ppo-Huggy / run_logs /timers.json
tsobolev's picture
Huggy
5a1a502 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408092737197876,
"min": 1.408092737197876,
"max": 1.4302630424499512,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69141.578125,
"min": 69141.578125,
"max": 76028.0625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.49186256781194,
"min": 80.79084967320262,
"max": 393.109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49489.0,
"min": 49079.0,
"max": 50318.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999996.0,
"min": 49960.0,
"max": 1999996.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999996.0,
"min": 49960.0,
"max": 1999996.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.439401388168335,
"min": 0.18963368237018585,
"max": 2.4725897312164307,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1348.989013671875,
"min": 24.083477020263672,
"max": 1472.6640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7347967294844753,
"min": 1.7188980145247903,
"max": 3.988961084892875,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2065.342591404915,
"min": 218.30004784464836,
"max": 2334.0976151823997,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7347967294844753,
"min": 1.7188980145247903,
"max": 3.988961084892875,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2065.342591404915,
"min": 218.30004784464836,
"max": 2334.0976151823997,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016327611554879697,
"min": 0.014640938709392988,
"max": 0.019572580119711348,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04898283466463909,
"min": 0.029281877418785976,
"max": 0.058717740359134046,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05244546776844395,
"min": 0.021148229669779542,
"max": 0.05727520976215601,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15733640330533186,
"min": 0.042296459339559084,
"max": 0.16663535386323927,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6569987810333413e-06,
"min": 3.6569987810333413e-06,
"max": 0.0002953074015642,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0970996343100024e-05,
"min": 1.0970996343100024e-05,
"max": 0.0008441095686301499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121896666666665,
"min": 0.10121896666666665,
"max": 0.1984358,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30365689999999995,
"min": 0.20759730000000004,
"max": 0.58136985,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.082643666666678e-05,
"min": 7.082643666666678e-05,
"max": 0.004921946420000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021247931000000032,
"min": 0.00021247931000000032,
"max": 0.014070355515,
"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": "1706154692",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/opt/conda/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706158507"
},
"total": 3814.7453364740004,
"count": 1,
"self": 0.39073027900030866,
"children": {
"run_training.setup": {
"total": 0.11949318400002085,
"count": 1,
"self": 0.11949318400002085
},
"TrainerController.start_learning": {
"total": 3814.235113011,
"count": 1,
"self": 9.011760732880248,
"children": {
"TrainerController._reset_env": {
"total": 3.0425401630000124,
"count": 1,
"self": 3.0425401630000124
},
"TrainerController.advance": {
"total": 3802.02992121612,
"count": 232458,
"self": 8.106822143205136,
"children": {
"env_step": {
"total": 2432.0271071709476,
"count": 232458,
"self": 1939.8015128873376,
"children": {
"SubprocessEnvManager._take_step": {
"total": 486.6125368868361,
"count": 232458,
"self": 28.9423408809605,
"children": {
"TorchPolicy.evaluate": {
"total": 457.6701960058756,
"count": 222880,
"self": 457.6701960058756
}
}
},
"workers": {
"total": 5.613057396773911,
"count": 232458,
"self": 0.0,
"children": {
"worker_root": {
"total": 3802.8926649107625,
"count": 232458,
"is_parallel": true,
"self": 2322.5906321067123,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001198208000005252,
"count": 1,
"is_parallel": true,
"self": 0.00034358200014139584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008546259998638561,
"count": 2,
"is_parallel": true,
"self": 0.0008546259998638561
}
}
},
"UnityEnvironment.step": {
"total": 0.03553283700011889,
"count": 1,
"is_parallel": true,
"self": 0.00041164100002788473,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002007089999551681,
"count": 1,
"is_parallel": true,
"self": 0.0002007089999551681
},
"communicator.exchange": {
"total": 0.03421245499998804,
"count": 1,
"is_parallel": true,
"self": 0.03421245499998804
},
"steps_from_proto": {
"total": 0.0007080320001477958,
"count": 1,
"is_parallel": true,
"self": 0.00019647600015559874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000511555999992197,
"count": 2,
"is_parallel": true,
"self": 0.000511555999992197
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1480.3020328040502,
"count": 232457,
"is_parallel": true,
"self": 43.895455363066276,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 96.18283312006065,
"count": 232457,
"is_parallel": true,
"self": 96.18283312006065
},
"communicator.exchange": {
"total": 1229.9618289699213,
"count": 232457,
"is_parallel": true,
"self": 1229.9618289699213
},
"steps_from_proto": {
"total": 110.26191535100202,
"count": 232457,
"is_parallel": true,
"self": 36.41193451064487,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.84998084035715,
"count": 464914,
"is_parallel": true,
"self": 73.84998084035715
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1361.895991901967,
"count": 232458,
"self": 12.509192290731107,
"children": {
"process_trajectory": {
"total": 287.27623810923274,
"count": 232458,
"self": 285.8505457542335,
"children": {
"RLTrainer._checkpoint": {
"total": 1.425692354999228,
"count": 10,
"self": 1.425692354999228
}
}
},
"_update_policy": {
"total": 1062.110561502003,
"count": 97,
"self": 541.8098764329957,
"children": {
"TorchPPOOptimizer.update": {
"total": 520.3006850690074,
"count": 2910,
"self": 520.3006850690074
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4450006347033195e-06,
"count": 1,
"self": 1.4450006347033195e-06
},
"TrainerController._save_models": {
"total": 0.15088945399929798,
"count": 1,
"self": 0.00706736199936131,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14382209199993667,
"count": 1,
"self": 0.14382209199993667
}
}
}
}
}
}
}