|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7965838313102722, |
|
"min": 0.663320779800415, |
|
"max": 1.3905432224273682, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 23961.2421875, |
|
"min": 20058.8203125, |
|
"max": 42183.51953125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479929.0, |
|
"min": 29952.0, |
|
"max": 479929.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479929.0, |
|
"min": 29952.0, |
|
"max": 479929.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.019923768937587738, |
|
"min": -0.0837169662117958, |
|
"max": 0.020291665568947792, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 4.901247024536133, |
|
"min": -20.17578887939453, |
|
"max": 4.9917497634887695, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.022518347948789597, |
|
"min": 0.022518347948789597, |
|
"max": 0.5150927305221558, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.53951358795166, |
|
"min": 5.53951358795166, |
|
"max": 122.07697296142578, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0654273441651063, |
|
"min": 0.0649713463319574, |
|
"max": 0.07310435739528531, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9814101624765946, |
|
"min": 0.4880576308018155, |
|
"max": 1.0234610035339944, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0061645034963612785, |
|
"min": 0.0006571549417035166, |
|
"max": 0.007849758718613334, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.09246755244541918, |
|
"min": 0.007228704358738683, |
|
"max": 0.09246755244541918, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.1033092988999998e-05, |
|
"min": 2.1033092988999998e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00031549639483499994, |
|
"min": 0.00031549639483499994, |
|
"max": 0.0030679377773542003, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10701100000000001, |
|
"min": 0.10701100000000001, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.6051650000000002, |
|
"min": 1.3773696000000002, |
|
"max": 2.4226457999999997, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007103989000000001, |
|
"min": 0.0007103989000000001, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0106559835, |
|
"min": 0.0106559835, |
|
"max": 0.10230231541999998, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.023372935131192207, |
|
"min": 0.023372935131192207, |
|
"max": 0.49998384714126587, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.35059401392936707, |
|
"min": 0.35059401392936707, |
|
"max": 3.499886989593506, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 872.9722222222222, |
|
"min": 850.7, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31427.0, |
|
"min": 15984.0, |
|
"max": 33143.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.011870313133742358, |
|
"min": -1.0000000521540642, |
|
"max": -0.011870313133742358, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -0.43920158594846725, |
|
"min": -31.99760165810585, |
|
"max": -0.43920158594846725, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.011870313133742358, |
|
"min": -1.0000000521540642, |
|
"max": -0.011870313133742358, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -0.43920158594846725, |
|
"min": -31.99760165810585, |
|
"max": -0.43920158594846725, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.21345641856031441, |
|
"min": 0.21345641856031441, |
|
"max": 9.945490904152393, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 7.8978874867316335, |
|
"min": 7.397603433346376, |
|
"max": 159.1278544664383, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1660382897", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", |
|
"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": "1.21.6", |
|
"end_time_seconds": "1660383911" |
|
}, |
|
"total": 1014.232996091, |
|
"count": 1, |
|
"self": 0.48038856699997723, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.05379294299996218, |
|
"count": 1, |
|
"self": 0.05379294299996218 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1013.6988145810001, |
|
"count": 1, |
|
"self": 0.802455990009662, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.534729317000028, |
|
"count": 1, |
|
"self": 10.534729317000028 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1002.2587386829902, |
|
"count": 31589, |
|
"self": 0.8254121539736161, |
|
"children": { |
|
"env_step": { |
|
"total": 634.4669941090184, |
|
"count": 31589, |
|
"self": 575.1914190409902, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 58.84729483303806, |
|
"count": 31589, |
|
"self": 2.491730585031064, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 56.355564248007, |
|
"count": 31314, |
|
"self": 18.860514689019055, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 37.495049558987944, |
|
"count": 31314, |
|
"self": 37.495049558987944 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.4282802349900976, |
|
"count": 31589, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1011.3993085610101, |
|
"count": 31589, |
|
"is_parallel": true, |
|
"self": 492.2511184940088, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005240025999910358, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003857050999954481, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013829749999558771, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013829749999558771 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.049120291000008365, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005129190000161543, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004982819999668209, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004982819999668209 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0461753319999616, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0461753319999616 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.00193375800006379, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005093350000606733, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014244230000031166, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014244230000031166 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 519.1481900670013, |
|
"count": 31588, |
|
"is_parallel": true, |
|
"self": 14.451164829974005, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.879989169000623, |
|
"count": 31588, |
|
"is_parallel": true, |
|
"self": 12.879989169000623 |
|
}, |
|
"communicator.exchange": { |
|
"total": 441.30127427002253, |
|
"count": 31588, |
|
"is_parallel": true, |
|
"self": 441.30127427002253 |
|
}, |
|
"steps_from_proto": { |
|
"total": 50.51576179800418, |
|
"count": 31588, |
|
"is_parallel": true, |
|
"self": 12.759855889963774, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 37.755905908040404, |
|
"count": 252704, |
|
"is_parallel": true, |
|
"self": 37.755905908040404 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 366.96633241999814, |
|
"count": 31589, |
|
"self": 1.381635942995672, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 87.65727581200065, |
|
"count": 31589, |
|
"self": 87.49529295300079, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1619828589998633, |
|
"count": 1, |
|
"self": 0.1619828589998633 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 277.9274206650018, |
|
"count": 216, |
|
"self": 109.14522085300916, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 168.78219981199265, |
|
"count": 11397, |
|
"self": 168.78219981199265 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.2220000371598871e-06, |
|
"count": 1, |
|
"self": 1.2220000371598871e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10288936900019507, |
|
"count": 1, |
|
"self": 0.0016921870001169736, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1011971820000781, |
|
"count": 1, |
|
"self": 0.1011971820000781 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |