|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5862696766853333, |
|
"min": 0.5862696766853333, |
|
"max": 1.3177770376205444, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 17681.892578125, |
|
"min": 17681.892578125, |
|
"max": 39976.0859375, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479997.0, |
|
"min": 29952.0, |
|
"max": 479997.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479997.0, |
|
"min": 29952.0, |
|
"max": 479997.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.05206555873155594, |
|
"min": -0.0986831784248352, |
|
"max": -0.009503819979727268, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -12.703996658325195, |
|
"min": -23.881328582763672, |
|
"max": -2.2524054050445557, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.028906242921948433, |
|
"min": 0.027536708861589432, |
|
"max": 0.3900533616542816, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 7.053123474121094, |
|
"min": 6.636346817016602, |
|
"max": 94.00286102294922, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07064599550991191, |
|
"min": 0.06571676671220675, |
|
"max": 0.0710426947901284, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9890439371387667, |
|
"min": 0.48011670930039446, |
|
"max": 0.9890439371387667, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0034727032462071564, |
|
"min": 0.0004417510743554429, |
|
"max": 0.010656321825284355, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.04861784544690019, |
|
"min": 0.005742763966620758, |
|
"max": 0.07459425277699049, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.130167861375714e-05, |
|
"min": 2.130167861375714e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00029822350059259995, |
|
"min": 0.00029822350059259995, |
|
"max": 0.003082917272361, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10710052857142859, |
|
"min": 0.10710052857142859, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4994074000000002, |
|
"min": 1.3773696000000002, |
|
"max": 2.327639, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007193428042857143, |
|
"min": 0.0007193428042857143, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.01007079926, |
|
"min": 0.01007079926, |
|
"max": 0.1027911361, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.029400188475847244, |
|
"min": 0.029400188475847244, |
|
"max": 0.5339993834495544, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.411602646112442, |
|
"min": 0.411602646112442, |
|
"max": 3.7379958629608154, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 890.1764705882352, |
|
"min": 890.1764705882352, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30266.0, |
|
"min": 15984.0, |
|
"max": 32491.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.4938286168234689, |
|
"min": -1.0000000521540642, |
|
"max": -0.41855762176441424, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -17.28400158882141, |
|
"min": -31.998801663517952, |
|
"max": -13.81240151822567, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.4938286168234689, |
|
"min": -1.0000000521540642, |
|
"max": -0.41855762176441424, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -17.28400158882141, |
|
"min": -31.998801663517952, |
|
"max": -13.81240151822567, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.27327577201649544, |
|
"min": 0.27327577201649544, |
|
"max": 10.826760705560446, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 9.564652020577341, |
|
"min": 9.564652020577341, |
|
"max": 173.22817128896713, |
|
"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": "1663595799", |
|
"python_version": "3.9.13 (main, May 23 2022, 22:01:06) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/usr/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", |
|
"mlagents_envs_version": "0.29.0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1663596744" |
|
}, |
|
"total": 944.8244097160641, |
|
"count": 1, |
|
"self": 0.6296948781237006, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.028697775909677148, |
|
"count": 1, |
|
"self": 0.028697775909677148 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 944.1660170620307, |
|
"count": 1, |
|
"self": 0.8002304707188159, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 8.708324674982578, |
|
"count": 1, |
|
"self": 8.708324674982578 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 933.8847909134347, |
|
"count": 31559, |
|
"self": 0.8637832710519433, |
|
"children": { |
|
"env_step": { |
|
"total": 593.8900285561103, |
|
"count": 31559, |
|
"self": 533.5406624246389, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 59.82513234624639, |
|
"count": 31559, |
|
"self": 2.944757096003741, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 56.88037525024265, |
|
"count": 31295, |
|
"self": 17.799992226762697, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 39.08038302347995, |
|
"count": 31295, |
|
"self": 39.08038302347995 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.5242337852250785, |
|
"count": 31559, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 941.0872891475447, |
|
"count": 31559, |
|
"is_parallel": true, |
|
"self": 458.2745265583508, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001939554000273347, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006597507745027542, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012798032257705927, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012798032257705927 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04375370079651475, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00038935081101953983, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00030633690766990185, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00030633690766990185 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.041946134995669127, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.041946134995669127 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0011118780821561813, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00029271887615323067, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008191592060029507, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008191592060029507 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 482.8127625891939, |
|
"count": 31558, |
|
"is_parallel": true, |
|
"self": 11.081325121223927, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 7.323908892460167, |
|
"count": 31558, |
|
"is_parallel": true, |
|
"self": 7.323908892460167 |
|
}, |
|
"communicator.exchange": { |
|
"total": 432.3006654770579, |
|
"count": 31558, |
|
"is_parallel": true, |
|
"self": 432.3006654770579 |
|
}, |
|
"steps_from_proto": { |
|
"total": 32.10686309845187, |
|
"count": 31558, |
|
"is_parallel": true, |
|
"self": 8.563154781702906, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 23.543708316748962, |
|
"count": 252464, |
|
"is_parallel": true, |
|
"self": 23.543708316748962 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 339.1309790862724, |
|
"count": 31559, |
|
"self": 1.532571898540482, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 75.60893396427855, |
|
"count": 31559, |
|
"self": 74.78607389726676, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.8228600670117885, |
|
"count": 1, |
|
"self": 0.8228600670117885 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 261.9894732234534, |
|
"count": 210, |
|
"self": 97.99888103501871, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 163.99059218843468, |
|
"count": 11394, |
|
"self": 163.99059218843468 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.6998965293169022e-06, |
|
"count": 1, |
|
"self": 1.6998965293169022e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.7726693029981107, |
|
"count": 1, |
|
"self": 0.001879665069282055, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.7707896379288286, |
|
"count": 1, |
|
"self": 0.7707896379288286 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |