ppo-Huggy / run_logs /timers.json
sdidier-dev's picture
Huggy
b9df619 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405288815498352,
"min": 1.405288815498352,
"max": 1.4287148714065552,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71308.5703125,
"min": 68602.40625,
"max": 76395.859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.94064748201438,
"min": 78.94249201277955,
"max": 392.8267716535433,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49451.0,
"min": 49093.0,
"max": 50141.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999928.0,
"min": 49840.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999928.0,
"min": 49840.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4511709213256836,
"min": 0.08663241565227509,
"max": 2.5060343742370605,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1362.85107421875,
"min": 10.915684700012207,
"max": 1530.6444091796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8062627789356727,
"min": 1.5986579599834623,
"max": 3.9732704353056207,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2116.282105088234,
"min": 201.43090295791626,
"max": 2431.132935464382,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8062627789356727,
"min": 1.5986579599834623,
"max": 3.9732704353056207,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2116.282105088234,
"min": 201.43090295791626,
"max": 2431.132935464382,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01940155830303007,
"min": 0.014150411528923238,
"max": 0.021191019160323777,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.058204674909090204,
"min": 0.028300823057846477,
"max": 0.058204674909090204,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05299650012618965,
"min": 0.021559273203214012,
"max": 0.060760821029543874,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15898950037856896,
"min": 0.043118546406428024,
"max": 0.1740966481467088,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.663348778916651e-06,
"min": 3.663348778916651e-06,
"max": 0.00029533942655352507,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0990046336749953e-05,
"min": 1.0990046336749953e-05,
"max": 0.00084406216864595,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122108333333331,
"min": 0.10122108333333331,
"max": 0.19844647499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30366324999999994,
"min": 0.20768734999999994,
"max": 0.58135405,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.093205833333308e-05,
"min": 7.093205833333308e-05,
"max": 0.0049224791025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021279617499999926,
"min": 0.00021279617499999926,
"max": 0.014069567095,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1710780895",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710783223"
},
"total": 2328.355314907,
"count": 1,
"self": 0.49651206699991235,
"children": {
"run_training.setup": {
"total": 0.09600599800000964,
"count": 1,
"self": 0.09600599800000964
},
"TrainerController.start_learning": {
"total": 2327.762796842,
"count": 1,
"self": 4.090668291913516,
"children": {
"TrainerController._reset_env": {
"total": 3.1775310250000075,
"count": 1,
"self": 3.1775310250000075
},
"TrainerController.advance": {
"total": 2320.3788775100866,
"count": 232814,
"self": 4.435244495997722,
"children": {
"env_step": {
"total": 1840.7575565220072,
"count": 232814,
"self": 1526.7665616840832,
"children": {
"SubprocessEnvManager._take_step": {
"total": 311.2902540589518,
"count": 232814,
"self": 16.009271907920606,
"children": {
"TorchPolicy.evaluate": {
"total": 295.2809821510312,
"count": 223008,
"self": 295.2809821510312
}
}
},
"workers": {
"total": 2.7007407789722038,
"count": 232814,
"self": 0.0,
"children": {
"worker_root": {
"total": 2320.705332238073,
"count": 232814,
"is_parallel": true,
"self": 1085.0987992130122,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008609199999796147,
"count": 1,
"is_parallel": true,
"self": 0.0002229629999987992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006379569999808155,
"count": 2,
"is_parallel": true,
"self": 0.0006379569999808155
}
}
},
"UnityEnvironment.step": {
"total": 0.03085151099998029,
"count": 1,
"is_parallel": true,
"self": 0.00042895400002862516,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019835199998397002,
"count": 1,
"is_parallel": true,
"self": 0.00019835199998397002
},
"communicator.exchange": {
"total": 0.029438868999989154,
"count": 1,
"is_parallel": true,
"self": 0.029438868999989154
},
"steps_from_proto": {
"total": 0.0007853359999785425,
"count": 1,
"is_parallel": true,
"self": 0.0002129050000121424,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005724309999664001,
"count": 2,
"is_parallel": true,
"self": 0.0005724309999664001
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1235.6065330250608,
"count": 232813,
"is_parallel": true,
"self": 38.62878723609401,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.79132157494246,
"count": 232813,
"is_parallel": true,
"self": 79.79132157494246
},
"communicator.exchange": {
"total": 1027.8069084799995,
"count": 232813,
"is_parallel": true,
"self": 1027.8069084799995
},
"steps_from_proto": {
"total": 89.37951573402489,
"count": 232813,
"is_parallel": true,
"self": 31.70993405408234,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.66958167994255,
"count": 465626,
"is_parallel": true,
"self": 57.66958167994255
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 475.18607649208167,
"count": 232814,
"self": 6.668998466039,
"children": {
"process_trajectory": {
"total": 150.92684964804226,
"count": 232814,
"self": 149.6865108580427,
"children": {
"RLTrainer._checkpoint": {
"total": 1.240338789999555,
"count": 10,
"self": 1.240338789999555
}
}
},
"_update_policy": {
"total": 317.5902283780004,
"count": 97,
"self": 255.39539390199275,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.19483447600766,
"count": 2910,
"self": 62.19483447600766
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.050001270021312e-07,
"count": 1,
"self": 8.050001270021312e-07
},
"TrainerController._save_models": {
"total": 0.115719209999952,
"count": 1,
"self": 0.0020055829995726526,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11371362700037935,
"count": 1,
"self": 0.11371362700037935
}
}
}
}
}
}
}