ppo-Huggy / run_logs /timers.json
nzdb70's picture
Huggy
87759a0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4024975299835205,
"min": 1.4024975299835205,
"max": 1.4279617071151733,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70040.7265625,
"min": 68525.203125,
"max": 78009.5859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.77142857142857,
"min": 84.7508591065292,
"max": 385.0076923076923,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49755.0,
"min": 48937.0,
"max": 50062.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999588.0,
"min": 49903.0,
"max": 1999588.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999588.0,
"min": 49903.0,
"max": 1999588.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.384751796722412,
"min": 0.08408811688423157,
"max": 2.4821035861968994,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1251.9947509765625,
"min": 10.847367286682129,
"max": 1387.38720703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7328809752918426,
"min": 1.7511386564073637,
"max": 4.0421470364244065,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1959.7625120282173,
"min": 225.8968866765499,
"max": 2212.5894265174866,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7328809752918426,
"min": 1.7511386564073637,
"max": 4.0421470364244065,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1959.7625120282173,
"min": 225.8968866765499,
"max": 2212.5894265174866,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015705139327716704,
"min": 0.014310311298565161,
"max": 0.021589645793331634,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03141027865543341,
"min": 0.028620622597130323,
"max": 0.05782969029587548,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04626583997160196,
"min": 0.02179873138666153,
"max": 0.060155202510456245,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09253167994320392,
"min": 0.04359746277332306,
"max": 0.16822766326367855,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.632248455949989e-06,
"min": 4.632248455949989e-06,
"max": 0.00029537385154204996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.264496911899979e-06,
"min": 9.264496911899979e-06,
"max": 0.0008441332686222499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10154405,
"min": 0.10154405,
"max": 0.19845795000000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2030881,
"min": 0.2030881,
"max": 0.5813777499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.704809499999986e-05,
"min": 8.704809499999986e-05,
"max": 0.0049230517050000006,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017409618999999972,
"min": 0.00017409618999999972,
"max": 0.014070749724999998,
"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": "1712123616",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712126023"
},
"total": 2407.3754353470003,
"count": 1,
"self": 0.44073831400055496,
"children": {
"run_training.setup": {
"total": 0.06232487800002673,
"count": 1,
"self": 0.06232487800002673
},
"TrainerController.start_learning": {
"total": 2406.8723721549995,
"count": 1,
"self": 4.34032256190585,
"children": {
"TrainerController._reset_env": {
"total": 2.9309199790000093,
"count": 1,
"self": 2.9309199790000093
},
"TrainerController.advance": {
"total": 2399.4856755470937,
"count": 232056,
"self": 4.656960270065156,
"children": {
"env_step": {
"total": 1934.6376195690575,
"count": 232056,
"self": 1601.5461497601714,
"children": {
"SubprocessEnvManager._take_step": {
"total": 330.19859364991134,
"count": 232056,
"self": 16.15214390988865,
"children": {
"TorchPolicy.evaluate": {
"total": 314.0464497400227,
"count": 222943,
"self": 314.0464497400227
}
}
},
"workers": {
"total": 2.8928761589746728,
"count": 232056,
"self": 0.0,
"children": {
"worker_root": {
"total": 2399.656721652002,
"count": 232056,
"is_parallel": true,
"self": 1106.193206334015,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009102500000608416,
"count": 1,
"is_parallel": true,
"self": 0.00024649500005580194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006637550000050396,
"count": 2,
"is_parallel": true,
"self": 0.0006637550000050396
}
}
},
"UnityEnvironment.step": {
"total": 0.02952521199995317,
"count": 1,
"is_parallel": true,
"self": 0.0003739559998621189,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002023450000478988,
"count": 1,
"is_parallel": true,
"self": 0.0002023450000478988
},
"communicator.exchange": {
"total": 0.028207608999991862,
"count": 1,
"is_parallel": true,
"self": 0.028207608999991862
},
"steps_from_proto": {
"total": 0.0007413020000512915,
"count": 1,
"is_parallel": true,
"self": 0.00021829399997841392,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005230080000728776,
"count": 2,
"is_parallel": true,
"self": 0.0005230080000728776
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1293.463515317987,
"count": 232055,
"is_parallel": true,
"self": 39.52845130184278,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.44091346602943,
"count": 232055,
"is_parallel": true,
"self": 83.44091346602943
},
"communicator.exchange": {
"total": 1077.9806923061633,
"count": 232055,
"is_parallel": true,
"self": 1077.9806923061633
},
"steps_from_proto": {
"total": 92.51345824395139,
"count": 232055,
"is_parallel": true,
"self": 34.98416565090554,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.52929259304585,
"count": 464110,
"is_parallel": true,
"self": 57.52929259304585
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 460.19109570797116,
"count": 232056,
"self": 6.4411181739940275,
"children": {
"process_trajectory": {
"total": 152.61281234497676,
"count": 232056,
"self": 151.2851996629763,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3276126820004492,
"count": 10,
"self": 1.3276126820004492
}
}
},
"_update_policy": {
"total": 301.13716518900037,
"count": 96,
"self": 240.80931494899949,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.327850240000885,
"count": 2880,
"self": 60.327850240000885
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.079999472305644e-07,
"count": 1,
"self": 9.079999472305644e-07
},
"TrainerController._save_models": {
"total": 0.11545315900002606,
"count": 1,
"self": 0.0019989649999843095,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11345419400004175,
"count": 1,
"self": 0.11345419400004175
}
}
}
}
}
}
}