"step": 68770, "dynamics_loss_avg": 0.025178458041045813}
+{"step": 68770, "action_loss_avg": 0.0008805968987871893}
+{"step": 68780, "dynamics_loss_avg": 0.027951336372643708}
+{"step": 68780, "action_loss_avg": 0.0010718218283727766}
+{"step": 68790, "dynamics_loss_avg": 0.030979622853919864}
+{"step": 68790, "action_loss_avg": 0.00106984528247267}
+{"step": 68800, "loss": 0.0279, "learning_rate": 2.433618060787351e-05}
+{"step": 68800, "dynamics_loss_avg": 0.026303553860634564}
+{"step": 68800, "action_loss_avg": 0.0013850230548996477}
+{"step": 68810, "dynamics_loss_avg": 0.02594424122944474}
+{"step": 68810, "action_loss_avg": 0.0010103343694936485}
+{"step": 68820, "dynamics_loss_avg": 0.033420426305383444}
+{"step": 68820, "action_loss_avg": 0.0010706282395403833}
+{"step": 68830, "dynamics_loss_avg": 0.026385589316487313}
+{"step": 68830, "action_loss_avg": 0.0011409445200115443}
+{"step": 68840, "dynamics_loss_avg": 0.023526400420814754}
+{"step": 68840, "action_loss_avg": 0.0007228258909890428}
+{"step": 68850, "loss": 0.0284, "learning_rate": 2.4265263400349497e-05}
+{"step": 68850, "dynamics_loss_avg": 0.03175227744504809}
+{"step": 68850, "action_loss_avg": 0.0016257376410067081}
+{"step": 68860, "dynamics_loss_avg": 0.028107591718435288}
+{"step": 68860, "action_loss_avg": 0.0009842959407251328}
+{"step": 68870, "dynamics_loss_avg": 0.037156027555465695}
+{"step": 68870, "action_loss_avg": 0.0018361905589699746}
+{"step": 68880, "dynamics_loss_avg": 0.03346658563241363}
+{"step": 68880, "action_loss_avg": 0.001539481183863245}
+{"step": 68890, "dynamics_loss_avg": 0.024550510197877885}
+{"step": 68890, "action_loss_avg": 0.0013209186581661925}
+{"step": 68900, "loss": 0.03, "learning_rate": 2.4194416550612687e-05}
+{"step": 68900, "dynamics_loss_avg": 0.028407037304714323}
+{"step": 68900, "action_loss_avg": 0.0010869469930185004}
+{"step": 68910, "dynamics_loss_avg": 0.03574084397405386}
+{"step": 68910, "action_loss_avg": 0.0018533640075474977}
+{"step": 68920, "dynamics_loss_avg": 0.028769968543201685}
+{"step": 68920, "action_loss_avg": 0.0014112812117673458}
+{"step": 68930, "dynamics_loss_avg": 0.024893076764419673}
+{"step": 68930, "action_loss_avg": 0.0011379783652955666}
+{"step": 68940, "dynamics_loss_avg": 0.02418295480310917}
+{"step": 68940, "action_loss_avg": 0.0009717241802718491}
+{"step": 68950, "loss": 0.0287, "learning_rate": 2.4123640252355652e-05}
+{"step": 68950, "dynamics_loss_avg": 0.029004781786352397}
+{"step": 68950, "action_loss_avg": 0.0015819429187104105}
+{"step": 68960, "dynamics_loss_avg": 0.02934274887666106}
+{"step": 68960, "action_loss_avg": 0.0015333706542151049}
+{"step": 68970, "dynamics_loss_avg": 0.030195143865421416}
+{"step": 68970, "action_loss_avg": 0.0014719214552314952}
+{"step": 68980, "dynamics_loss_avg": 0.030878898780792953}
+{"step": 68980, "action_loss_avg": 0.0015630499954568222}
+{"step": 68990, "dynamics_loss_avg": 0.03559857625514269}
+{"step": 68990, "action_loss_avg": 0.0018063692783471196}
+{"step": 69000, "loss": 0.0308, "learning_rate": 2.405293469907805e-05}
+{"step": 69000, "dynamics_loss_avg": 0.02709908476099372}
+{"step": 69000, "action_loss_avg": 0.0012743561586830766}
+{"step": 69010, "dynamics_loss_avg": 0.033201923593878746}
+{"step": 69010, "action_loss_avg": 0.001440592249855399}
+{"step": 69020, "dynamics_loss_avg": 0.031413630582392216}
+{"step": 69020, "action_loss_avg": 0.001131395241827704}
+{"step": 69030, "dynamics_loss_avg": 0.03216191744431853}
+{"step": 69030, "action_loss_avg": 0.0015579531842377036}
+{"step": 69040, "dynamics_loss_avg": 0.02494762521237135}
+{"step": 69040, "action_loss_avg": 0.000942625675816089}
+{"step": 69050, "loss": 0.0313, "learning_rate": 2.3982300084086224e-05}
+{"step": 69050, "dynamics_loss_avg": 0.03775215754285455}
+{"step": 69050, "action_loss_avg": 0.001434725492435973}
+{"step": 69060, "dynamics_loss_avg": 0.0203228821977973}
+{"step": 69060, "action_loss_avg": 0.0009230052586644888}
+{"step": 69070, "dynamics_loss_avg": 0.02889407183974981}
+{"step": 69070, "action_loss_avg": 0.0010927008668659254}
+{"step": 69080, "dynamics_loss_avg": 0.03176692528650164}
+{"step": 69080, "action_loss_avg": 0.0015722758980700746}
+{"step": 69090, "dynamics_loss_avg": 0.02754502659663558}
+{"step": 69090, "action_loss_avg": 0.0008864571864251047}
+{"step": 69100, "loss": 0.0291, "learning_rate": 2.3911736600492463e-05}
+{"step": 69100, "dynamics_loss_avg": 0.025770522095263003}
+{"step": 69100, "action_loss_avg": 0.000993176773772575}
+{"step": 69110, "dynamics_loss_avg": 0.02620282107964158}
+{"step": 69110, "action_loss_avg": 0.0009706331737106666}
+{"step": 69120, "dynamics_loss_avg": 0.02890859991312027}
+{"step": 69120, "action_loss_avg": 0.0010755813418654725}
+{"step": 69130, "dynamics_loss_avg": 0.027064669993706048}
+{"step": 69130, "action_loss_avg": 0.0010768275649752467}
+{"step": 69140, "dynamics_loss_avg": 0.021433984488248826}
+{"step": 69140, "action_loss_avg": 0.0007570179339381866}
+{"step": 69150, "loss": 0.0269, "learning_rate": 2.3841244441214673e-05}
+{"step": 69150, "dynamics_loss_avg": 0.031052393931895496}
+{"step": 69150, "action_loss_avg": 0.0011157213826663791}
+{"step": 69160, "dynamics_loss_avg": 0.033330424968153236}
+{"step": 69160, "action_loss_avg": 0.0012456745374947787}
+{"step": 69170, "dynamics_loss_avg": 0.02579136872664094}
+{"step": 69170, "action_loss_avg": 0.0008453947317320854}
+{"step": 69180, "dynamics_loss_avg": 0.031497016455978154}
+{"step": 69180, "action_loss_avg": 0.001675565613550134}
+{"step": 69190, "dynamics_loss_avg": 0.03333665188401937}
+{"step": 69190, "action_loss_avg": 0.0011187905096448959}
+{"step": 69200, "loss": 0.032, "learning_rate": 2.3770823798975716e-05}
+{"step": 69200, "dynamics_loss_avg": 0.03280145479366183}
+{"step": 69200, "action_loss_avg": 0.001294788980158046}
+{"step": 69210, "dynamics_loss_avg": 0.026798757212236523}
+{"step": 69210, "action_loss_avg": 0.001041491559590213}
+{"step": 69220, "dynamics_loss_avg": 0.023861869424581527}
+{"step": 69220, "action_loss_avg": 0.0011944666708586737}
+{"step": 69230, "dynamics_loss_avg": 0.035254367534071206}
+{"step": 69230, "action_loss_avg": 0.0015017857600469141}
+{"step": 69240, "dynamics_loss_avg": 0.024863087013363837}
+{"step": 69240, "action_loss_avg": 0.0007883982470957562}
+{"step": 69250, "loss": 0.0293, "learning_rate": 2.3700474866302913e-05}
+{"step": 69250, "dynamics_loss_avg": 0.02813309822231531}
+{"step": 69250, "action_loss_avg": 0.0011799766041804105}
+{"step": 69260, "dynamics_loss_avg": 0.03244603117927909}
+{"step": 69260, "action_loss_avg": 0.0015189498255494982}
+{"step": 69270, "dynamics_loss_avg": 0.02418799391016364}
+{"step": 69270, "action_loss_avg": 0.000987258873647079}
+{"step": 69280, "dynamics_loss_avg": 0.024018681794404983}
+{"step": 69280, "action_loss_avg": 0.0010525770238018594}
+{"step": 69290, "dynamics_loss_avg": 0.028173156082630157}
+{"step": 69290, "action_loss_avg": 0.0013163371186237782}
+{"step": 69300, "loss": 0.0299, "learning_rate": 2.3630197835527595e-05}
+{"step": 69300, "dynamics_loss_avg": 0.033281265012919906}
+{"step": 69300, "action_loss_avg": 0.001577520798309706}
+{"step": 69310, "dynamics_loss_avg": 0.03517015390098095}
+{"step": 69310, "action_loss_avg": 0.002025376004166901}
+{"step": 69320, "dynamics_loss_avg": 0.02099046208895743}
+{"step": 69320, "action_loss_avg": 0.0009374505083542317}
+{"step": 69330, "dynamics_loss_avg": 0.030336894979700445}
+{"step": 69330, "action_loss_avg": 0.0010842619085451588}
+{"step": 69340, "dynamics_loss_avg": 0.02710323822684586}
+{"step": 69340, "action_loss_avg": 0.001241580068017356}
+{"step": 69350, "loss": 0.0298, "learning_rate": 2.3559992898784454e-05}
+{"step": 69350, "dynamics_loss_avg": 0.027096499875187873}
+{"step": 69350, "action_loss_avg": 0.0011927799845580012}
+{"step": 69360, "dynamics_loss_avg": 0.02897833874449134}
+{"step": 69360, "action_loss_avg": 0.0017289884592173621}
+{"step": 69370, "dynamics_loss_avg": 0.028347423113882542}
+{"step": 69370, "action_loss_avg": 0.0011511214761412703}
+{"step": 69380, "dynamics_loss_avg": 0.028753427043557166}
+{"step": 69380, "action_loss_avg": 0.0011863090039696544}
+{"step": 69390, "dynamics_loss_avg": 0.0254691400565207}
+{"step": 69390, "action_loss_avg": 0.0008707843429874629}
+{"step": 69400, "loss": 0.028, "learning_rate": 2.3489860248011136e-05}
+{"step": 69400, "dynamics_loss_avg": 0.022088975785300134}
+{"step": 69400, "action_loss_avg": 0.001089953549671918}
+{"step": 69410, "dynamics_loss_avg": 0.03225120939314365}
+{"step": 69410, "action_loss_avg": 0.0011864533327752725}
+{"step": 69420, "dynamics_loss_avg": 0.02297928910702467}
+{"step": 69420, "action_loss_avg": 0.000982027838472277}
+{"step": 69430, "dynamics_loss_avg": 0.026798267848789692}
+{"step": 69430, "action_loss_avg": 0.0011965461890213192}
+{"step": 69440, "dynamics_loss_avg": 0.03521138541400433}
+{"step": 69440, "action_loss_avg": 0.001385920640313998}
+{"step": 69450, "loss": 0.0301, "learning_rate": 2.3419800074947612e-05}
+{"step": 69450, "dynamics_loss_avg": 0.03646474052220583}
+{"step": 69450, "action_loss_avg": 0.0015019269194453955}
+{"step": 69460, "dynamics_loss_avg": 0.03056074199266732}
+{"step": 69460, "action_loss_avg": 0.0017192876606713981}
+{"step": 69470, "dynamics_loss_avg": 0.029462021309882402}
+{"step": 69470, "action_loss_avg": 0.0014714180899318308}
+{"step": 69480, "dynamics_loss_avg": 0.0278420630376786}
+{"step": 69480, "action_loss_avg": 0.0011246639769524336}
+{"step": 69490, "dynamics_loss_avg": 0.026356647349894048}
+{"step": 69490, "action_loss_avg": 0.00108735446119681}
+{"step": 69500, "loss": 0.0291, "learning_rate": 2.3349812571135703e-05}
+{"step": 69500, "dynamics_loss_avg": 0.019682319555431604}
+{"step": 69500, "action_loss_avg": 0.0010991215880494566}
+{"step": 69510, "dynamics_loss_avg": 0.031493214331567286}
+{"step": 69510, "action_loss_avg": 0.0011222767119761557}
+{"step": 69520, "dynamics_loss_avg": 0.03414008263498545}
+{"step": 69520, "action_loss_avg": 0.0015969802683684976}
+{"step": 69530, "dynamics_loss_avg": 0.029773473832756282}
+{"step": 69530, "action_loss_avg": 0.0011741473397705704}
+{"step": 69540, "dynamics_loss_avg": 0.03887144830077886}
+{"step": 69540, "action_loss_avg": 0.0020776140125235544}
+{"step": 69550, "loss": 0.0317, "learning_rate": 2.327989792791861e-05}
+{"step": 69550, "dynamics_loss_avg": 0.030100463423877954}
+{"step": 69550, "action_loss_avg": 0.0011443264229455963}
+{"step": 69560, "dynamics_loss_avg": 0.030373152904212476}
+{"step": 69560, "action_loss_avg": 0.0010900784691330045}
+{"step": 69570, "dynamics_loss_avg": 0.028066805377602578}
+{"step": 69570, "action_loss_avg": 0.0013328230183105917}
+{"step": 69580, "dynamics_loss_avg": 0.024044105689972638}
+{"step": 69580, "action_loss_avg": 0.0010393945907708258}
+{"step": 69590, "dynamics_loss_avg": 0.026587904989719392}
+{"step": 69590, "action_loss_avg": 0.0015030516078695655}
+{"step": 69600, "loss": 0.0276, "learning_rate": 2.3210056336440273e-05}
+{"step": 69600, "dynamics_loss_avg": 0.029880310874432325}
+{"step": 69600, "action_loss_avg": 0.0012435142591129989}
+{"step": 69610, "dynamics_loss_avg": 0.023442974034696817}
+{"step": 69610, "action_loss_avg": 0.0011429204052546993}
+{"step": 69620, "dynamics_loss_avg": 0.023504996136762202}
+{"step": 69620, "action_loss_avg": 0.001248307849164121}
+{"step": 69630, "dynamics_loss_avg": 0.036847911216318606}
+{"step": 69630, "action_loss_avg": 0.0012618580309208482}
+{"step": 69640, "dynamics_loss_avg": 0.026915149576961995}
+{"step": 69640, "action_loss_avg": 0.0011242570268223061}
+{"step": 69650, "loss": 0.0304, "learning_rate": 2.3140287987644927e-05}
+{"step": 69650, "dynamics_loss_avg": 0.02673909775912762}
+{"step": 69650, "action_loss_avg": 0.0011988336656941101}
+{"step": 69660, "dynamics_loss_avg": 0.03049026560038328}
+{"step": 69660, "action_loss_avg": 0.0011923930025659502}
+{"step": 69670, "dynamics_loss_avg": 0.028356515523046254}
+{"step": 69670, "action_loss_avg": 0.0011113752174424008}
+{"step": 69680, "dynamics_loss_avg": 0.04358411058783531}
+{"step": 69680, "action_loss_avg": 0.0020105637348024176}
+{"step": 69690, "dynamics_loss_avg": 0.026906032767146825}
+{"step": 69690, "action_loss_avg": 0.0010627718816976993}
+{"step": 69700, "loss": 0.0319, "learning_rate": 2.3070593072276603e-05}
+{"step": 69700, "dynamics_loss_avg": 0.029541130922734738}
+{"step": 69700, "action_loss_avg": 0.001209199771983549}
+{"step": 69710, "dynamics_loss_avg": 0.03164077363908291}
+{"step": 69710, "action_loss_avg": 0.0012969090545084327}
+{"step": 69720, "dynamics_loss_avg": 0.035628022998571394}
+{"step": 69720, "action_loss_avg": 0.0010603167494991795}
+{"step": 69730, "dynamics_loss_avg": 0.035990596190094946}
+{"step": 69730, "action_loss_avg": 0.0017946727981325238}
+{"step": 69740, "dynamics_loss_avg": 0.024861759273335338}
+{"step": 69740, "action_loss_avg": 0.0015946062136208638}
+{"step": 69750, "loss": 0.0322, "learning_rate": 2.30009717808785e-05}
+{"step": 69750, "dynamics_loss_avg": 0.03155368259176612}
+{"step": 69750, "action_loss_avg": 0.0016744714928790926}
+{"step": 69760, "dynamics_loss_avg": 0.034949691873043774}
+{"step": 69760, "action_loss_avg": 0.0015305721492040903}
+{"step": 69770, "dynamics_loss_avg": 0.02754858173429966}
+{"step": 69770, "action_loss_avg": 0.0009287402528570965}
+{"step": 69780, "dynamics_loss_avg": 0.026031267549842595}
+{"step": 69780, "action_loss_avg": 0.001020115870051086}
+{"step": 69790, "dynamics_loss_avg": 0.035018772818148136}
+{"step": 69790, "action_loss_avg": 0.0013470974517986178}
+{"step": 69800, "loss": 0.0278, "learning_rate": 2.293142430379262e-05}
+{"step": 69800, "dynamics_loss_avg": 0.015094555611722172}
+{"step": 69800, "action_loss_avg": 0.0004822543385671452}
+{"step": 69810, "dynamics_loss_avg": 0.024094482976943256}
+{"step": 69810, "action_loss_avg": 0.0013402733544353395}
+{"step": 69820, "dynamics_loss_avg": 0.032995777856558564}
+{"step": 69820, "action_loss_avg": 0.0013701031362870707}
+{"step": 69830, "dynamics_loss_avg": 0.03538725534453988}
+{"step": 69830, "action_loss_avg": 0.0014566960104275494}
+{"step": 69840, "dynamics_loss_avg": 0.023569206055253745}
+{"step": 69840, "action_loss_avg": 0.0012756566342432053}
+{"step": 69850, "loss": 0.03, "learning_rate": 2.2861950831159074e-05}
+{"step": 69850, "dynamics_loss_avg": 0.035209353081882}
+{"step": 69850, "action_loss_avg": 0.001138249266659841}
+{"step": 69860, "dynamics_loss_avg": 0.028722993098199368}
+{"step": 69860, "action_loss_avg": 0.0014392078563105315}
+{"step": 69870, "dynamics_loss_avg": 0.03287571864202619}
+{"step": 69870, "action_loss_avg": 0.0012707099376711994}
+{"step": 69880, "dynamics_loss_avg": 0.01948690749704838}
+{"step": 69880, "action_loss_avg": 0.0011074345995439217}
+{"step": 69890, "dynamics_loss_avg": 0.035572518967092036}
+{"step": 69890, "action_loss_avg": 0.0016700943873729558}
+{"step": 69900, "loss": 0.0315, "learning_rate": 2.279255155291568e-05}
+{"step": 69900, "dynamics_loss_avg": 0.03182641454041004}
+{"step": 69900, "action_loss_avg": 0.0014727217960171402}
+{"step": 69910, "dynamics_loss_avg": 0.0319414465688169}
+{"step": 69910, "action_loss_avg": 0.0012862951960414648}
+{"step": 69920, "dynamics_loss_avg": 0.02752962736412883}
+{"step": 69920, "action_loss_avg": 0.001238993162405677}
+{"step": 69930, "dynamics_loss_avg": 0.02123819524422288}
+{"step": 69930, "action_loss_avg": 0.0010112974312505684}
+{"step": 69940, "dynamics_loss_avg": 0.029928172007203102}
+{"step": 69940, "action_loss_avg": 0.0014939287619199603}
+{"step": 69950, "loss": 0.0299, "learning_rate": 2.2723226658797443e-05}
+{"step": 69950, "dynamics_loss_avg": 0.021535378508269788}
+{"step": 69950, "action_loss_avg": 0.0012019612739095464}
+{"step": 69960, "dynamics_loss_avg": 0.03089632848277688}
+{"step": 69960, "action_loss_avg": 0.0015291277726646514}
+{"step": 69970, "dynamics_loss_avg": 0.028753915801644325}
+{"step": 69970, "action_loss_avg": 0.0011653304798528552}
+{"step": 69980, "dynamics_loss_avg": 0.0338871113024652}
+{"step": 69980, "action_loss_avg": 0.0014213423419278115}
+{"step": 69990, "dynamics_loss_avg": 0.03363378131762147}
+{"step": 69990, "action_loss_avg": 0.001186162666999735}
+{"step": 70000, "loss": 0.031, "learning_rate": 2.2653976338335935e-05}
+{"step": 70000, "dynamics_loss_avg": 0.02812484633177519}
+{"step": 70000, "action_loss_avg": 0.0009427694283658638}
+{"step": 70010, "dynamics_loss_avg": 0.029706525802612304}
+{"step": 70010, "action_loss_avg": 0.001977933425223455}
+{"step": 70020, "dynamics_loss_avg": 0.03234316194429994}
+{"step": 70020, "action_loss_avg": 0.0017102486366638915}
+{"step": 70030, "dynamics_loss_avg": 0.024655653163790703}
+{"step": 70030, "action_loss_avg": 0.0009186381153995171}
+{"step": 70040, "dynamics_loss_avg": 0.042339037731289865}
+{"step": 70040, "action_loss_avg": 0.0017266409064177423}
+{"step": 70050, "loss": 0.0302, "learning_rate": 2.258480078085894e-05}
+{"step": 70050, "dynamics_loss_avg": 0.037705764174461365}
+{"step": 70050, "action_loss_avg": 0.0021551932324655352}
+{"step": 70060, "dynamics_loss_avg": 0.031654234044253826}
+{"step": 70060, "action_loss_avg": 0.0013408544822596014}
+{"step": 70070, "dynamics_loss_avg": 0.028933089599013327}
+{"step": 70070, "action_loss_avg": 0.001287582895020023}
+{"step": 70080, "dynamics_loss_avg": 0.026010346366092563}
+{"step": 70080, "action_loss_avg": 0.0010405030901893043}
+{"step": 70090, "dynamics_loss_avg": 0.028902119025588036}
+{"step": 70090, "action_loss_avg": 0.0011005655105691403}
+{"step": 70100, "loss": 0.0302, "learning_rate": 2.2515700175489762e-05}
+{"step": 70100, "dynamics_loss_avg": 0.03010378796607256}
+{"step": 70100, "action_loss_avg": 0.0015275621946784668}
+{"step": 70110, "dynamics_loss_avg": 0.024827034142799676}
+{"step": 70110, "action_loss_avg": 0.0007798951119184494}
+{"step": 70120, "dynamics_loss_avg": 0.027793418522924183}
+{"step": 70120, "action_loss_avg": 0.0009594837087206542}
+{"step": 70130, "dynamics_loss_avg": 0.031077063549309968}
+{"step": 70130, "action_loss_avg": 0.001775972283212468}
+{"step": 70140, "dynamics_loss_avg": 0.028961978480219842}
+{"step": 70140, "action_loss_avg": 0.0015206348805804736}
+{"step": 70150, "loss": 0.0288, "learning_rate": 2.2446674711146798e-05}
+{"step": 70150, "dynamics_loss_avg": 0.021762113738805055}
+{"step": 70150, "action_loss_avg": 0.0008141189988236875}
+{"step": 70160, "dynamics_loss_avg": 0.022784615494310857}
+{"step": 70160, "action_loss_avg": 0.0013128657592460513}
+{"step": 70170, "dynamics_loss_avg": 0.03816682882606983}
+{"step": 70170, "action_loss_avg": 0.001701497408794239}
+{"step": 70180, "dynamics_loss_avg": 0.02725299457088113}
+{"step": 70180, "action_loss_avg": 0.0011422801049775443}
+{"step": 70190, "dynamics_loss_avg": 0.02918064659461379}
+{"step": 70190, "action_loss_avg": 0.0008764668164076284}
+{"step": 70200, "loss": 0.0276, "learning_rate": 2.237772457654307e-05}
+{"step": 70200, "dynamics_loss_avg": 0.029203703720122577}
+{"step": 70200, "action_loss_avg": 0.0014657522086054086}
+{"step": 70210, "dynamics_loss_avg": 0.03339758859947324}
+{"step": 70210, "action_loss_avg": 0.0014033959712833166}
+{"step": 70220, "dynamics_loss_avg": 0.03281167056411505}
+{"step": 70220, "action_loss_avg": 0.0013356054900214077}
+{"step": 70230, "dynamics_loss_avg": 0.03401530543342233}
+{"step": 70230, "action_loss_avg": 0.0015683717909269034}
+{"step": 70240, "dynamics_loss_avg": 0.029426880925893784}
+{"step": 70240, "action_loss_avg": 0.0013769772893283516}
+{"step": 70250, "loss": 0.0308, "learning_rate": 2.2308849960185578e-05}
+{"step": 70250, "dynamics_loss_avg": 0.02327251937240362}
+{"step": 70250, "action_loss_avg": 0.000837317384139169}
+{"step": 70260, "dynamics_loss_avg": 0.038645471446216106}
+{"step": 70260, "action_loss_avg": 0.0016063397051766515}
+{"step": 70270, "dynamics_loss_avg": 0.030105562042444946}
+{"step": 70270, "action_loss_avg": 0.0009764810070919339}
+{"step": 70280, "dynamics_loss_avg": 0.019347810838371515}
+{"step": 70280, "action_loss_avg": 0.0008127212640829384}
+{"step": 70290, "dynamics_loss_avg": 0.021490353113040327}
+{"step": 70290, "action_loss_avg": 0.0007726706855464727}
+{"step": 70300, "loss": 0.0278, "learning_rate": 2.2240051050374933e-05}
+{"step": 70300, "dynamics_loss_avg": 0.02207505442202091}
+{"step": 70300, "action_loss_avg": 0.0009389561833813787}
+{"step": 70310, "dynamics_loss_avg": 0.021526833809912205}
+{"step": 70310, "action_loss_avg": 0.000987251620972529}
+{"step": 70320, "dynamics_loss_avg": 0.023363046627491713}
+{"step": 70320, "action_loss_avg": 0.0010079170169774443}
+{"step": 70330, "dynamics_loss_avg": 0.028244641982018946}
+{"step": 70330, "action_loss_avg": 0.0011083233752287925}
+{"step": 70340, "dynamics_loss_avg": 0.028994352370500565}
+{"step": 70340, "action_loss_avg": 0.0015874035219894723}
+{"step": 70350, "loss": 0.0275, "learning_rate": 2.2171328035204704e-05}
+{"step": 70350, "dynamics_loss_avg": 0.029058105684816836}
+{"step": 70350, "action_loss_avg": 0.0012389489158522338}
+{"step": 70360, "dynamics_loss_avg": 0.021380394464358687}
+{"step": 70360, "action_loss_avg": 0.0010622587986290454}
+{"step": 70370, "dynamics_loss_avg": 0.025994157418608665}
+{"step": 70370, "action_loss_avg": 0.001804750489827711}
+{"step": 70380, "dynamics_loss_avg": 0.029338960908353327}
+{"step": 70380, "action_loss_avg": 0.0013229896634584294}
+{"step": 70390, "dynamics_loss_avg": 0.031687192153185606}
+{"step": 70390, "action_loss_avg": 0.0009168664779281244}
+{"step": 70400, "loss": 0.0267, "learning_rate": 2.2102681102560967e-05}
+{"step": 70400, "dynamics_loss_avg": 0.03573353602550924}
+{"step": 70400, "action_loss_avg": 0.0018815042509231716}
+{"step": 70410, "dynamics_loss_avg": 0.028094142256304622}
+{"step": 70410, "action_loss_avg": 0.0013751602993579582}
+{"step": 70420, "dynamics_loss_avg": 0.029716962948441505}
+{"step": 70420, "action_loss_avg": 0.0015110395092051477}
+{"step": 70430, "dynamics_loss_avg": 0.022920450568199156}
+{"step": 70430, "action_loss_avg": 0.0007158970445743762}
+{"step": 70440, "dynamics_loss_avg": 0.031342779146507384}
+{"step": 70440, "action_loss_avg": 0.0009323228761786595}
+{"step": 70450, "loss": 0.0323, "learning_rate": 2.2034110440121864e-05}
+{"step": 70450, "dynamics_loss_avg": 0.03391925944015384}
+{"step": 70450, "action_loss_avg": 0.0014954348444007337}
+{"step": 70460, "dynamics_loss_avg": 0.03203539866954088}
+{"step": 70460, "action_loss_avg": 0.0012370106560410932}
+{"step": 70470, "dynamics_loss_avg": 0.028170297434553505}
+{"step": 70470, "action_loss_avg": 0.0013870731978386174}
+{"step": 70480, "dynamics_loss_avg": 0.034212555224075916}
+{"step": 70480, "action_loss_avg": 0.001363402555580251}
+{"step": 70490, "dynamics_loss_avg": 0.02883999506011605}
+{"step": 70490, "action_loss_avg": 0.0010002861585235224}
+{"step": 70500, "loss": 0.0315, "learning_rate": 2.1965616235356923e-05}
+{"step": 70500, "dynamics_loss_avg": 0.024407679727301002}
+{"step": 70500, "action_loss_avg": 0.0009039822543854825}
+{"step": 70510, "dynamics_loss_avg": 0.03294228110462427}
+{"step": 70510, "action_loss_avg": 0.0009519540762994438}
+{"step": 70520, "dynamics_loss_avg": 0.025180130172520875}
+{"step": 70520, "action_loss_avg": 0.0013556127261836082}
+{"step": 70530, "dynamics_loss_avg": 0.0260566801764071}
+{"step": 70530, "action_loss_avg": 0.00136732010578271}
+{"step": 70540, "dynamics_loss_avg": 0.02297716112807393}
+{"step": 70540, "action_loss_avg": 0.0012564848002512008}
+{"step": 70550, "loss": 0.0274, "learning_rate": 2.1897198675526725e-05}
+{"step": 70550, "dynamics_loss_avg": 0.023418161645531656}
+{"step": 70550, "action_loss_avg": 0.0010550796112511307}
+{"step": 70560, "dynamics_loss_avg": 0.03428630246780813}
+{"step": 70560, "action_loss_avg": 0.0014224565937183797}
+{"step": 70570, "dynamics_loss_avg": 0.022178870812058448}
+{"step": 70570, "action_loss_avg": 0.0011306191576295533}
+{"step": 70580, "dynamics_loss_avg": 0.032395911822095516}
+{"step": 70580, "action_loss_avg": 0.0016260877106105908}
+{"step": 70590, "dynamics_loss_avg": 0.030132640851661563}
+{"step": 70590, "action_loss_avg": 0.0010263995587592944}
+{"step": 70600, "loss": 0.0286, "learning_rate": 2.182885794768224e-05}
+{"step": 70600, "dynamics_loss_avg": 0.018607249949127436}
+{"step": 70600, "action_loss_avg": 0.0021777851157821714}
+{"step": 70610, "dynamics_loss_avg": 0.031025229301303626}
+{"step": 70610, "action_loss_avg": 0.0017650841298745945}
+{"step": 70620, "dynamics_loss_avg": 0.03350312244147062}
+{"step": 70620, "action_loss_avg": 0.0012813967987312935}
+{"step": 70630, "dynamics_loss_avg": 0.01637131399475038}
+{"step": 70630, "action_loss_avg": 0.0008777140552410856}
+{"step": 70640, "dynamics_loss_avg": 0.03829752081073821}
+{"step": 70640, "action_loss_avg": 0.0016368979486287571}
+{"step": 70650, "loss": 0.0299, "learning_rate": 2.17605942386644e-05}
+{"step": 70650, "dynamics_loss_avg": 0.0322412284091115}
+{"step": 70650, "action_loss_avg": 0.0012494454334955663}
+{"step": 70660, "dynamics_loss_avg": 0.030534062907099722}
+{"step": 70660, "action_loss_avg": 0.0009588962304405868}
+{"step": 70670, "dynamics_loss_avg": 0.02650122931227088}
+{"step": 70670, "action_loss_avg": 0.001291061899974011}
+{"step": 70680, "dynamics_loss_avg": 0.025841649528592824}
+{"step": 70680, "action_loss_avg": 0.0011184226750629023}
+{"step": 70690, "dynamics_loss_avg": 0.02709904806688428}
+{"step": 70690, "action_loss_avg": 0.0013832091121003033}
+{"step": 70700, "loss": 0.0285, "learning_rate": 2.169240773510361e-05}
+{"step": 70700, "dynamics_loss_avg": 0.022194246342405678}
+{"step": 70700, "action_loss_avg": 0.0008290743964607828}
+{"step": 70710, "dynamics_loss_avg": 0.030102499388158323}
+{"step": 70710, "action_loss_avg": 0.0014236937800887971}
+{"step": 70720, "dynamics_loss_avg": 0.028862122539430858}
+{"step": 70720, "action_loss_avg": 0.0009799974475754424}
+{"step": 70730, "dynamics_loss_avg": 0.025481478404253723}
+{"step": 70730, "action_loss_avg": 0.0010575666616205125}
+{"step": 70740, "dynamics_loss_avg": 0.025883129239082335}
+{"step": 70740, "action_loss_avg": 0.0010295275103999301}
+{"step": 70750, "loss": 0.0289, "learning_rate": 2.1624298623419133e-05}
+{"step": 70750, "dynamics_loss_avg": 0.03004434276372194}
+{"step": 70750, "action_loss_avg": 0.0012720666447421536}
+{"step": 70760, "dynamics_loss_avg": 0.03196875471621752}
+{"step": 70760, "action_loss_avg": 0.0012714534328551962}
+{"step": 70770, "dynamics_loss_avg": 0.028669438418000938}
+{"step": 70770, "action_loss_avg": 0.001147707726340741}
+{"step": 70780, "dynamics_loss_avg": 0.025462536513805388}
+{"step": 70780, "action_loss_avg": 0.001058620066032745}
+{"step": 70790, "dynamics_loss_avg": 0.03297802628949285}
+{"step": 70790, "action_loss_avg": 0.0014256920665502548}
+{"step": 70800, "loss": 0.0309, "learning_rate": 2.155626708981871e-05}
+{"step": 70800, "dynamics_loss_avg": 0.03417617306113243}
+{"step": 70800, "action_loss_avg": 0.0012519980024080723}
+{"step": 70810, "dynamics_loss_avg": 0.02741659600287676}
+{"step": 70810, "action_loss_avg": 0.0009797614242415876}
+{"step": 70820, "dynamics_loss_avg": 0.02604722958058119}
+{"step": 70820, "action_loss_avg": 0.0012338974862359463}
+{"step": 70830, "dynamics_loss_avg": 0.02362269312143326}
+{"step": 70830, "action_loss_avg": 0.0007745801078272053}
+{"step": 70840, "dynamics_loss_avg": 0.028744552470743655}
+{"step": 70840, "action_loss_avg": 0.001491941761923954}
+{"step": 70850, "loss": 0.0296, "learning_rate": 2.148831332029794e-05}
+{"step": 70850, "dynamics_loss_avg": 0.02105555571615696}
+{"step": 70850, "action_loss_avg": 0.0009956331312423572}
+{"step": 70860, "dynamics_loss_avg": 0.025137732457369565}
+{"step": 70860, "action_loss_avg": 0.0010956237121718005}
+{"step": 70870, "dynamics_loss_avg": 0.02075376408174634}
+{"step": 70870, "action_loss_avg": 0.0008513947483152151}
+{"step": 70880, "dynamics_loss_avg": 0.02860654746182263}
+{"step": 70880, "action_loss_avg": 0.0010971130745019765}
+{"step": 70890, "dynamics_loss_avg": 0.03451377805322409}
+{"step": 70890, "action_loss_avg": 0.0012711289164144546}
+{"step": 70900, "loss": 0.0291, "learning_rate": 2.1420437500639823e-05}
+{"step": 70900, "dynamics_loss_avg": 0.03172883875668049}
+{"step": 70900, "action_loss_avg": 0.0014233206718927249}
+{"step": 70910, "dynamics_loss_avg": 0.03638099199160934}
+{"step": 70910, "action_loss_avg": 0.0016960083099547773}
+{"step": 70920, "dynamics_loss_avg": 0.03687143921852112}
+{"step": 70920, "action_loss_avg": 0.0014297482062829658}
+{"step": 70930, "dynamics_loss_avg": 0.028890732768923046}
+{"step": 70930, "action_loss_avg": 0.0009672907326603308}
+{"step": 70940, "dynamics_loss_avg": 0.02343937223777175}
+{"step": 70940, "action_loss_avg": 0.0007791495314450003}
+{"step": 70950, "loss": 0.031, "learning_rate": 2.1352639816414288e-05}
+{"step": 70950, "dynamics_loss_avg": 0.025899055786430834}
+{"step": 70950, "action_loss_avg": 0.001217265940795187}
+{"step": 70960, "dynamics_loss_avg": 0.031099125230684876}
+{"step": 70960, "action_loss_avg": 0.0014103775552939623}
+{"step": 70970, "dynamics_loss_avg": 0.032334025204181674}
+{"step": 70970, "action_loss_avg": 0.0015619308513123542}
+{"step": 70980, "dynamics_loss_avg": 0.02017705882899463}
+{"step": 70980, "action_loss_avg": 0.0009519134851871059}
+{"step": 70990, "dynamics_loss_avg": 0.028561180364340542}
+{"step": 70990, "action_loss_avg": 0.0011482966103358195}
+{"step": 71000, "loss": 0.027, "learning_rate": 2.1284920452977602e-05}
+{"step": 71000, "dynamics_loss_avg": 0.02636941815726459}
+{"step": 71000, "action_loss_avg": 0.001156688918126747}
+{"step": 71010, "dynamics_loss_avg": 0.03394831363111735}
+{"step": 71010, "action_loss_avg": 0.0014705502544529736}
+{"step": 71020, "dynamics_loss_avg": 0.033628955483436584}
+{"step": 71020, "action_loss_avg": 0.0014444551256019623}
+{"step": 71030, "dynamics_loss_avg": 0.03170385705307126}
+{"step": 71030, "action_loss_avg": 0.0009639908093959093}
+{"step": 71040, "dynamics_loss_avg": 0.029571384703740478}
+{"step": 71040, "action_loss_avg": 0.0013416317437076942}
+{"step": 71050, "loss": 0.0305, "learning_rate": 2.121727959547189e-05}
+{"step": 71050, "dynamics_loss_avg": 0.02681317236274481}
+{"step": 71050, "action_loss_avg": 0.0013336306321434677}
+{"step": 71060, "dynamics_loss_avg": 0.026805510651320218}
+{"step": 71060, "action_loss_avg": 0.0012133653275668622}
+{"step": 71070, "dynamics_loss_avg": 0.02500772913917899}
+{"step": 71070, "action_loss_avg": 0.0008200526994187385}
+{"step": 71080, "dynamics_loss_avg": 0.0378383063711226}
+{"step": 71080, "action_loss_avg": 0.001203579903813079}
+{"step": 71090, "dynamics_loss_avg": 0.029405942372977733}
+{"step": 71090, "action_loss_avg": 0.0013874954835046082}
+{"step": 71100, "loss": 0.0304, "learning_rate": 2.1149717428824722e-05}
+{"step": 71100, "dynamics_loss_avg": 0.030923242680728436}
+{"step": 71100, "action_loss_avg": 0.0015146088437177241}
+{"step": 71110, "dynamics_loss_avg": 0.03032486392185092}
+{"step": 71110, "action_loss_avg": 0.001106421891017817}
+{"step": 71120, "dynamics_loss_avg": 0.02704027760773897}
+{"step": 71120, "action_loss_avg": 0.0008618563224445097}
+{"step": 71130, "dynamics_loss_avg": 0.025347458478063346}
+{"step": 71130, "action_loss_avg": 0.0010053987265564502}
+{"step": 71140, "dynamics_loss_avg": 0.024316107155755162}
+{"step": 71140, "action_loss_avg": 0.0010712451592553407}
+{"step": 71150, "loss": 0.0276, "learning_rate": 2.1082234137748434e-05}
+{"step": 71150, "dynamics_loss_avg": 0.024592365324497222}
+{"step": 71150, "action_loss_avg": 0.0009653746063122525}
+{"step": 71160, "dynamics_loss_avg": 0.02999974680133164}
+{"step": 71160, "action_loss_avg": 0.0009837366320425644}
+{"step": 71170, "dynamics_loss_avg": 0.027859818562865256}
+{"step": 71170, "action_loss_avg": 0.0014534011308569462}
+{"step": 71180, "dynamics_loss_avg": 0.021183282742276786}
+{"step": 71180, "action_loss_avg": 0.0006807587051298469}
+{"step": 71190, "dynamics_loss_avg": 0.02176903858780861}
+{"step": 71190, "action_loss_avg": 0.0008986032247776165}
+{"step": 71200, "loss": 0.0264, "learning_rate": 2.101482990673982e-05}
+{"step": 71200, "dynamics_loss_avg": 0.0324261630885303}
+{"step": 71200, "action_loss_avg": 0.0016018042340874672}
+{"step": 71210, "dynamics_loss_avg": 0.03311088401824236}
+{"step": 71210, "action_loss_avg": 0.001676820940338075}
+{"step": 71220, "dynamics_loss_avg": 0.0255596830509603}
+{"step": 71220, "action_loss_avg": 0.0010345684946514665}
+{"step": 71230, "dynamics_loss_avg": 0.02649845276027918}
+{"step": 71230, "action_loss_avg": 0.001169270885293372}
+{"step": 71240, "dynamics_loss_avg": 0.034061849629506466}
+{"step": 71240, "action_loss_avg": 0.0012958588005858474}
+{"step": 71250, "loss": 0.0311, "learning_rate": 2.0947504920079435e-05}
+{"step": 71250, "dynamics_loss_avg": 0.029293613275513053}
+{"step": 71250, "action_loss_avg": 0.001135550590697676}
+{"step": 71260, "dynamics_loss_avg": 0.03353677382692695}
+{"step": 71260, "action_loss_avg": 0.0016136329853907228}
+{"step": 71270, "dynamics_loss_avg": 0.034693185798823835}
+{"step": 71270, "action_loss_avg": 0.0012160991842392831}
+{"step": 71280, "dynamics_loss_avg": 0.023688301770016552}
+{"step": 71280, "action_loss_avg": 0.0008659475191961974}
+{"step": 71290, "dynamics_loss_avg": 0.02302782330662012}
+{"step": 71290, "action_loss_avg": 0.0009298269564169459}
+{"step": 71300, "loss": 0.0286, "learning_rate": 2.0880259361831216e-05}
+{"step": 71300, "dynamics_loss_avg": 0.025699498783797025}
+{"step": 71300, "action_loss_avg": 0.0009301260113716125}
+{"step": 71310, "dynamics_loss_avg": 0.031247578095644712}
+{"step": 71310, "action_loss_avg": 0.001166386259137653}
+{"step": 71320, "dynamics_loss_avg": 0.025206815358251332}
+{"step": 71320, "action_loss_avg": 0.0009959267976228149}
+{"step": 71330, "dynamics_loss_avg": 0.03955272464081645}
+{"step": 71330, "action_loss_avg": 0.001310345224919729}
+{"step": 71340, "dynamics_loss_avg": 0.03473882395774126}
+{"step": 71340, "action_loss_avg": 0.0011374236113624648}
+{"step": 71350, "loss": 0.0286, "learning_rate": 2.081309341584199e-05}
+{"step": 71350, "dynamics_loss_avg": 0.0239405432716012}
+{"step": 71350, "action_loss_avg": 0.001444639265537262}
+{"step": 71360, "dynamics_loss_avg": 0.033324611373245716}
+{"step": 71360, "action_loss_avg": 0.001804896502289921}
+{"step": 71370, "dynamics_loss_avg": 0.026865984965115785}
+{"step": 71370, "action_loss_avg": 0.0011242480686632916}
+{"step": 71380, "dynamics_loss_avg": 0.030029423628002407}
+{"step": 71380, "action_loss_avg": 0.0015746897930512204}
+{"step": 71390, "dynamics_loss_avg": 0.027099210349842907}
+{"step": 71390, "action_loss_avg": 0.0013358349271584303}
+{"step": 71400, "loss": 0.0304, "learning_rate": 2.0746007265740846e-05}
+{"step": 71400, "dynamics_loss_avg": 0.027980949729681015}
+{"step": 71400, "action_loss_avg": 0.0011340539902448654}
+{"step": 71410, "dynamics_loss_avg": 0.027803066931664944}
+{"step": 71410, "action_loss_avg": 0.0014029800106072799}
+{"step": 71420, "dynamics_loss_avg": 0.032433019811287524}
+{"step": 71420, "action_loss_avg": 0.0015617691606166773}
+{"step": 71430, "dynamics_loss_avg": 0.03066354412585497}
+{"step": 71430, "action_loss_avg": 0.0011383606062736363}
+{"step": 71440, "dynamics_loss_avg": 0.03364470787346363}
+{"step": 71440, "action_loss_avg": 0.0014198859164025635}
+{"step": 71450, "loss": 0.0292, "learning_rate": 2.0679001094938793e-05}
+{"step": 71450, "dynamics_loss_avg": 0.039251486258581283}
+{"step": 71450, "action_loss_avg": 0.001434663136024028}
+{"step": 71460, "dynamics_loss_avg": 0.021525273844599725}
+{"step": 71460, "action_loss_avg": 0.0010169265558943152}
+{"step": 71470, "dynamics_loss_avg": 0.035490742046386005}
+{"step": 71470, "action_loss_avg": 0.0012006019795080646}
+{"step": 71480, "dynamics_loss_avg": 0.030274338182061912}
+{"step": 71480, "action_loss_avg": 0.0014949857897590846}
+{"step": 71490, "dynamics_loss_avg": 0.024536924622952937}
+{"step": 71490, "action_loss_avg": 0.0011136552930111066}
+{"step": 71500, "loss": 0.0297, "learning_rate": 2.0612075086628123e-05}
+{"step": 71500, "dynamics_loss_avg": 0.03556884811259806}
+{"step": 71500, "action_loss_avg": 0.001722650055307895}
+{"step": 71510, "dynamics_loss_avg": 0.034474403131753206}
+{"step": 71510, "action_loss_avg": 0.0013534095778595656}
+{"step": 71520, "dynamics_loss_avg": 0.027307877037674188}
+{"step": 71520, "action_loss_avg": 0.0011487665062304587}
+{"step": 71530, "dynamics_loss_avg": 0.04121791571378708}
+{"step": 71530, "action_loss_avg": 0.0014960223517846317}
+{"step": 71540, "dynamics_loss_avg": 0.024976676795631647}
+{"step": 71540, "action_loss_avg": 0.0008768776489887387}
+{"step": 71550, "loss": 0.0303, "learning_rate": 2.054522942378198e-05}
+{"step": 71550, "dynamics_loss_avg": 0.028460619598627092}
+{"step": 71550, "action_loss_avg": 0.0012771492270985617}
+{"step": 71560, "dynamics_loss_avg": 0.03414344247430563}
+{"step": 71560, "action_loss_avg": 0.00139120229287073}
+{"step": 71570, "dynamics_loss_avg": 0.022404461167752743}
+{"step": 71570, "action_loss_avg": 0.0007459829037543386}
+{"step": 71580, "dynamics_loss_avg": 0.029341565212234855}
+{"step": 71580, "action_loss_avg": 0.0012353256650385446}
+{"step": 71590, "dynamics_loss_avg": 0.03216987401247025}
+{"step": 71590, "action_loss_avg": 0.0012746634194627405}
+{"step": 71600, "loss": 0.0291, "learning_rate": 2.0478464289153882e-05}
+{"step": 71600, "dynamics_loss_avg": 0.0326988291926682}
+{"step": 71600, "action_loss_avg": 0.001232544820231851}
+{"step": 71610, "dynamics_loss_avg": 0.02728220745921135}
+{"step": 71610, "action_loss_avg": 0.0011940669501200318}
+{"step": 71620, "dynamics_loss_avg": 0.02069671484641731}
+{"step": 71620, "action_loss_avg": 0.001095944904955104}
+{"step": 71630, "dynamics_loss_avg": 0.022042016498744488}
+{"step": 71630, "action_loss_avg": 0.0007498300547013059}
+{"step": 71640, "dynamics_loss_avg": 0.02375935222953558}
+{"step": 71640, "action_loss_avg": 0.000992966824560426}
+{"step": 71650, "loss": 0.028, "learning_rate": 2.041177986527712e-05}
+{"step": 71650, "dynamics_loss_avg": 0.033336551301181315}
+{"step": 71650, "action_loss_avg": 0.0014143456050078385}
+{"step": 71660, "dynamics_loss_avg": 0.027859649807214736}
+{"step": 71660, "action_loss_avg": 0.0009505358146270737}
+{"step": 71670, "dynamics_loss_avg": 0.039485206641256806}
+{"step": 71670, "action_loss_avg": 0.0025043091969564556}
+{"step": 71680, "dynamics_loss_avg": 0.02512232060544193}
+{"step": 71680, "action_loss_avg": 0.0011751428406569175}
+{"step": 71690, "dynamics_loss_avg": 0.029918658547103405}
+{"step": 71690, "action_loss_avg": 0.0012941536420839838}
+{"step": 71700, "loss": 0.0323, "learning_rate": 2.03451763344644e-05}
+{"step": 71700, "dynamics_loss_avg": 0.03464805586263538}
+{"step": 71700, "action_loss_avg": 0.0014322901086416095}
+{"step": 71710, "dynamics_loss_avg": 0.032992136850953105}
+{"step": 71710, "action_loss_avg": 0.0014724731561727821}
+{"step": 71720, "dynamics_loss_avg": 0.027063251985237003}
+{"step": 71720, "action_loss_avg": 0.0010305853727913927}
+{"step": 71730, "dynamics_loss_avg": 0.032421082723885775}
+{"step": 71730, "action_loss_avg": 0.0011491695477161556}
+{"step": 71740, "dynamics_loss_avg": 0.02146982094272971}
+{"step": 71740, "action_loss_avg": 0.0008720060053747147}
+{"step": 71750, "loss": 0.0296, "learning_rate": 2.0278653878807217e-05}
+{"step": 71750, "dynamics_loss_avg": 0.029724354110658168}
+{"step": 71750, "action_loss_avg": 0.0014193209121003748}
+{"step": 71760, "dynamics_loss_avg": 0.021527493931353094}
+{"step": 71760, "action_loss_avg": 0.0008372712341952138}
+{"step": 71770, "dynamics_loss_avg": 0.033279390260577205}
+{"step": 71770, "action_loss_avg": 0.001598459019442089}
+{"step": 71780, "dynamics_loss_avg": 0.02730141014326364}
+{"step": 71780, "action_loss_avg": 0.0012180513673229142}
+{"step": 71790, "dynamics_loss_avg": 0.023598156590014695}
+{"step": 71790, "action_loss_avg": 0.0013473857718054206}
+{"step": 71800, "loss": 0.0309, "learning_rate": 2.02122126801754e-05}
+{"step": 71800, "dynamics_loss_avg": 0.027430219296365976}
+{"step": 71800, "action_loss_avg": 0.0011041392630431802}
+{"step": 71810, "dynamics_loss_avg": 0.027610896807163953}
+{"step": 71810, "action_loss_avg": 0.0009292388276662678}
+{"step": 71820, "dynamics_loss_avg": 0.02562416484579444}
+{"step": 71820, "action_loss_avg": 0.001049481031805044}
+{"step": 71830, "dynamics_loss_avg": 0.03229877641424537}
+{"step": 71830, "action_loss_avg": 0.0013614737137686462}
+{"step": 71840, "dynamics_loss_avg": 0.03816443188115955}
+{"step": 71840, "action_loss_avg": 0.0016766283079050481}
+{"step": 71850, "loss": 0.0314, "learning_rate": 2.0145852920216697e-05}
+{"step": 71850, "dynamics_loss_avg": 0.02504386343061924}
+{"step": 71850, "action_loss_avg": 0.0012368101393803953}
+{"step": 71860, "dynamics_loss_avg": 0.02395837688818574}
+{"step": 71860, "action_loss_avg": 0.0012393742799758911}
+{"step": 71870, "dynamics_loss_avg": 0.03347396049648523}
+{"step": 71870, "action_loss_avg": 0.0014401721593458206}
+{"step": 71880, "dynamics_loss_avg": 0.026989345625042915}
+{"step": 71880, "action_loss_avg": 0.0016609121987130493}
+{"step": 71890, "dynamics_loss_avg": 0.028590068593621253}
+{"step": 71890, "action_loss_avg": 0.0009655053581809625}
+{"step": 71900, "loss": 0.0272, "learning_rate": 2.0079574780356115e-05}
+{"step": 71900, "dynamics_loss_avg": 0.028642400447279216}
+{"step": 71900, "action_loss_avg": 0.0015094574308022856}
+{"step": 71910, "dynamics_loss_avg": 0.03440850805491209}
+{"step": 71910, "action_loss_avg": 0.0011685935605783015}
+{"step": 71920, "dynamics_loss_avg": 0.035441681183874606}
+{"step": 71920, "action_loss_avg": 0.00181624538381584}
+{"step": 71930, "dynamics_loss_avg": 0.030722694541327655}
+{"step": 71930, "action_loss_avg": 0.0013531645032344385}
+{"step": 71940, "dynamics_loss_avg": 0.029932846827432514}
+{"step": 71940, "action_loss_avg": 0.0011358803880284541}
+{"step": 71950, "loss": 0.032, "learning_rate": 2.0013378441795584e-05}
+{"step": 71950, "dynamics_loss_avg": 0.034364666184410454}
+{"step": 71950, "action_loss_avg": 0.0012745763786369934}
+{"step": 71960, "dynamics_loss_avg": 0.02486159885302186}
+{"step": 71960, "action_loss_avg": 0.0012259013688890263}
+{"step": 71970, "dynamics_loss_avg": 0.022663588100112975}
+{"step": 71970, "action_loss_avg": 0.0007347498627495952}
+{"step": 71980, "dynamics_loss_avg": 0.035658532101660964}
+{"step": 71980, "action_loss_avg": 0.0014670278527773918}
+{"step": 71990, "dynamics_loss_avg": 0.024268117547035218}
+{"step": 71990, "action_loss_avg": 0.001046445278916508}
+{"step": 72000, "loss": 0.0262, "learning_rate": 1.9947264085513363e-05}
+{"step": 72000, "dynamics_loss_avg": 0.019757440499961375}
+{"step": 72000, "action_loss_avg": 0.0006439274293370545}
+{"step": 72010, "dynamics_loss_avg": 0.020456889597699045}
+{"step": 72010, "action_loss_avg": 0.0008133931609336287}
+{"step": 72020, "dynamics_loss_avg": 0.026876871986314655}
+{"step": 72020, "action_loss_avg": 0.0011795070924563334}
+{"step": 72030, "dynamics_loss_avg": 0.02483173431828618}
+{"step": 72030, "action_loss_avg": 0.0008968562091467902}
+{"step": 72040, "dynamics_loss_avg": 0.02586805373430252}
+{"step": 72040, "action_loss_avg": 0.0007610603905050084}
+{"step": 72050, "loss": 0.0251, "learning_rate": 1.988123189226355e-05}
+{"step": 72050, "dynamics_loss_avg": 0.024501293897628784}
+{"step": 72050, "action_loss_avg": 0.0012905345734907313}
+{"step": 72060, "dynamics_loss_avg": 0.026063253311440347}
+{"step": 72060, "action_loss_avg": 0.0009218298073392361}
+{"step": 72070, "dynamics_loss_avg": 0.023488945607095957}
+{"step": 72070, "action_loss_avg": 0.001273601857246831}
+{"step": 72080, "dynamics_loss_avg": 0.03109399937093258}
+{"step": 72080, "action_loss_avg": 0.0011331787711242214}
+{"step": 72090, "dynamics_loss_avg": 0.021464399294927716}
+{"step": 72090, "action_loss_avg": 0.0012145836080890149}
+{"step": 72100, "loss": 0.0281, "learning_rate": 1.9815282042575685e-05}
+{"step": 72100, "dynamics_loss_avg": 0.021649501519277692}
+{"step": 72100, "action_loss_avg": 0.0009163359485683031}
+{"step": 72110, "dynamics_loss_avg": 0.03642888348549604}
+{"step": 72110, "action_loss_avg": 0.0012114848999772222}
+{"step": 72120, "dynamics_loss_avg": 0.031056922022253276}
+{"step": 72120, "action_loss_avg": 0.0011936937749851494}
+{"step": 72130, "dynamics_loss_avg": 0.026006526686251162}
+{"step": 72130, "action_loss_avg": 0.0011397093097912149}
+{"step": 72140, "dynamics_loss_avg": 0.026418057922273874}
+{"step": 72140, "action_loss_avg": 0.0011621223005931825}
+{"step": 72150, "loss": 0.0298, "learning_rate": 1.9749414716754112e-05}
+{"step": 72150, "dynamics_loss_avg": 0.024568206258118154}
+{"step": 72150, "action_loss_avg": 0.0010408656773506664}
+{"step": 72160, "dynamics_loss_avg": 0.030098649393767118}
+{"step": 72160, "action_loss_avg": 0.0016669419244863092}
+{"step": 72170, "dynamics_loss_avg": 0.03189819436520338}
+{"step": 72170, "action_loss_avg": 0.0014960667758714408}
+{"step": 72180, "dynamics_loss_avg": 0.02808734467253089}
+{"step": 72180, "action_loss_avg": 0.0013145077333319931}
+{"step": 72190, "dynamics_loss_avg": 0.02337373825721443}
+{"step": 72190, "action_loss_avg": 0.0011018403922207654}
+{"step": 72200, "loss": 0.0288, "learning_rate": 1.9683630094877564e-05}
+{"step": 72200, "dynamics_loss_avg": 0.02065133242867887}
+{"step": 72200, "action_loss_avg": 0.0008903465597541072}
+{"step": 72210, "dynamics_loss_avg": 0.026809308491647244}
+{"step": 72210, "action_loss_avg": 0.0010464816965395584}
+{"step": 72220, "dynamics_loss_avg": 0.02315816329792142}
+{"step": 72220, "action_loss_avg": 0.0008378661004826427}
+{"step": 72230, "dynamics_loss_avg": 0.025469593424350023}
+{"step": 72230, "action_loss_avg": 0.0009915549628203735}
+{"step": 72240, "dynamics_loss_avg": 0.023436699248850345}
+{"step": 72240, "action_loss_avg": 0.0008938481129007414}
+{"step": 72250, "loss": 0.0257, "learning_rate": 1.9617928356798738e-05}
+{"step": 72250, "dynamics_loss_avg": 0.02437343690544367}
+{"step": 72250, "action_loss_avg": 0.0006879913999000564}
+{"step": 72260, "dynamics_loss_avg": 0.02574599953368306}
+{"step": 72260, "action_loss_avg": 0.0006646512047154829}
+{"step": 72270, "dynamics_loss_avg": 0.030927311163395643}
+{"step": 72270, "action_loss_avg": 0.0011765114730224013}
+{"step": 72280, "dynamics_loss_avg": 0.02907858993858099}
+{"step": 72280, "action_loss_avg": 0.0014838898205198348}
+{"step": 72290, "dynamics_loss_avg": 0.028831092268228532}
+{"step": 72290, "action_loss_avg": 0.0009195530394208618}
+{"step": 72300, "loss": 0.03, "learning_rate": 1.9552309682143622e-05}
+{"step": 72300, "dynamics_loss_avg": 0.018711234722286463}
+{"step": 72300, "action_loss_avg": 0.0009523720917059108}
+{"step": 72310, "dynamics_loss_avg": 0.024279696587473153}
+{"step": 72310, "action_loss_avg": 0.0006462047807872295}
+{"step": 72320, "dynamics_loss_avg": 0.029830699600279332}
+{"step": 72320, "action_loss_avg": 0.0014987451228080317}