ppo-Huggy / run_logs /timers.json
rodrfons's picture
Huggy
c0aa85a
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015130996704102,
"min": 1.4015130996704102,
"max": 1.4253166913986206,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69293.609375,
"min": 68819.828125,
"max": 74960.9140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.20970266040689,
"min": 74.43872919818457,
"max": 421.69747899159665,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49337.0,
"min": 48909.0,
"max": 50182.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999940.0,
"min": 49551.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999940.0,
"min": 49551.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4805707931518555,
"min": 0.0748320147395134,
"max": 2.541454315185547,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1585.084716796875,
"min": 8.830177307128906,
"max": 1659.4620361328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.834465375901761,
"min": 1.8129098640154984,
"max": 4.099937227904069,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2450.2233752012253,
"min": 213.9233639538288,
"max": 2561.912171781063,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.834465375901761,
"min": 1.8129098640154984,
"max": 4.099937227904069,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2450.2233752012253,
"min": 213.9233639538288,
"max": 2561.912171781063,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014845110942769678,
"min": 0.013424946147036583,
"max": 0.019917004189725654,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.044535332828309036,
"min": 0.026849892294073165,
"max": 0.05587162899901159,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05844020222624143,
"min": 0.021861958721031746,
"max": 0.06353189429889122,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1753206066787243,
"min": 0.04372391744206349,
"max": 0.18924565501511098,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6178987940666587e-06,
"min": 3.6178987940666587e-06,
"max": 0.00029534535155155005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0853696382199977e-05,
"min": 1.0853696382199977e-05,
"max": 0.0008440455186515,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120593333333334,
"min": 0.10120593333333334,
"max": 0.19844845,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30361780000000005,
"min": 0.20754385,
"max": 0.5813485,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.017607333333323e-05,
"min": 7.017607333333323e-05,
"max": 0.004922577655000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002105282199999997,
"min": 0.0002105282199999997,
"max": 0.014069290150000004,
"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": "1677436118",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677438515"
},
"total": 2397.7368738659998,
"count": 1,
"self": 0.4354551819997141,
"children": {
"run_training.setup": {
"total": 0.11508414200000061,
"count": 1,
"self": 0.11508414200000061
},
"TrainerController.start_learning": {
"total": 2397.186334542,
"count": 1,
"self": 4.193698457035225,
"children": {
"TrainerController._reset_env": {
"total": 10.697533342000014,
"count": 1,
"self": 10.697533342000014
},
"TrainerController.advance": {
"total": 2382.1894101959647,
"count": 233139,
"self": 4.705116733072828,
"children": {
"env_step": {
"total": 1846.692937343963,
"count": 233139,
"self": 1546.3998705919566,
"children": {
"SubprocessEnvManager._take_step": {
"total": 297.51831918997243,
"count": 233139,
"self": 15.911997437072273,
"children": {
"TorchPolicy.evaluate": {
"total": 281.60632175290016,
"count": 222938,
"self": 71.04522513380618,
"children": {
"TorchPolicy.sample_actions": {
"total": 210.56109661909397,
"count": 222938,
"self": 210.56109661909397
}
}
}
}
},
"workers": {
"total": 2.7747475620338378,
"count": 233139,
"self": 0.0,
"children": {
"worker_root": {
"total": 2388.3959878469846,
"count": 233139,
"is_parallel": true,
"self": 1136.545460227979,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0032154159999890908,
"count": 1,
"is_parallel": true,
"self": 0.0003394739999862395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028759420000028513,
"count": 2,
"is_parallel": true,
"self": 0.0028759420000028513
}
}
},
"UnityEnvironment.step": {
"total": 0.04768755700001748,
"count": 1,
"is_parallel": true,
"self": 0.0003351039999870409,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038706999998794345,
"count": 1,
"is_parallel": true,
"self": 0.00038706999998794345
},
"communicator.exchange": {
"total": 0.046255275000021356,
"count": 1,
"is_parallel": true,
"self": 0.046255275000021356
},
"steps_from_proto": {
"total": 0.0007101080000211368,
"count": 1,
"is_parallel": true,
"self": 0.00024868700000979516,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004614210000113417,
"count": 2,
"is_parallel": true,
"self": 0.0004614210000113417
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1251.8505276190056,
"count": 233138,
"is_parallel": true,
"self": 38.89363842198213,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.2478066319672,
"count": 233138,
"is_parallel": true,
"self": 78.2478066319672
},
"communicator.exchange": {
"total": 1043.3817153040332,
"count": 233138,
"is_parallel": true,
"self": 1043.3817153040332
},
"steps_from_proto": {
"total": 91.32736726102308,
"count": 233138,
"is_parallel": true,
"self": 36.80185960401121,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.52550765701187,
"count": 466276,
"is_parallel": true,
"self": 54.52550765701187
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 530.7913561189289,
"count": 233139,
"self": 6.728766893912052,
"children": {
"process_trajectory": {
"total": 169.82338358201844,
"count": 233139,
"self": 168.537250184019,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2861333979994356,
"count": 10,
"self": 1.2861333979994356
}
}
},
"_update_policy": {
"total": 354.23920564299846,
"count": 97,
"self": 296.30317627699725,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.93602936600121,
"count": 2910,
"self": 57.93602936600121
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.720000212430023e-07,
"count": 1,
"self": 7.720000212430023e-07
},
"TrainerController._save_models": {
"total": 0.10569177500019578,
"count": 1,
"self": 0.0051663790004568,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10052539599973898,
"count": 1,
"self": 0.10052539599973898
}
}
}
}
}
}
}