ppo-Huggy / run_logs /timers.json
Sviatoslavs's picture
Huggy
dd74e37
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3997081518173218,
"min": 1.3997081518173218,
"max": 1.4258760213851929,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69659.2734375,
"min": 68580.6171875,
"max": 76970.7109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.90378006872852,
"min": 83.00503355704699,
"max": 385.8692307692308,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49996.0,
"min": 49063.0,
"max": 50163.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999885.0,
"min": 49886.0,
"max": 1999885.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999885.0,
"min": 49886.0,
"max": 1999885.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.448516845703125,
"min": 0.07431825250387192,
"max": 2.4627695083618164,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1425.036865234375,
"min": 9.587054252624512,
"max": 1448.486572265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8553865970819676,
"min": 1.854570682196654,
"max": 3.940252128599861,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2243.834999501705,
"min": 239.23961800336838,
"max": 2273.03903901577,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8553865970819676,
"min": 1.854570682196654,
"max": 3.940252128599861,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2243.834999501705,
"min": 239.23961800336838,
"max": 2273.03903901577,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01947753863739005,
"min": 0.013608011686786388,
"max": 0.021600235377021212,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05843261591217015,
"min": 0.02861452833058138,
"max": 0.05884166806063149,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.060170917378531565,
"min": 0.023442229442298415,
"max": 0.06414359516153734,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1805127521355947,
"min": 0.04688445888459683,
"max": 0.1832003265619278,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.396948867716663e-06,
"min": 3.396948867716663e-06,
"max": 0.00029533485155504996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.019084660314999e-05,
"min": 1.019084660314999e-05,
"max": 0.0008441931186022999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113228333333334,
"min": 0.10113228333333334,
"max": 0.19844494999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30339685,
"min": 0.20740714999999998,
"max": 0.5813976999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.650093833333326e-05,
"min": 6.650093833333326e-05,
"max": 0.004922403004999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001995028149999998,
"min": 0.0001995028149999998,
"max": 0.014071745230000002,
"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": "1692610265",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"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": "1692613028"
},
"total": 2763.5374486130004,
"count": 1,
"self": 0.48700865500086366,
"children": {
"run_training.setup": {
"total": 0.04691320199992788,
"count": 1,
"self": 0.04691320199992788
},
"TrainerController.start_learning": {
"total": 2763.0035267559997,
"count": 1,
"self": 5.035712170127226,
"children": {
"TrainerController._reset_env": {
"total": 4.612932002999969,
"count": 1,
"self": 4.612932002999969
},
"TrainerController.advance": {
"total": 2753.219378612873,
"count": 232173,
"self": 5.267248051863135,
"children": {
"env_step": {
"total": 2144.3843530900194,
"count": 232173,
"self": 1809.5612599608796,
"children": {
"SubprocessEnvManager._take_step": {
"total": 331.5234280040663,
"count": 232173,
"self": 18.77980235405846,
"children": {
"TorchPolicy.evaluate": {
"total": 312.74362565000786,
"count": 222920,
"self": 312.74362565000786
}
}
},
"workers": {
"total": 3.2996651250734885,
"count": 232173,
"self": 0.0,
"children": {
"worker_root": {
"total": 2754.5188505859824,
"count": 232173,
"is_parallel": true,
"self": 1279.4017158738943,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009653119999484261,
"count": 1,
"is_parallel": true,
"self": 0.0002838689999862254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006814429999622007,
"count": 2,
"is_parallel": true,
"self": 0.0006814429999622007
}
}
},
"UnityEnvironment.step": {
"total": 0.06416388499997083,
"count": 1,
"is_parallel": true,
"self": 0.00038428999994266633,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002293960000088191,
"count": 1,
"is_parallel": true,
"self": 0.0002293960000088191
},
"communicator.exchange": {
"total": 0.06272694699998738,
"count": 1,
"is_parallel": true,
"self": 0.06272694699998738
},
"steps_from_proto": {
"total": 0.000823252000031971,
"count": 1,
"is_parallel": true,
"self": 0.00024498700008734886,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005782649999446221,
"count": 2,
"is_parallel": true,
"self": 0.0005782649999446221
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1475.117134712088,
"count": 232172,
"is_parallel": true,
"self": 43.94886063502395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.48636992206139,
"count": 232172,
"is_parallel": true,
"self": 93.48636992206139
},
"communicator.exchange": {
"total": 1227.8022205169932,
"count": 232172,
"is_parallel": true,
"self": 1227.8022205169932
},
"steps_from_proto": {
"total": 109.87968363800951,
"count": 232172,
"is_parallel": true,
"self": 41.71420398582302,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.16547965218649,
"count": 464344,
"is_parallel": true,
"self": 68.16547965218649
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 603.5677774709902,
"count": 232173,
"self": 7.276236972077868,
"children": {
"process_trajectory": {
"total": 158.29613330691234,
"count": 232173,
"self": 156.69017155291226,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6059617540000772,
"count": 10,
"self": 1.6059617540000772
}
}
},
"_update_policy": {
"total": 437.995407192,
"count": 97,
"self": 374.832579588012,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.162827603988035,
"count": 2910,
"self": 63.162827603988035
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.51999936660286e-07,
"count": 1,
"self": 9.51999936660286e-07
},
"TrainerController._save_models": {
"total": 0.13550301799978115,
"count": 1,
"self": 0.002156627999738703,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13334639000004245,
"count": 1,
"self": 0.13334639000004245
}
}
}
}
}
}
}