ppo-Huggy / run_logs /timers.json
rsilg's picture
Huggy
2c0edf7
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4096589088439941,
"min": 1.4096589088439941,
"max": 1.4287707805633545,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72325.3671875,
"min": 67974.0625,
"max": 76512.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 114.09280742459397,
"min": 98.8201581027668,
"max": 383.9076923076923,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49174.0,
"min": 48909.0,
"max": 50228.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999983.0,
"min": 49666.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999983.0,
"min": 49666.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3135838508605957,
"min": 0.09179792553186417,
"max": 2.3616886138916016,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 997.1546020507812,
"min": 11.84193229675293,
"max": 1179.183349609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4839470508203707,
"min": 1.728302187582319,
"max": 3.7083889887883115,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1501.5811789035797,
"min": 222.95098219811916,
"max": 1880.1532173156738,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4839470508203707,
"min": 1.728302187582319,
"max": 3.7083889887883115,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1501.5811789035797,
"min": 222.95098219811916,
"max": 1880.1532173156738,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01490569564703037,
"min": 0.013216842510610149,
"max": 0.019493532068736386,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02981139129406074,
"min": 0.026433685021220298,
"max": 0.05714377082282833,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04511536446710428,
"min": 0.022271101394047338,
"max": 0.054014352129565346,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09023072893420855,
"min": 0.044542202788094676,
"max": 0.16204305638869604,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.112798629100008e-06,
"min": 4.112798629100008e-06,
"max": 0.000295383001539,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.225597258200016e-06,
"min": 8.225597258200016e-06,
"max": 0.0008441179686273501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10137090000000001,
"min": 0.10137090000000001,
"max": 0.198461,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20274180000000003,
"min": 0.20274180000000003,
"max": 0.5813726500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.840791000000016e-05,
"min": 7.840791000000016e-05,
"max": 0.004923203900000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001568158200000003,
"min": 0.0001568158200000003,
"max": 0.014070495234999997,
"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": "1688492106",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "1688494561"
},
"total": 2454.7063996310003,
"count": 1,
"self": 0.6296191200008252,
"children": {
"run_training.setup": {
"total": 0.04050608999978067,
"count": 1,
"self": 0.04050608999978067
},
"TrainerController.start_learning": {
"total": 2454.0362744209997,
"count": 1,
"self": 4.42173912199587,
"children": {
"TrainerController._reset_env": {
"total": 4.173149043000194,
"count": 1,
"self": 4.173149043000194
},
"TrainerController.advance": {
"total": 2445.2681163750035,
"count": 230966,
"self": 4.583471822270894,
"children": {
"env_step": {
"total": 1915.3593444309067,
"count": 230966,
"self": 1611.5268493968188,
"children": {
"SubprocessEnvManager._take_step": {
"total": 300.93989028002215,
"count": 230966,
"self": 17.185104369053533,
"children": {
"TorchPolicy.evaluate": {
"total": 283.7547859109686,
"count": 223092,
"self": 283.7547859109686
}
}
},
"workers": {
"total": 2.8926047540658146,
"count": 230966,
"self": 0.0,
"children": {
"worker_root": {
"total": 2445.894801785071,
"count": 230966,
"is_parallel": true,
"self": 1130.3850810329209,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008600159999332391,
"count": 1,
"is_parallel": true,
"self": 0.00026251899953422253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005974970003990165,
"count": 2,
"is_parallel": true,
"self": 0.0005974970003990165
}
}
},
"UnityEnvironment.step": {
"total": 0.02834632900021461,
"count": 1,
"is_parallel": true,
"self": 0.00032454400025017094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021129800006747246,
"count": 1,
"is_parallel": true,
"self": 0.00021129800006747246
},
"communicator.exchange": {
"total": 0.027135461999932886,
"count": 1,
"is_parallel": true,
"self": 0.027135461999932886
},
"steps_from_proto": {
"total": 0.00067502499996408,
"count": 1,
"is_parallel": true,
"self": 0.0001873590003924619,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00048766599957161816,
"count": 2,
"is_parallel": true,
"self": 0.00048766599957161816
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1315.5097207521503,
"count": 230965,
"is_parallel": true,
"self": 39.8961238656334,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.77491719786303,
"count": 230965,
"is_parallel": true,
"self": 79.77491719786303
},
"communicator.exchange": {
"total": 1100.4123878396658,
"count": 230965,
"is_parallel": true,
"self": 1100.4123878396658
},
"steps_from_proto": {
"total": 95.42629184898806,
"count": 230965,
"is_parallel": true,
"self": 33.255530062165235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.17076178682282,
"count": 461930,
"is_parallel": true,
"self": 62.17076178682282
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 525.3253001218259,
"count": 230966,
"self": 7.272451178579104,
"children": {
"process_trajectory": {
"total": 131.19425118424988,
"count": 230966,
"self": 129.92031553625065,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2739356479992239,
"count": 10,
"self": 1.2739356479992239
}
}
},
"_update_policy": {
"total": 386.8585977589969,
"count": 96,
"self": 326.2770013459799,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.581596413016996,
"count": 2880,
"self": 60.581596413016996
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1590000212891027e-06,
"count": 1,
"self": 1.1590000212891027e-06
},
"TrainerController._save_models": {
"total": 0.17326872200010257,
"count": 1,
"self": 0.0025132140008281567,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17075550799927441,
"count": 1,
"self": 0.17075550799927441
}
}
}
}
}
}
}