ppo-Huggy / run_logs /timers.json
maaldic's picture
Huggy
0c60efc verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.40269935131073,
"min": 1.40269935131073,
"max": 1.4271069765090942,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70391.6640625,
"min": 68587.7890625,
"max": 78062.125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 111.0089485458613,
"min": 89.33574007220217,
"max": 394.1171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49621.0,
"min": 48849.0,
"max": 50447.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999593.0,
"min": 49883.0,
"max": 1999593.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999593.0,
"min": 49883.0,
"max": 1999593.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3306756019592285,
"min": 0.046396609395742416,
"max": 2.419452667236328,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1041.81201171875,
"min": 5.892369270324707,
"max": 1329.493896484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.536940425701056,
"min": 1.8428863181373265,
"max": 3.85449446729018,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1581.012370288372,
"min": 234.04656240344048,
"max": 2055.2518236637115,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.536940425701056,
"min": 1.8428863181373265,
"max": 3.85449446729018,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1581.012370288372,
"min": 234.04656240344048,
"max": 2055.2518236637115,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01850285617717115,
"min": 0.013786612976400648,
"max": 0.020392896728784155,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0370057123543423,
"min": 0.027573225952801296,
"max": 0.05915257677212746,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04623859946926435,
"min": 0.022112535312771797,
"max": 0.06395853397746881,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0924771989385287,
"min": 0.044225070625543594,
"max": 0.17141475019355615,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.114973628374994e-06,
"min": 4.114973628374994e-06,
"max": 0.000295336426554525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.229947256749988e-06,
"min": 8.229947256749988e-06,
"max": 0.0008441442186186,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10137162500000002,
"min": 0.10137162500000002,
"max": 0.19844547500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20274325000000004,
"min": 0.20274325000000004,
"max": 0.5813813999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.844408749999994e-05,
"min": 7.844408749999994e-05,
"max": 0.0049224292025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001568881749999999,
"min": 0.0001568881749999999,
"max": 0.01407093186,
"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": "1725201567",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1725206346"
},
"total": 4779.40655661,
"count": 1,
"self": 1.1593739910003933,
"children": {
"run_training.setup": {
"total": 0.12381318099983218,
"count": 1,
"self": 0.12381318099983218
},
"TrainerController.start_learning": {
"total": 4778.123369438,
"count": 1,
"self": 8.66852232283236,
"children": {
"TrainerController._reset_env": {
"total": 3.3840093349999734,
"count": 1,
"self": 3.3840093349999734
},
"TrainerController.advance": {
"total": 4765.901177276168,
"count": 231215,
"self": 8.089198178187871,
"children": {
"env_step": {
"total": 3024.7241519270056,
"count": 231215,
"self": 2517.989135577819,
"children": {
"SubprocessEnvManager._take_step": {
"total": 501.32835793310073,
"count": 231215,
"self": 33.34459441617446,
"children": {
"TorchPolicy.evaluate": {
"total": 467.9837635169263,
"count": 223031,
"self": 467.9837635169263
}
}
},
"workers": {
"total": 5.406658416085975,
"count": 231215,
"self": 0.0,
"children": {
"worker_root": {
"total": 4764.61610849511,
"count": 231215,
"is_parallel": true,
"self": 2765.5676031202033,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010555050000675692,
"count": 1,
"is_parallel": true,
"self": 0.00038450300030490325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000671001999762666,
"count": 2,
"is_parallel": true,
"self": 0.000671001999762666
}
}
},
"UnityEnvironment.step": {
"total": 0.03940649600008328,
"count": 1,
"is_parallel": true,
"self": 0.0005039909999595693,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025092999999287713,
"count": 1,
"is_parallel": true,
"self": 0.00025092999999287713
},
"communicator.exchange": {
"total": 0.03749402300013571,
"count": 1,
"is_parallel": true,
"self": 0.03749402300013571
},
"steps_from_proto": {
"total": 0.0011575519999951212,
"count": 1,
"is_parallel": true,
"self": 0.00032539299991185544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008321590000832657,
"count": 2,
"is_parallel": true,
"self": 0.0008321590000832657
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1999.0485053749067,
"count": 231214,
"is_parallel": true,
"self": 62.766036841786445,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 109.91667689206815,
"count": 231214,
"is_parallel": true,
"self": 109.91667689206815
},
"communicator.exchange": {
"total": 1688.17797512502,
"count": 231214,
"is_parallel": true,
"self": 1688.17797512502
},
"steps_from_proto": {
"total": 138.18781651603194,
"count": 231214,
"is_parallel": true,
"self": 44.312309957829484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 93.87550655820246,
"count": 462428,
"is_parallel": true,
"self": 93.87550655820246
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1733.0878271709744,
"count": 231215,
"self": 12.883904591098144,
"children": {
"process_trajectory": {
"total": 251.74334097287942,
"count": 231215,
"self": 250.5025016668801,
"children": {
"RLTrainer._checkpoint": {
"total": 1.240839305999316,
"count": 10,
"self": 1.240839305999316
}
}
},
"_update_policy": {
"total": 1468.4605816069968,
"count": 96,
"self": 345.39087940401805,
"children": {
"TorchPPOOptimizer.update": {
"total": 1123.0697022029788,
"count": 2880,
"self": 1123.0697022029788
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6129997675307095e-06,
"count": 1,
"self": 1.6129997675307095e-06
},
"TrainerController._save_models": {
"total": 0.16965889099992637,
"count": 1,
"self": 0.004172889999608742,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16548600100031763,
"count": 1,
"self": 0.16548600100031763
}
}
}
}
}
}
}