ppo-Huggy / run_logs /timers.json
conlan's picture
Huggy first version
dbb2e9a
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4060430526733398,
"min": 1.4060195684432983,
"max": 1.428171157836914,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70217.7890625,
"min": 68877.9375,
"max": 77488.8515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.63829787234043,
"min": 79.5330112721417,
"max": 396.1746031746032,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49428.0,
"min": 48942.0,
"max": 50172.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999981.0,
"min": 49959.0,
"max": 1999981.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999981.0,
"min": 49959.0,
"max": 1999981.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.439411163330078,
"min": 0.05751113221049309,
"max": 2.469188928604126,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1375.827880859375,
"min": 7.188891410827637,
"max": 1484.667236328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7485869228839874,
"min": 1.7716423060894013,
"max": 4.02967092568857,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2114.203024506569,
"min": 221.45528826117516,
"max": 2338.7106687426567,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7485869228839874,
"min": 1.7716423060894013,
"max": 4.02967092568857,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2114.203024506569,
"min": 221.45528826117516,
"max": 2338.7106687426567,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015240153029379951,
"min": 0.013952298537090731,
"max": 0.019195528787289126,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045720459088139855,
"min": 0.027904597074181463,
"max": 0.05512462681848168,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05484700037373438,
"min": 0.02247302414228519,
"max": 0.06260727383196353,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16454100112120312,
"min": 0.04494604828457038,
"max": 0.18202051868041355,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.379198873633346e-06,
"min": 3.379198873633346e-06,
"max": 0.0002953704015431999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0137596620900038e-05,
"min": 1.0137596620900038e-05,
"max": 0.0008440989186337,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112636666666668,
"min": 0.10112636666666668,
"max": 0.19845680000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033791,
"min": 0.20738399999999996,
"max": 0.5813663,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.620569666666688e-05,
"min": 6.620569666666688e-05,
"max": 0.00492299432,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019861709000000064,
"min": 0.00019861709000000064,
"max": 0.014070178370000002,
"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": "1698424075",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698426487"
},
"total": 2412.077092937,
"count": 1,
"self": 0.4751691890000984,
"children": {
"run_training.setup": {
"total": 0.045899953000002824,
"count": 1,
"self": 0.045899953000002824
},
"TrainerController.start_learning": {
"total": 2411.556023795,
"count": 1,
"self": 4.330938278911617,
"children": {
"TrainerController._reset_env": {
"total": 8.873728261999986,
"count": 1,
"self": 8.873728261999986
},
"TrainerController.advance": {
"total": 2398.252055694088,
"count": 232293,
"self": 4.717870190137546,
"children": {
"env_step": {
"total": 1892.6339212249752,
"count": 232293,
"self": 1556.6706980410665,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.2151357079201,
"count": 232293,
"self": 16.61435651093177,
"children": {
"TorchPolicy.evaluate": {
"total": 316.60077919698836,
"count": 222972,
"self": 316.60077919698836
}
}
},
"workers": {
"total": 2.748087475988541,
"count": 232293,
"self": 0.0,
"children": {
"worker_root": {
"total": 2404.160013019987,
"count": 232293,
"is_parallel": true,
"self": 1131.5139367248441,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008217529999683393,
"count": 1,
"is_parallel": true,
"self": 0.00024245899999186804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005792939999764712,
"count": 2,
"is_parallel": true,
"self": 0.0005792939999764712
}
}
},
"UnityEnvironment.step": {
"total": 0.029093825000018114,
"count": 1,
"is_parallel": true,
"self": 0.00032570900020800764,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001993299999867304,
"count": 1,
"is_parallel": true,
"self": 0.0001993299999867304
},
"communicator.exchange": {
"total": 0.02780155499999637,
"count": 1,
"is_parallel": true,
"self": 0.02780155499999637
},
"steps_from_proto": {
"total": 0.0007672309998270066,
"count": 1,
"is_parallel": true,
"self": 0.00021995499969307275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005472760001339338,
"count": 2,
"is_parallel": true,
"self": 0.0005472760001339338
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1272.646076295143,
"count": 232292,
"is_parallel": true,
"self": 40.600482980043125,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.89957904299513,
"count": 232292,
"is_parallel": true,
"self": 83.89957904299513
},
"communicator.exchange": {
"total": 1058.0240360560592,
"count": 232292,
"is_parallel": true,
"self": 1058.0240360560592
},
"steps_from_proto": {
"total": 90.12197821604559,
"count": 232292,
"is_parallel": true,
"self": 31.8369353291921,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.28504288685349,
"count": 464584,
"is_parallel": true,
"self": 58.28504288685349
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 500.9002642789753,
"count": 232293,
"self": 6.428928863035935,
"children": {
"process_trajectory": {
"total": 150.4527380289387,
"count": 232293,
"self": 149.3066243109388,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1461137179999241,
"count": 10,
"self": 1.1461137179999241
}
}
},
"_update_policy": {
"total": 344.0185973870007,
"count": 97,
"self": 281.13999215700255,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.87860522999813,
"count": 2910,
"self": 62.87860522999813
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.410002010350581e-07,
"count": 1,
"self": 8.410002010350581e-07
},
"TrainerController._save_models": {
"total": 0.09930071899998438,
"count": 1,
"self": 0.0018526639996707672,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09744805500031362,
"count": 1,
"self": 0.09744805500031362
}
}
}
}
}
}
}