ppo-Huggy / run_logs /timers.json
neoshang's picture
Huggy
cbd0077 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.388451099395752,
"min": 1.388451099395752,
"max": 1.42368745803833,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68435.3671875,
"min": 67897.7109375,
"max": 77262.6484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.47020933977456,
"min": 78.9856,
"max": 408.87704918032784,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49351.0,
"min": 48746.0,
"max": 50063.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49456.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49456.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.407233715057373,
"min": 0.07515204697847366,
"max": 2.4768590927124023,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1494.89208984375,
"min": 9.093398094177246,
"max": 1522.6053466796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7370618644159963,
"min": 1.9771755997799645,
"max": 4.018416181996337,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2320.715417802334,
"min": 239.2382475733757,
"max": 2459.74085187912,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7370618644159963,
"min": 1.9771755997799645,
"max": 4.018416181996337,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2320.715417802334,
"min": 239.2382475733757,
"max": 2459.74085187912,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018417791575484444,
"min": 0.01401273495340547,
"max": 0.019910274291760288,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.055253374726453336,
"min": 0.02802546990681094,
"max": 0.057943435123888776,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04790537206766506,
"min": 0.020207801833748817,
"max": 0.050109643745236104,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14371611620299518,
"min": 0.040415603667497635,
"max": 0.1449234513565898,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.72809875733332e-06,
"min": 3.72809875733332e-06,
"max": 0.0002952792015736,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.118429627199996e-05,
"min": 1.118429627199996e-05,
"max": 0.0008441914686028499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124266666666666,
"min": 0.10124266666666666,
"max": 0.1984264,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.303728,
"min": 0.20763425000000002,
"max": 0.58139715,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.200906666666644e-05,
"min": 7.200906666666644e-05,
"max": 0.00492147736,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021602719999999935,
"min": 0.00021602719999999935,
"max": 0.014071717785,
"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": "1759058313",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1759060957"
},
"total": 2643.663824971,
"count": 1,
"self": 0.8006455410004492,
"children": {
"run_training.setup": {
"total": 0.028204884999922797,
"count": 1,
"self": 0.028204884999922797
},
"TrainerController.start_learning": {
"total": 2642.8349745449996,
"count": 1,
"self": 4.061810085080197,
"children": {
"TrainerController._reset_env": {
"total": 2.8482380719999583,
"count": 1,
"self": 2.8482380719999583
},
"TrainerController.advance": {
"total": 2635.7321839239194,
"count": 232526,
"self": 4.2765887849363935,
"children": {
"env_step": {
"total": 2060.30261644399,
"count": 232526,
"self": 1654.4957404631136,
"children": {
"SubprocessEnvManager._take_step": {
"total": 403.20420897594784,
"count": 232526,
"self": 15.044884124029068,
"children": {
"TorchPolicy.evaluate": {
"total": 388.15932485191877,
"count": 222834,
"self": 388.15932485191877
}
}
},
"workers": {
"total": 2.602667004928435,
"count": 232526,
"self": 0.0,
"children": {
"worker_root": {
"total": 2630.583716125914,
"count": 232526,
"is_parallel": true,
"self": 1286.9475969048895,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008929240000270511,
"count": 1,
"is_parallel": true,
"self": 0.0002677930000345441,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000625130999992507,
"count": 2,
"is_parallel": true,
"self": 0.000625130999992507
}
}
},
"UnityEnvironment.step": {
"total": 0.03217310299999099,
"count": 1,
"is_parallel": true,
"self": 0.00037257899998621724,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001976980000790718,
"count": 1,
"is_parallel": true,
"self": 0.0001976980000790718
},
"communicator.exchange": {
"total": 0.030745932999934666,
"count": 1,
"is_parallel": true,
"self": 0.030745932999934666
},
"steps_from_proto": {
"total": 0.0008568929999910324,
"count": 1,
"is_parallel": true,
"self": 0.0002190780001001258,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006378149998909066,
"count": 2,
"is_parallel": true,
"self": 0.0006378149998909066
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1343.6361192210247,
"count": 232525,
"is_parallel": true,
"self": 37.46772805612977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.95162168590014,
"count": 232525,
"is_parallel": true,
"self": 81.95162168590014
},
"communicator.exchange": {
"total": 1134.749095991006,
"count": 232525,
"is_parallel": true,
"self": 1134.749095991006
},
"steps_from_proto": {
"total": 89.4676734879888,
"count": 232525,
"is_parallel": true,
"self": 32.12454599601335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.34312749197545,
"count": 465050,
"is_parallel": true,
"self": 57.34312749197545
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 571.1529786949933,
"count": 232526,
"self": 6.303527505005377,
"children": {
"process_trajectory": {
"total": 157.11691385698873,
"count": 232526,
"self": 155.58737613398944,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5295377229992937,
"count": 10,
"self": 1.5295377229992937
}
}
},
"_update_policy": {
"total": 407.7325373329992,
"count": 97,
"self": 316.325644125999,
"children": {
"TorchPPOOptimizer.update": {
"total": 91.40689320700017,
"count": 3880,
"self": 91.40689320700017
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.160000010713702e-06,
"count": 1,
"self": 1.160000010713702e-06
},
"TrainerController._save_models": {
"total": 0.1927413040002648,
"count": 1,
"self": 0.002473042000474379,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1902682619997904,
"count": 1,
"self": 0.1902682619997904
}
}
}
}
}
}
}