|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.41358017921447754, |
|
"min": 0.38993197679519653, |
|
"max": 1.42996084690094, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 12414.0224609375, |
|
"min": 11644.017578125, |
|
"max": 43379.29296875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989901.0, |
|
"min": 29952.0, |
|
"max": 989901.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989901.0, |
|
"min": 29952.0, |
|
"max": 989901.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7401013374328613, |
|
"min": -0.09754466265439987, |
|
"max": 0.7401013374328613, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 219.81008911132812, |
|
"min": -23.41071891784668, |
|
"max": 219.81008911132812, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.02549360878765583, |
|
"min": 0.003851822344586253, |
|
"max": 0.7033986449241638, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 7.571601867675781, |
|
"min": 0.9899183511734009, |
|
"max": 166.70547485351562, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0676898630846861, |
|
"min": 0.06459672924473933, |
|
"max": 0.07350445102617544, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0153479462702915, |
|
"min": 0.505004010894774, |
|
"max": 1.0290623143664561, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016136129894423198, |
|
"min": 0.0015388093025537023, |
|
"max": 0.01637205031909703, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.24204194841634796, |
|
"min": 0.016926902328090725, |
|
"max": 0.24411679549181525, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.479637506820002e-06, |
|
"min": 7.479637506820002e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011219456260230004, |
|
"min": 0.00011219456260230004, |
|
"max": 0.0034903297365567994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10249318000000002, |
|
"min": 0.10249318000000002, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5373977000000003, |
|
"min": 1.3886848, |
|
"max": 2.5266442000000007, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025906868200000014, |
|
"min": 0.00025906868200000014, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003886030230000002, |
|
"min": 0.003886030230000002, |
|
"max": 0.11635797568, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.012334185652434826, |
|
"min": 0.012258809991180897, |
|
"max": 0.6404990553855896, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1850127875804901, |
|
"min": 0.1716233342885971, |
|
"max": 4.483493328094482, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 244.64406779661016, |
|
"min": 244.64406779661016, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28868.0, |
|
"min": 15984.0, |
|
"max": 33564.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.755355921210879, |
|
"min": -1.0000000521540642, |
|
"max": 1.755355921210879, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 207.13199870288372, |
|
"min": -28.58000161498785, |
|
"max": 207.13199870288372, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.755355921210879, |
|
"min": -1.0000000521540642, |
|
"max": 1.755355921210879, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 207.13199870288372, |
|
"min": -28.58000161498785, |
|
"max": 207.13199870288372, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.031063366807618384, |
|
"min": 0.031063366807618384, |
|
"max": 12.83260870166123, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.6654772832989693, |
|
"min": 3.6654772832989693, |
|
"max": 205.32173922657967, |
|
"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": "1657918978", |
|
"python_version": "3.6.9 (default, Mar 15 2022, 13:55:28) \n[GCC 8.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.18.5", |
|
"end_time_seconds": "1657920813" |
|
}, |
|
"total": 1835.534962362999, |
|
"count": 1, |
|
"self": 0.27018346799741266, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.014960827000322752, |
|
"count": 1, |
|
"self": 0.014960827000322752 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1835.2498180680013, |
|
"count": 1, |
|
"self": 1.4931210819959233, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.7412118799984455, |
|
"count": 1, |
|
"self": 1.7412118799984455 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1831.9644836230036, |
|
"count": 64262, |
|
"self": 1.3356513751932653, |
|
"children": { |
|
"env_step": { |
|
"total": 1103.3998733392073, |
|
"count": 64262, |
|
"self": 1026.0440612346138, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 76.48616008808312, |
|
"count": 64262, |
|
"self": 3.511202939298528, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 72.9749571487846, |
|
"count": 62574, |
|
"self": 14.95561928774623, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 58.019337861038366, |
|
"count": 62574, |
|
"self": 58.019337861038366 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.869652016510372, |
|
"count": 64262, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1831.8139931432816, |
|
"count": 64262, |
|
"is_parallel": true, |
|
"self": 895.3981945827618, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002930039001512341, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0016086690011434257, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013213700003689155, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013213700003689155 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.032493468999746256, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002630399976624176, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00045806999696651474, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045806999696651474 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.030669170002511237, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.030669170002511237 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0011031890026060864, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002713490066525992, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008318399959534872, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008318399959534872 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 936.4157985605198, |
|
"count": 64261, |
|
"is_parallel": true, |
|
"self": 16.50556306400904, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.00767444599478, |
|
"count": 64261, |
|
"is_parallel": true, |
|
"self": 12.00767444599478 |
|
}, |
|
"communicator.exchange": { |
|
"total": 843.9158501789898, |
|
"count": 64261, |
|
"is_parallel": true, |
|
"self": 843.9158501789898 |
|
}, |
|
"steps_from_proto": { |
|
"total": 63.98671087152616, |
|
"count": 64261, |
|
"is_parallel": true, |
|
"self": 13.251265531023819, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 50.73544534050234, |
|
"count": 514088, |
|
"is_parallel": true, |
|
"self": 50.73544534050234 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 727.2289589086031, |
|
"count": 64262, |
|
"self": 3.0074682592312456, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 127.86817325334778, |
|
"count": 64262, |
|
"self": 127.75923370034434, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10893955300343805, |
|
"count": 2, |
|
"self": 0.10893955300343805 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 596.3533173960241, |
|
"count": 453, |
|
"self": 204.11661663311315, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 392.2367007629109, |
|
"count": 22812, |
|
"self": 392.2367007629109 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.00002453615889e-07, |
|
"count": 1, |
|
"self": 8.00002453615889e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.05100068300089333, |
|
"count": 1, |
|
"self": 0.001038469999912195, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.04996221300098114, |
|
"count": 1, |
|
"self": 0.04996221300098114 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |