ppo-Huggy / run_logs /timers.json
osbm's picture
Huggy
b36c813
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4040480852127075,
"min": 1.4040480852127075,
"max": 1.43059241771698,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68690.2421875,
"min": 68279.65625,
"max": 79204.984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 116.1592505854801,
"min": 82.98319327731092,
"max": 376.8796992481203,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49600.0,
"min": 49154.0,
"max": 50125.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999958.0,
"min": 49895.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999958.0,
"min": 49895.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3358895778656006,
"min": 0.08485370874404907,
"max": 2.4292893409729004,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 997.4248046875,
"min": 11.200689315795898,
"max": 1431.705810546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.603481322875905,
"min": 1.877691355505676,
"max": 3.8468319112701077,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1538.6865248680115,
"min": 247.85525892674923,
"max": 2189.2064690589905,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.603481322875905,
"min": 1.877691355505676,
"max": 3.8468319112701077,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1538.6865248680115,
"min": 247.85525892674923,
"max": 2189.2064690589905,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015958112010654682,
"min": 0.013878456743744513,
"max": 0.02024642507118794,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.031916224021309364,
"min": 0.027756913487489026,
"max": 0.05582732490438502,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.049127084016799924,
"min": 0.022067918069660665,
"max": 0.06781355643437968,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09825416803359985,
"min": 0.04413583613932133,
"max": 0.20344066930313903,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.5663234779250025e-06,
"min": 4.5663234779250025e-06,
"max": 0.0002953117515627499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.132646955850005e-06,
"min": 9.132646955850005e-06,
"max": 0.0008439112686962499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10152207500000003,
"min": 0.10152207500000003,
"max": 0.19843725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20304415000000006,
"min": 0.20304415000000006,
"max": 0.58130375,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.59515425e-05,
"min": 8.59515425e-05,
"max": 0.004922018774999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000171903085,
"min": 0.000171903085,
"max": 0.014067057125,
"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": "1671801194",
"python_version": "3.7.12 | packaged by conda-forge | (default, Oct 26 2021, 06:08:53) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1671803686"
},
"total": 2491.6570817089996,
"count": 1,
"self": 0.44564658599983886,
"children": {
"run_training.setup": {
"total": 0.09536291199992775,
"count": 1,
"self": 0.09536291199992775
},
"TrainerController.start_learning": {
"total": 2491.116072211,
"count": 1,
"self": 5.168588274114882,
"children": {
"TrainerController._reset_env": {
"total": 8.456842929000004,
"count": 1,
"self": 8.456842929000004
},
"TrainerController.advance": {
"total": 2477.366211185885,
"count": 231550,
"self": 5.505464811754791,
"children": {
"env_step": {
"total": 1917.8411558360426,
"count": 231550,
"self": 1624.0135333690753,
"children": {
"SubprocessEnvManager._take_step": {
"total": 290.7461578199768,
"count": 231550,
"self": 16.715931122098937,
"children": {
"TorchPolicy.evaluate": {
"total": 274.0302266978779,
"count": 222965,
"self": 69.49714043974245,
"children": {
"TorchPolicy.sample_actions": {
"total": 204.53308625813543,
"count": 222965,
"self": 204.53308625813543
}
}
}
}
},
"workers": {
"total": 3.0814646469905256,
"count": 231550,
"self": 0.0,
"children": {
"worker_root": {
"total": 2482.467674972925,
"count": 231550,
"is_parallel": true,
"self": 1177.0738899738217,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001058644999829994,
"count": 1,
"is_parallel": true,
"self": 0.0003997809997144941,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006588640001155,
"count": 2,
"is_parallel": true,
"self": 0.0006588640001155
}
}
},
"UnityEnvironment.step": {
"total": 0.052678358999855845,
"count": 1,
"is_parallel": true,
"self": 0.0003795899997385277,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022297400005300005,
"count": 1,
"is_parallel": true,
"self": 0.00022297400005300005
},
"communicator.exchange": {
"total": 0.051331891000018004,
"count": 1,
"is_parallel": true,
"self": 0.051331891000018004
},
"steps_from_proto": {
"total": 0.0007439040000463137,
"count": 1,
"is_parallel": true,
"self": 0.0002738000000590546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047010399998725916,
"count": 2,
"is_parallel": true,
"self": 0.00047010399998725916
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1305.3937849991034,
"count": 231549,
"is_parallel": true,
"self": 44.00743753919687,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.11771244494139,
"count": 231549,
"is_parallel": true,
"self": 91.11771244494139
},
"communicator.exchange": {
"total": 1064.2688094009618,
"count": 231549,
"is_parallel": true,
"self": 1064.2688094009618
},
"steps_from_proto": {
"total": 105.99982561400338,
"count": 231549,
"is_parallel": true,
"self": 46.098697086055836,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.90112852794755,
"count": 463098,
"is_parallel": true,
"self": 59.90112852794755
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 554.0195905380874,
"count": 231550,
"self": 7.755158143059816,
"children": {
"process_trajectory": {
"total": 184.97786716902647,
"count": 231550,
"self": 183.60874245102673,
"children": {
"RLTrainer._checkpoint": {
"total": 1.369124717999739,
"count": 10,
"self": 1.369124717999739
}
}
},
"_update_policy": {
"total": 361.28656522600113,
"count": 96,
"self": 317.35596853299603,
"children": {
"TorchPPOOptimizer.update": {
"total": 43.9305966930051,
"count": 2880,
"self": 43.9305966930051
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0700000530050602e-06,
"count": 1,
"self": 1.0700000530050602e-06
},
"TrainerController._save_models": {
"total": 0.12442875199985792,
"count": 1,
"self": 0.00283076899995649,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12159798299990143,
"count": 1,
"self": 0.12159798299990143
}
}
}
}
}
}
}