|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.19957461953163147, |
|
"min": 0.19038215279579163, |
|
"max": 1.0497084856033325, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5996.818359375, |
|
"min": 5751.06396484375, |
|
"max": 28449.53515625, |
|
"count": 99 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999989.0, |
|
"min": 59944.0, |
|
"max": 2999989.0, |
|
"count": 99 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999989.0, |
|
"min": 59944.0, |
|
"max": 2999989.0, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7243598103523254, |
|
"min": -0.1040952205657959, |
|
"max": 0.8301359415054321, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 216.58358764648438, |
|
"min": -25.08694839477539, |
|
"max": 254.3348388671875, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.021130813285708427, |
|
"min": -0.034339264035224915, |
|
"max": 0.2802739143371582, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 6.318113327026367, |
|
"min": -9.992725372314453, |
|
"max": 44.27830505371094, |
|
"count": 99 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06521453087657897, |
|
"min": 0.06306012758470914, |
|
"max": 0.07484804215992304, |
|
"count": 99 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9782179631486846, |
|
"min": 0.2767886349262284, |
|
"max": 1.0822987864279032, |
|
"count": 99 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0153679837349854, |
|
"min": 0.00010339826174093141, |
|
"max": 0.015760882191465327, |
|
"count": 99 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.230519756024781, |
|
"min": 0.0014475756643730396, |
|
"max": 0.230519756024781, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.4864461712177802e-06, |
|
"min": 1.4864461712177802e-06, |
|
"max": 0.00029474975175008326, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.2296692568266704e-05, |
|
"min": 2.2296692568266704e-05, |
|
"max": 0.004010408363197233, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1004954488888889, |
|
"min": 0.1004954488888889, |
|
"max": 0.19824991666666664, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5074317333333334, |
|
"min": 0.7929996666666665, |
|
"max": 2.736802766666666, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.949534400000008e-05, |
|
"min": 5.949534400000008e-05, |
|
"max": 0.009825166675, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008924301600000012, |
|
"min": 0.0008924301600000012, |
|
"max": 0.13368659639, |
|
"count": 99 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007170303259044886, |
|
"min": 0.007170303259044886, |
|
"max": 0.16945092380046844, |
|
"count": 99 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.10755454748868942, |
|
"min": 0.1009792760014534, |
|
"max": 1.5497738122940063, |
|
"count": 99 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 250.3252032520325, |
|
"min": 211.5281690140845, |
|
"max": 999.0, |
|
"count": 99 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30790.0, |
|
"min": 15438.0, |
|
"max": 33296.0, |
|
"count": 99 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6835426110468927, |
|
"min": -0.9997677937630685, |
|
"max": 1.7884718203838443, |
|
"count": 99 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 205.3921985477209, |
|
"min": -31.992401659488678, |
|
"max": 253.96299849450588, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6835426110468927, |
|
"min": -0.9997677937630685, |
|
"max": 1.7884718203838443, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 205.3921985477209, |
|
"min": -31.992401659488678, |
|
"max": 253.96299849450588, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.018851242525148547, |
|
"min": 0.016631738800050453, |
|
"max": 1.6788370145054965, |
|
"count": 99 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.2998515880681225, |
|
"min": 2.122373921563849, |
|
"max": 32.9552084505558, |
|
"count": 99 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 99 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 99 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1656923154", |
|
"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 --resume --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": "1656929704" |
|
}, |
|
"total": 6549.990268541, |
|
"count": 1, |
|
"self": 0.49137349400007224, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04358492200026376, |
|
"count": 1, |
|
"self": 0.04358492200026376 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6549.455310124999, |
|
"count": 1, |
|
"self": 4.240622910352613, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.456813679999868, |
|
"count": 1, |
|
"self": 6.456813679999868 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6538.659631376648, |
|
"count": 191263, |
|
"self": 4.322407115647366, |
|
"children": { |
|
"env_step": { |
|
"total": 4426.247812239084, |
|
"count": 191263, |
|
"self": 4106.3025222477045, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 317.6402370843052, |
|
"count": 191263, |
|
"self": 13.966380570244382, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 303.67385651406084, |
|
"count": 184787, |
|
"self": 104.54375911802708, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 199.13009739603376, |
|
"count": 184787, |
|
"self": 199.13009739603376 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.305052907074696, |
|
"count": 191263, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6538.218747065998, |
|
"count": 191263, |
|
"is_parallel": true, |
|
"self": 2733.737740221955, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001918997999837302, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007346469997173699, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001184351000119932, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001184351000119932 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04378057499980059, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00048794099984661443, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00047037400008775876, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00047037400008775876 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.041191875000095024, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.041191875000095024 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001630384999771195, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00040700099953028257, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012233840002409124, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012233840002409124 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 3804.4810068440433, |
|
"count": 191262, |
|
"is_parallel": true, |
|
"self": 82.77840285848424, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 67.83800751053377, |
|
"count": 191262, |
|
"is_parallel": true, |
|
"self": 67.83800751053377 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3376.0346072972034, |
|
"count": 191262, |
|
"is_parallel": true, |
|
"self": 3376.0346072972034 |
|
}, |
|
"steps_from_proto": { |
|
"total": 277.829989177822, |
|
"count": 191262, |
|
"is_parallel": true, |
|
"self": 68.9166901651729, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 208.91329901264908, |
|
"count": 1530096, |
|
"is_parallel": true, |
|
"self": 208.91329901264908 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2108.089412021917, |
|
"count": 191263, |
|
"self": 8.245916585592113, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 485.2914323192931, |
|
"count": 191263, |
|
"self": 484.69187374029434, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5995585789987672, |
|
"count": 6, |
|
"self": 0.5995585789987672 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1614.5520631170316, |
|
"count": 1388, |
|
"self": 630.2288148848261, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 984.3232482322055, |
|
"count": 67347, |
|
"self": 984.3232482322055 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0929998097708449e-06, |
|
"count": 1, |
|
"self": 1.0929998097708449e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09824106499945628, |
|
"count": 1, |
|
"self": 0.0020509370006038807, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0961901279988524, |
|
"count": 1, |
|
"self": 0.0961901279988524 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |