|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7951178550720215, |
|
"min": 0.7684348821640015, |
|
"max": 1.4516193866729736, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 23917.14453125, |
|
"min": 23053.046875, |
|
"max": 44036.32421875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989917.0, |
|
"min": 29952.0, |
|
"max": 989917.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989917.0, |
|
"min": 29952.0, |
|
"max": 989917.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.16335511207580566, |
|
"min": -0.09027876704931259, |
|
"max": 0.23784534633159637, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 41.32884216308594, |
|
"min": -21.66690444946289, |
|
"max": 57.981239318847656, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0038602554704993963, |
|
"min": -0.020093420520424843, |
|
"max": 0.31468987464904785, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 0.9766446352005005, |
|
"min": -5.123822212219238, |
|
"max": 74.58149719238281, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06832695886541153, |
|
"min": 0.06490997650701814, |
|
"max": 0.07455365993591959, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9565774241157614, |
|
"min": 0.47060980925677026, |
|
"max": 1.0323578038620396, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.009633754660085073, |
|
"min": 0.0001613800387325917, |
|
"max": 0.012063296642112281, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.134872565241191, |
|
"min": 0.0020979405035236923, |
|
"max": 0.134872565241191, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.714833142707142e-06, |
|
"min": 7.714833142707142e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010800766399789998, |
|
"min": 0.00010800766399789998, |
|
"max": 0.0032558372147209994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10257157857142858, |
|
"min": 0.10257157857142858, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4360021, |
|
"min": 1.3691136000000002, |
|
"max": 2.4426171000000005, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002669006992857143, |
|
"min": 0.0002669006992857143, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0037366097899999996, |
|
"min": 0.0037366097899999996, |
|
"max": 0.10854937209999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01120004989206791, |
|
"min": 0.01120004989206791, |
|
"max": 0.4630848467350006, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.15680070221424103, |
|
"min": 0.15680070221424103, |
|
"max": 3.241593837738037, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 640.5, |
|
"min": 611.6595744680851, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 32025.0, |
|
"min": 15984.0, |
|
"max": 33054.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.7193479681015015, |
|
"min": -1.0000000521540642, |
|
"max": 0.9626978380565948, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 35.96739840507507, |
|
"min": -32.000001668930054, |
|
"max": 45.246798388659954, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.7193479681015015, |
|
"min": -1.0000000521540642, |
|
"max": 0.9626978380565948, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 35.96739840507507, |
|
"min": -32.000001668930054, |
|
"max": 45.246798388659954, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.07486897539463826, |
|
"min": 0.07266902872528434, |
|
"max": 8.924482538364828, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.7434487697319128, |
|
"min": 3.4154443500883644, |
|
"max": 142.79172061383724, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1673636535", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-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": "1673638505" |
|
}, |
|
"total": 1970.0247175269997, |
|
"count": 1, |
|
"self": 0.4326485579999826, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1107966109998415, |
|
"count": 1, |
|
"self": 0.1107966109998415 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1969.4812723579998, |
|
"count": 1, |
|
"self": 1.1332032149816769, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.429782052000064, |
|
"count": 1, |
|
"self": 6.429782052000064 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1961.8285864310174, |
|
"count": 63288, |
|
"self": 1.1776086089466844, |
|
"children": { |
|
"env_step": { |
|
"total": 1310.581264446976, |
|
"count": 63288, |
|
"self": 1212.7390236778601, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 97.14663811905166, |
|
"count": 63288, |
|
"self": 4.056621237064974, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 93.09001688198668, |
|
"count": 62555, |
|
"self": 31.92652645707676, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 61.163490424909924, |
|
"count": 62555, |
|
"self": 61.163490424909924 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.695602650064302, |
|
"count": 63288, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1965.1720664260033, |
|
"count": 63288, |
|
"is_parallel": true, |
|
"self": 846.5279963260678, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0020938630000273406, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007149459997890517, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001378917000238289, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001378917000238289 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04443406100017455, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005096380004943057, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004766070001096523, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004766070001096523 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.041666700999940076, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.041666700999940076 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017811149996305176, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005007779996049067, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001280337000025611, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001280337000025611 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1118.6440700999356, |
|
"count": 63287, |
|
"is_parallel": true, |
|
"self": 27.615656920992024, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.044522318938107, |
|
"count": 63287, |
|
"is_parallel": true, |
|
"self": 22.044522318938107 |
|
}, |
|
"communicator.exchange": { |
|
"total": 971.4308631328968, |
|
"count": 63287, |
|
"is_parallel": true, |
|
"self": 971.4308631328968 |
|
}, |
|
"steps_from_proto": { |
|
"total": 97.55302772710866, |
|
"count": 63287, |
|
"is_parallel": true, |
|
"self": 21.054341804866908, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 76.49868592224175, |
|
"count": 506296, |
|
"is_parallel": true, |
|
"self": 76.49868592224175 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 650.0697133750946, |
|
"count": 63288, |
|
"self": 2.1263138201034053, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 140.65715376598973, |
|
"count": 63288, |
|
"self": 140.4680277829898, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.18912598299993988, |
|
"count": 2, |
|
"self": 0.18912598299993988 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 507.28624578900144, |
|
"count": 440, |
|
"self": 194.16636339310344, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 313.119882395898, |
|
"count": 22824, |
|
"self": 313.119882395898 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.10000380827114e-07, |
|
"count": 1, |
|
"self": 9.10000380827114e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08969975000036357, |
|
"count": 1, |
|
"self": 0.0013341590001800796, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08836559100018349, |
|
"count": 1, |
|
"self": 0.08836559100018349 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |