| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.15378662943840027, |
| "min": 0.14404195547103882, |
| "max": 1.6030467748641968, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4606.21728515625, |
| "min": 4390.4140625, |
| "max": 51297.49609375, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999817.0, |
| "min": 29912.0, |
| "max": 2999817.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999817.0, |
| "min": 29912.0, |
| "max": 2999817.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8220644593238831, |
| "min": 0.01450348924845457, |
| "max": 0.8746668100357056, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 144.683349609375, |
| "min": 1.8419431447982788, |
| "max": 161.16427612304688, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.009445223025977612, |
| "min": 0.0006061827298253775, |
| "max": 0.5029016733169556, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 1.6623592376708984, |
| "min": 0.10244487971067429, |
| "max": 60.85110092163086, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 196.5857142857143, |
| "min": 192.59354838709677, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 27522.0, |
| "min": 15984.0, |
| "max": 33040.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7753256910613604, |
| "min": -1.0000000596046448, |
| "max": 1.8073096536820934, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 248.54559674859047, |
| "min": -29.07160195708275, |
| "max": 280.1329963207245, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7753256910613604, |
| "min": -1.0000000596046448, |
| "max": 1.8073096536820934, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 248.54559674859047, |
| "min": -29.07160195708275, |
| "max": 280.1329963207245, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.015794421898733292, |
| "min": 0.015794421898733292, |
| "max": 19.355570865714032, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.211219065822661, |
| "min": 2.211219065822661, |
| "max": 445.17812991142273, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.03657035482756328, |
| "min": 0.02963721946143778, |
| "max": 0.04222333023133568, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.03657035482756328, |
| "min": 0.029650880441477057, |
| "max": 0.07956579182386228, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014543148496886715, |
| "min": 0.002317265165651119, |
| "max": 0.02763955980921403, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.014543148496886715, |
| "min": 0.004634530331302238, |
| "max": 0.03412364292307757, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.3679995440333222e-06, |
| "min": 1.3679995440333222e-06, |
| "max": 0.0002979904006698667, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 1.3679995440333222e-06, |
| "min": 1.3679995440333222e-06, |
| "max": 0.0005859845046718333, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10045596666666667, |
| "min": 0.10045596666666667, |
| "max": 0.19933013333333335, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 0.10045596666666667, |
| "min": 0.10045596666666667, |
| "max": 0.39532816666666676, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 2.3633403333333216e-05, |
| "min": 2.3633403333333216e-05, |
| "max": 0.0029799709866666674, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 2.3633403333333216e-05, |
| "min": 2.3633403333333216e-05, |
| "max": 0.005860312183333332, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.026398826390504837, |
| "min": 0.02608591876924038, |
| "max": 4.097460746765137, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.026398826390504837, |
| "min": 0.02608591876924038, |
| "max": 4.097460746765137, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1765807204", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1765814405" |
| }, |
| "total": 7200.533529934999, |
| "count": 1, |
| "self": 0.4797982000000047, |
| "children": { |
| "run_training.setup": { |
| "total": 0.022678635999909602, |
| "count": 1, |
| "self": 0.022678635999909602 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7200.031053098999, |
| "count": 1, |
| "self": 4.134616134208045, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.079387463999865, |
| "count": 1, |
| "self": 2.079387463999865 |
| }, |
| "TrainerController.advance": { |
| "total": 7193.713240719792, |
| "count": 196512, |
| "self": 4.240567009994265, |
| "children": { |
| "env_step": { |
| "total": 5247.806457977811, |
| "count": 196512, |
| "self": 4748.291023282955, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 497.1344659299634, |
| "count": 196512, |
| "self": 13.261644775900095, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 483.87282115406333, |
| "count": 187601, |
| "self": 483.87282115406333 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.380968764892259, |
| "count": 196512, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7180.3410972360825, |
| "count": 196512, |
| "is_parallel": true, |
| "self": 2767.749860874156, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0017397510000591865, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005661360009980854, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011736149990611011, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011736149990611011 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04724372700002277, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005285479996928188, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005041770000389079, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005041770000389079 |
| }, |
| "communicator.exchange": { |
| "total": 0.04465668100010589, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04465668100010589 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015543210001851548, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003285800007688522, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012257409994163027, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012257409994163027 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 4412.591236361926, |
| "count": 196511, |
| "is_parallel": true, |
| "self": 98.11327869975139, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 65.99152841016348, |
| "count": 196511, |
| "is_parallel": true, |
| "self": 65.99152841016348 |
| }, |
| "communicator.exchange": { |
| "total": 3945.18902613913, |
| "count": 196511, |
| "is_parallel": true, |
| "self": 3945.18902613913 |
| }, |
| "steps_from_proto": { |
| "total": 303.29740311288106, |
| "count": 196511, |
| "is_parallel": true, |
| "self": 63.11231778451702, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 240.18508532836404, |
| "count": 1572088, |
| "is_parallel": true, |
| "self": 240.18508532836404 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1941.666215731987, |
| "count": 196512, |
| "self": 8.4303283904801, |
| "children": { |
| "process_trajectory": { |
| "total": 371.757702294507, |
| "count": 196512, |
| "self": 371.1589351945081, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.598767099998895, |
| "count": 6, |
| "self": 0.598767099998895 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1561.478185047, |
| "count": 180, |
| "self": 1167.131613064038, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 394.3465719829619, |
| "count": 28965, |
| "self": 394.3465719829619 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.010000212583691e-07, |
| "count": 1, |
| "self": 9.010000212583691e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10380787999929453, |
| "count": 1, |
| "self": 0.0014720250001118984, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10233585499918263, |
| "count": 1, |
| "self": 0.10233585499918263 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
