|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.9756197333335876, |
|
"min": 0.9529168605804443, |
|
"max": 1.5301482677459717, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 29112.4921875, |
|
"min": 28450.28515625, |
|
"max": 46418.578125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479874.0, |
|
"min": 29952.0, |
|
"max": 479874.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479874.0, |
|
"min": 29952.0, |
|
"max": 479874.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.04790247231721878, |
|
"min": -0.09485263377428055, |
|
"max": -0.0291922464966774, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -11.496593475341797, |
|
"min": -22.859485626220703, |
|
"max": -6.918562412261963, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01858367957174778, |
|
"min": 0.01828259415924549, |
|
"max": 0.35818520188331604, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.4600830078125, |
|
"min": 4.4243879318237305, |
|
"max": 84.889892578125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06743060675037486, |
|
"min": 0.06331922370901613, |
|
"max": 0.0721219398907775, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9440284945052482, |
|
"min": 0.5048535792354425, |
|
"max": 0.981739985554054, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0020660763982658014, |
|
"min": 0.0003246885974566497, |
|
"max": 0.007734341929179578, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.028925069575721222, |
|
"min": 0.0041467015180762295, |
|
"max": 0.05414039350425705, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.0785164500214288e-05, |
|
"min": 2.0785164500214288e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00029099230300300003, |
|
"min": 0.00029099230300300003, |
|
"max": 0.002850516349828, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10692835714285713, |
|
"min": 0.10692835714285713, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.496997, |
|
"min": 1.3773696000000002, |
|
"max": 2.250172, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007021428785714288, |
|
"min": 0.0007021428785714288, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009830000300000004, |
|
"min": 0.009830000300000004, |
|
"max": 0.09505218280000001, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.017350923269987106, |
|
"min": 0.017350923269987106, |
|
"max": 0.26778683066368103, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.24291293323040009, |
|
"min": 0.24291293323040009, |
|
"max": 1.8745079040527344, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 948.8333333333334, |
|
"min": 885.25, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28465.0, |
|
"min": 15984.0, |
|
"max": 33069.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.7494600494702657, |
|
"min": -1.0000000521540642, |
|
"max": -0.3857000474818051, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -22.48380148410797, |
|
"min": -31.996801644563675, |
|
"max": -12.342401519417763, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.7494600494702657, |
|
"min": -1.0000000521540642, |
|
"max": -0.3857000474818051, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -22.48380148410797, |
|
"min": -31.996801644563675, |
|
"max": -12.342401519417763, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.17150917273635666, |
|
"min": 0.17051595891825855, |
|
"max": 5.226827583741397, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.1452751820907, |
|
"min": 5.1452751820907, |
|
"max": 83.62924133986235, |
|
"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": "1670419629", |
|
"python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670420607" |
|
}, |
|
"total": 978.6046048170001, |
|
"count": 1, |
|
"self": 0.42425565700000334, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10552453700006481, |
|
"count": 1, |
|
"self": 0.10552453700006481 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 978.074824623, |
|
"count": 1, |
|
"self": 0.6236130319973654, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.4377899490000345, |
|
"count": 1, |
|
"self": 6.4377899490000345 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 970.9175159580025, |
|
"count": 31577, |
|
"self": 0.6327445240099223, |
|
"children": { |
|
"env_step": { |
|
"total": 632.9329397039892, |
|
"count": 31577, |
|
"self": 577.2544680859412, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 55.29414234104547, |
|
"count": 31577, |
|
"self": 2.2742474350588964, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 53.019894905986575, |
|
"count": 31321, |
|
"self": 18.23082550797949, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 34.789069398007086, |
|
"count": 31321, |
|
"self": 34.789069398007086 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.3843292770025073, |
|
"count": 31577, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 975.6925199249988, |
|
"count": 31577, |
|
"is_parallel": true, |
|
"self": 448.59599664697384, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00192470900014996, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007160790000853012, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012086300000646588, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012086300000646588 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05675902300004054, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005310550002377568, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004589469999700668, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004589469999700668 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05406694999987849, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05406694999987849 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017020709999542305, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004099140003290813, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012921569996251492, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012921569996251492 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 527.096523278025, |
|
"count": 31576, |
|
"is_parallel": true, |
|
"self": 14.090789567986121, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.966035297032704, |
|
"count": 31576, |
|
"is_parallel": true, |
|
"self": 11.966035297032704 |
|
}, |
|
"communicator.exchange": { |
|
"total": 452.24083973399433, |
|
"count": 31576, |
|
"is_parallel": true, |
|
"self": 452.24083973399433 |
|
}, |
|
"steps_from_proto": { |
|
"total": 48.7988586790118, |
|
"count": 31576, |
|
"is_parallel": true, |
|
"self": 11.422131943048498, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 37.3767267359633, |
|
"count": 252608, |
|
"is_parallel": true, |
|
"self": 37.3767267359633 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 337.35183173000337, |
|
"count": 31577, |
|
"self": 1.0555493089673291, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 77.04579664803396, |
|
"count": 31577, |
|
"self": 76.930708557034, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11508809099996142, |
|
"count": 1, |
|
"self": 0.11508809099996142 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 259.2504857730021, |
|
"count": 214, |
|
"self": 95.73136521500828, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 163.5191205579938, |
|
"count": 11388, |
|
"self": 163.5191205579938 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.690002116258256e-07, |
|
"count": 1, |
|
"self": 9.690002116258256e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09590471499996056, |
|
"count": 1, |
|
"self": 0.001459221000004618, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09444549399995594, |
|
"count": 1, |
|
"self": 0.09444549399995594 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |