| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5051900744438171, |
| "min": 0.5051900744438171, |
| "max": 1.4581128358840942, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 15179.951171875, |
| "min": 15179.951171875, |
| "max": 44233.3125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989897.0, |
| "min": 29894.0, |
| "max": 989897.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989897.0, |
| "min": 29894.0, |
| "max": 989897.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.2487221360206604, |
| "min": -0.10975060611963272, |
| "max": 0.25868022441864014, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 64.66775512695312, |
| "min": -26.559646606445312, |
| "max": 65.96345520019531, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.17655110359191895, |
| "min": -0.31895631551742554, |
| "max": 0.22103823721408844, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -45.90328598022461, |
| "min": -81.3338623046875, |
| "max": 53.27021408081055, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06898486472099515, |
| "min": 0.06515650913934222, |
| "max": 0.0729250141645882, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.965788106093932, |
| "min": 0.5809412502324751, |
| "max": 1.0904194857381906, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015495144149084077, |
| "min": 0.0005266084795960589, |
| "max": 0.023456230520322505, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21693201808717708, |
| "min": 0.006845910234748765, |
| "max": 0.35184345780483756, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.273661861192861e-06, |
| "min": 7.273661861192861e-06, |
| "max": 0.0002947701017433, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010183126605670005, |
| "min": 0.00010183126605670005, |
| "max": 0.0035082698305767997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10242452142857143, |
| "min": 0.10242452142857143, |
| "max": 0.1982567, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4339433000000001, |
| "min": 1.4339433000000001, |
| "max": 2.5694231999999997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025220969071428593, |
| "min": 0.00025220969071428593, |
| "max": 0.00982584433, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035309356700000028, |
| "min": 0.0035309356700000028, |
| "max": 0.11696537767999998, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.009560888633131981, |
| "min": 0.009329685010015965, |
| "max": 0.3751799762248993, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.13385243713855743, |
| "min": 0.13070960342884064, |
| "max": 3.0014398097991943, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 561.8888888888889, |
| "min": 561.8888888888889, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30342.0, |
| "min": 17332.0, |
| "max": 33739.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.0675999667081568, |
| "min": -0.9999000513926148, |
| "max": 1.0675999667081568, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 57.65039820224047, |
| "min": -31.996801644563675, |
| "max": 57.65039820224047, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.0675999667081568, |
| "min": -0.9999000513926148, |
| "max": 1.0675999667081568, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 57.65039820224047, |
| "min": -31.996801644563675, |
| "max": 57.65039820224047, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.05554253103521963, |
| "min": 0.05554253103521963, |
| "max": 7.033807673439798, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.99929667590186, |
| "min": 2.8350150443620805, |
| "max": 126.60853812191635, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1704015333", |
| "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
| "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": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.1.2+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1704017582" |
| }, |
| "total": 2248.932787756, |
| "count": 1, |
| "self": 0.4933229630000824, |
| "children": { |
| "run_training.setup": { |
| "total": 0.058000097999979516, |
| "count": 1, |
| "self": 0.058000097999979516 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2248.381464695, |
| "count": 1, |
| "self": 1.5899396879872256, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.9022496499999306, |
| "count": 1, |
| "self": 3.9022496499999306 |
| }, |
| "TrainerController.advance": { |
| "total": 2242.800112424013, |
| "count": 63452, |
| "self": 1.7124911399419034, |
| "children": { |
| "env_step": { |
| "total": 1594.7246473900468, |
| "count": 63452, |
| "self": 1455.2875197899486, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 138.51344353506022, |
| "count": 63452, |
| "self": 4.944456437999747, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 133.56898709706047, |
| "count": 62568, |
| "self": 133.56898709706047 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.9236840650379463, |
| "count": 63452, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2243.0319351120465, |
| "count": 63452, |
| "is_parallel": true, |
| "self": 913.1511439750966, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.007315004000020053, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0037803610000537446, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0035346429999663087, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0035346429999663087 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04736910100007208, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006474710000929917, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004914889999554362, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004914889999554362 |
| }, |
| "communicator.exchange": { |
| "total": 0.044555703000014546, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.044555703000014546 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016744380000091041, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004093840002497018, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012650539997594024, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012650539997594024 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1329.88079113695, |
| "count": 63451, |
| "is_parallel": true, |
| "self": 36.94967154988035, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 24.728953440050304, |
| "count": 63451, |
| "is_parallel": true, |
| "self": 24.728953440050304 |
| }, |
| "communicator.exchange": { |
| "total": 1167.0420609079702, |
| "count": 63451, |
| "is_parallel": true, |
| "self": 1167.0420609079702 |
| }, |
| "steps_from_proto": { |
| "total": 101.16010523904924, |
| "count": 63451, |
| "is_parallel": true, |
| "self": 20.426797689050318, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 80.73330754999893, |
| "count": 507608, |
| "is_parallel": true, |
| "self": 80.73330754999893 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 646.3629738940244, |
| "count": 63452, |
| "self": 3.0134323490100314, |
| "children": { |
| "process_trajectory": { |
| "total": 129.01817224601086, |
| "count": 63452, |
| "self": 128.8183325930106, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.19983965300025375, |
| "count": 2, |
| "self": 0.19983965300025375 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 514.3313692990035, |
| "count": 451, |
| "self": 303.6601458060187, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 210.67122349298484, |
| "count": 22767, |
| "self": 210.67122349298484 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0769999789772555e-06, |
| "count": 1, |
| "self": 1.0769999789772555e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08916185599991877, |
| "count": 1, |
| "self": 0.001354629000161367, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0878072269997574, |
| "count": 1, |
| "self": 0.0878072269997574 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
