|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7718034982681274, |
|
"min": 0.769055187702179, |
|
"max": 1.3696790933609009, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 22919.4765625, |
|
"min": 22919.4765625, |
|
"max": 41550.5859375, |
|
"count": 22 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 659955.0, |
|
"min": 29952.0, |
|
"max": 659955.0, |
|
"count": 22 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 659955.0, |
|
"min": 29952.0, |
|
"max": 659955.0, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.3880106210708618, |
|
"min": -0.11473724246025085, |
|
"max": 0.3880106210708618, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 102.82281494140625, |
|
"min": -27.536937713623047, |
|
"max": 102.82281494140625, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.00528643187135458, |
|
"min": 0.00528643187135458, |
|
"max": 0.5329198241233826, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.4009044170379639, |
|
"min": 1.4009044170379639, |
|
"max": 126.30199432373047, |
|
"count": 22 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0674748248683976, |
|
"min": 0.06509932343631615, |
|
"max": 0.07344120107119946, |
|
"count": 22 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9446475481575665, |
|
"min": 0.48254589916487234, |
|
"max": 1.037305413453164, |
|
"count": 22 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.013391631856523289, |
|
"min": 0.0008747547597472183, |
|
"max": 0.015420653826373898, |
|
"count": 22 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.18748284599132606, |
|
"min": 0.012246566636461056, |
|
"max": 0.18748284599132606, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 0.00023552407863483804, |
|
"min": 0.00023552407863483804, |
|
"max": 0.00029838354339596195, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0032973371008877326, |
|
"min": 0.0020886848037717336, |
|
"max": 0.0040107099630967, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.17850801904761907, |
|
"min": 0.17850801904761907, |
|
"max": 0.19946118095238097, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 2.4991122666666667, |
|
"min": 1.3962282666666668, |
|
"max": 2.7369033000000003, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.007852951102857142, |
|
"min": 0.007852951102857142, |
|
"max": 0.009946171977142856, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.10994131543999999, |
|
"min": 0.06962320384, |
|
"max": 0.13369663967, |
|
"count": 22 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010041001252830029, |
|
"min": 0.010041001252830029, |
|
"max": 0.590167224407196, |
|
"count": 22 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14057402312755585, |
|
"min": 0.14057402312755585, |
|
"max": 4.131170749664307, |
|
"count": 22 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 468.7647058823529, |
|
"min": 468.7647058823529, |
|
"max": 999.0, |
|
"count": 22 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31876.0, |
|
"min": 15984.0, |
|
"max": 32719.0, |
|
"count": 22 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.266444089329418, |
|
"min": -1.0000000521540642, |
|
"max": 1.3186524323508388, |
|
"count": 22 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 86.11819807440042, |
|
"min": -28.74720162153244, |
|
"max": 86.11819807440042, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.266444089329418, |
|
"min": -1.0000000521540642, |
|
"max": 1.3186524323508388, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 86.11819807440042, |
|
"min": -28.74720162153244, |
|
"max": 86.11819807440042, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.0486753513379132, |
|
"min": 0.0486753513379132, |
|
"max": 13.090168526396155, |
|
"count": 22 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.309923890978098, |
|
"min": 3.182563574271626, |
|
"max": 209.44269642233849, |
|
"count": 22 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 22 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 22 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1659982512", |
|
"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": "1659983984" |
|
}, |
|
"total": 1472.6413112869998, |
|
"count": 1, |
|
"self": 0.3613817329999165, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.17209062500000982, |
|
"count": 1, |
|
"self": 0.17209062500000982 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1472.1078389289999, |
|
"count": 1, |
|
"self": 1.1836729120070686, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 12.174847659999955, |
|
"count": 1, |
|
"self": 12.174847659999955 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1458.5779057439922, |
|
"count": 42436, |
|
"self": 1.2518434319845255, |
|
"children": { |
|
"env_step": { |
|
"total": 922.4360542100036, |
|
"count": 42436, |
|
"self": 837.172228768038, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 84.63412457599122, |
|
"count": 42436, |
|
"self": 3.611470007965181, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 81.02265456802604, |
|
"count": 41898, |
|
"self": 26.933642801973747, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 54.089011766052295, |
|
"count": 41898, |
|
"self": 54.089011766052295 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6297008659743142, |
|
"count": 42435, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1469.1872678530383, |
|
"count": 42435, |
|
"is_parallel": true, |
|
"self": 712.4351316240399, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.010425950000012563, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00644375400008812, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003982195999924443, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003982195999924443 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.050613548000001174, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005365579999079273, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005165820000456733, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005165820000456733 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04757401999995636, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04757401999995636 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0019863880000912104, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046808300010070525, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015183049999905052, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015183049999905052 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 756.7521362289984, |
|
"count": 42434, |
|
"is_parallel": true, |
|
"self": 21.030148722005947, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 17.69013084297376, |
|
"count": 42434, |
|
"is_parallel": true, |
|
"self": 17.69013084297376 |
|
}, |
|
"communicator.exchange": { |
|
"total": 647.3793244129985, |
|
"count": 42434, |
|
"is_parallel": true, |
|
"self": 647.3793244129985 |
|
}, |
|
"steps_from_proto": { |
|
"total": 70.65253225102026, |
|
"count": 42434, |
|
"is_parallel": true, |
|
"self": 18.244157922028194, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 52.40837432899207, |
|
"count": 339472, |
|
"is_parallel": true, |
|
"self": 52.40837432899207 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 534.8900081020042, |
|
"count": 42435, |
|
"self": 2.1160900819980952, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 119.68441864100407, |
|
"count": 42435, |
|
"self": 119.5698528990041, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11456574199996794, |
|
"count": 1, |
|
"self": 0.11456574199996794 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 413.08949937900206, |
|
"count": 296, |
|
"self": 164.31402788099615, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 248.7754714980059, |
|
"count": 15312, |
|
"self": 248.7754714980059 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 2.462000338709913e-06, |
|
"count": 1, |
|
"self": 2.462000338709913e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.17141015100014556, |
|
"count": 1, |
|
"self": 0.002410419000170805, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.16899973199997476, |
|
"count": 1, |
|
"self": 0.16899973199997476 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |