|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.22990769147872925, |
|
"min": 0.22990769147872925, |
|
"max": 0.9623711705207825, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11484.3486328125, |
|
"min": 11484.3486328125, |
|
"max": 48380.32421875, |
|
"count": 30 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 1999978.0, |
|
"min": 549877.0, |
|
"max": 1999978.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 1999978.0, |
|
"min": 549877.0, |
|
"max": 1999978.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.79498291015625, |
|
"min": -0.049888525158166885, |
|
"max": 0.8327198028564453, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 404.64630126953125, |
|
"min": -20.10507583618164, |
|
"max": 423.02166748046875, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.008816980756819248, |
|
"min": -0.015706252306699753, |
|
"max": 0.04321414232254028, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.487843036651611, |
|
"min": -7.664651393890381, |
|
"max": 20.569931030273438, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06890473043030297, |
|
"min": 0.06715824836536068, |
|
"max": 0.07270693400694214, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.6537135303272712, |
|
"min": 1.4417596207530268, |
|
"max": 1.7449664161666114, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.013658327631775236, |
|
"min": 0.002909782167301695, |
|
"max": 0.015598461065061851, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.3277998631626057, |
|
"min": 0.06983477201524069, |
|
"max": 0.36465456387811046, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 3.761623746158331e-06, |
|
"min": 3.761623746158331e-06, |
|
"max": 0.0002208904688698525, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 9.027896990779994e-05, |
|
"min": 9.027896990779994e-05, |
|
"max": 0.0051297780900742005, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10125384166666666, |
|
"min": 0.10125384166666666, |
|
"max": 0.1736301475, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 2.4300922, |
|
"min": 2.4300922, |
|
"max": 4.109925800000001, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00013525878249999993, |
|
"min": 0.00013525878249999993, |
|
"max": 0.007365651735250001, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0032462107799999984, |
|
"min": 0.0032462107799999984, |
|
"max": 0.17106158742, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.005682992283254862, |
|
"min": 0.005682992283254862, |
|
"max": 0.017659258097410202, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.13639181852340698, |
|
"min": 0.13236719369888306, |
|
"max": 0.40205714106559753, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 235.55405405405406, |
|
"min": 223.0137614678899, |
|
"max": 913.68, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 52293.0, |
|
"min": 45684.0, |
|
"max": 52293.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7374116968665574, |
|
"min": -0.41572597678060885, |
|
"max": 1.7752282960365897, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 385.70539670437574, |
|
"min": -22.449202746152878, |
|
"max": 388.77499683201313, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7374116968665574, |
|
"min": -0.41572597678060885, |
|
"max": 1.7752282960365897, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 385.70539670437574, |
|
"min": -22.449202746152878, |
|
"max": 388.77499683201313, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.013987002048534205, |
|
"min": 0.013545649350124707, |
|
"max": 0.16782157377339899, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.1051144547745935, |
|
"min": 2.8492067171282542, |
|
"max": 8.41888378362637, |
|
"count": 30 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 30 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1690894269", |
|
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", |
|
"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 --resume", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1690897948" |
|
}, |
|
"total": 3678.1012117030004, |
|
"count": 1, |
|
"self": 0.4758699430003617, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.03274945100019977, |
|
"count": 1, |
|
"self": 0.03274945100019977 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 3677.592592309, |
|
"count": 1, |
|
"self": 2.0773819288069717, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.084842718999425, |
|
"count": 1, |
|
"self": 4.084842718999425 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 3671.334356512193, |
|
"count": 97701, |
|
"self": 1.9837136676160299, |
|
"children": { |
|
"env_step": { |
|
"total": 2673.681366750845, |
|
"count": 97701, |
|
"self": 2512.7749599728977, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 159.7130742850877, |
|
"count": 97701, |
|
"self": 6.983719284030485, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 152.72935500105723, |
|
"count": 93816, |
|
"self": 152.72935500105723 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.193332492859554, |
|
"count": 97701, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 3669.4285612269287, |
|
"count": 97701, |
|
"is_parallel": true, |
|
"self": 1328.2800386228382, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017689090000203578, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005289179998726468, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001239991000147711, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001239991000147711 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04616322499987291, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006317520001175581, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004857240001001628, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004857240001001628 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.043255069999759144, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.043255069999759144 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017906789998960448, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003428509980949457, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014478280018010992, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014478280018010992 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2341.1485226040904, |
|
"count": 97700, |
|
"is_parallel": true, |
|
"self": 51.45940181703827, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 34.14660361704682, |
|
"count": 97700, |
|
"is_parallel": true, |
|
"self": 34.14660361704682 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2102.989779297909, |
|
"count": 97700, |
|
"is_parallel": true, |
|
"self": 2102.989779297909 |
|
}, |
|
"steps_from_proto": { |
|
"total": 152.55273787209626, |
|
"count": 97700, |
|
"is_parallel": true, |
|
"self": 30.888071267690066, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 121.6646666044062, |
|
"count": 781600, |
|
"is_parallel": true, |
|
"self": 121.6646666044062 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 995.6692760937322, |
|
"count": 97701, |
|
"self": 4.01680010486416, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 169.72121598989634, |
|
"count": 97701, |
|
"self": 169.31345781989603, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.40775817000030656, |
|
"count": 3, |
|
"self": 0.40775817000030656 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 821.9312599989717, |
|
"count": 707, |
|
"self": 535.8821322959229, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 286.0491277030487, |
|
"count": 34197, |
|
"self": 286.0491277030487 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.739989425521344e-07, |
|
"count": 1, |
|
"self": 8.739989425521344e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09601027500139026, |
|
"count": 1, |
|
"self": 0.0018373540024185786, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09417292099897168, |
|
"count": 1, |
|
"self": 0.09417292099897168 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |