ppo-Huggy / run_logs /timers.json
Balab2021's picture
Huggy
375b701 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4114713668823242,
"min": 1.4114713668823242,
"max": 1.4297913312911987,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70620.1484375,
"min": 68437.328125,
"max": 78103.2890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 109.3355408388521,
"min": 90.33941605839416,
"max": 412.5983606557377,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49529.0,
"min": 48781.0,
"max": 50337.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49709.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49709.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2685093879699707,
"min": 0.11077821254730225,
"max": 2.4174020290374756,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1027.634765625,
"min": 13.404163360595703,
"max": 1324.736328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5053201851992153,
"min": 1.884971677518088,
"max": 3.8972247118564476,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1587.9100438952446,
"min": 228.08157297968864,
"max": 2073.32354670763,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5053201851992153,
"min": 1.884971677518088,
"max": 3.8972247118564476,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1587.9100438952446,
"min": 228.08157297968864,
"max": 2073.32354670763,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016370820426770176,
"min": 0.014362972006428108,
"max": 0.018576375613661687,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03274164085354035,
"min": 0.029919816211804576,
"max": 0.05572912684098506,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04347275085747242,
"min": 0.022656979411840437,
"max": 0.061019168111185226,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08694550171494483,
"min": 0.045313958823680875,
"max": 0.17268241122364997,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.608773463775008e-06,
"min": 4.608773463775008e-06,
"max": 0.000295270876576375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.217546927550016e-06,
"min": 9.217546927550016e-06,
"max": 0.0008438713687095498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10153622500000001,
"min": 0.10153622500000001,
"max": 0.198423625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20307245000000002,
"min": 0.20307245000000002,
"max": 0.58129045,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.665762750000012e-05,
"min": 8.665762750000012e-05,
"max": 0.004921338887500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017331525500000023,
"min": 0.00017331525500000023,
"max": 0.014066393454999998,
"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": "1739818579",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739820969"
},
"total": 2389.920839589,
"count": 1,
"self": 0.43235364800011666,
"children": {
"run_training.setup": {
"total": 0.022820142999989912,
"count": 1,
"self": 0.022820142999989912
},
"TrainerController.start_learning": {
"total": 2389.465665798,
"count": 1,
"self": 4.150967974901505,
"children": {
"TrainerController._reset_env": {
"total": 3.115381470999978,
"count": 1,
"self": 3.115381470999978
},
"TrainerController.advance": {
"total": 2382.084831128099,
"count": 231716,
"self": 4.3992339580818225,
"children": {
"env_step": {
"total": 1885.7824572890102,
"count": 231716,
"self": 1477.7077772200532,
"children": {
"SubprocessEnvManager._take_step": {
"total": 405.5094497070379,
"count": 231716,
"self": 15.248557567970238,
"children": {
"TorchPolicy.evaluate": {
"total": 390.26089213906766,
"count": 223037,
"self": 390.26089213906766
}
}
},
"workers": {
"total": 2.5652303619190207,
"count": 231716,
"self": 0.0,
"children": {
"worker_root": {
"total": 2382.399541377044,
"count": 231716,
"is_parallel": true,
"self": 1178.1761799110432,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010218040000609108,
"count": 1,
"is_parallel": true,
"self": 0.00039219100005993823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006296130000009725,
"count": 2,
"is_parallel": true,
"self": 0.0006296130000009725
}
}
},
"UnityEnvironment.step": {
"total": 0.03916089099993769,
"count": 1,
"is_parallel": true,
"self": 0.0004229319999922154,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021106199994846975,
"count": 1,
"is_parallel": true,
"self": 0.00021106199994846975
},
"communicator.exchange": {
"total": 0.0375983769999948,
"count": 1,
"is_parallel": true,
"self": 0.0375983769999948
},
"steps_from_proto": {
"total": 0.0009285200000022087,
"count": 1,
"is_parallel": true,
"self": 0.0002568249999512773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006716950000509314,
"count": 2,
"is_parallel": true,
"self": 0.0006716950000509314
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1204.2233614660008,
"count": 231715,
"is_parallel": true,
"self": 36.709541843975785,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.24560934910335,
"count": 231715,
"is_parallel": true,
"self": 79.24560934910335
},
"communicator.exchange": {
"total": 1003.5331667879408,
"count": 231715,
"is_parallel": true,
"self": 1003.5331667879408
},
"steps_from_proto": {
"total": 84.73504348498079,
"count": 231715,
"is_parallel": true,
"self": 29.408391259010273,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.32665222597052,
"count": 463430,
"is_parallel": true,
"self": 55.32665222597052
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.9031398810067,
"count": 231716,
"self": 6.334026777953568,
"children": {
"process_trajectory": {
"total": 153.3994345230526,
"count": 231716,
"self": 152.13931177205245,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2601227510001536,
"count": 10,
"self": 1.2601227510001536
}
}
},
"_update_policy": {
"total": 332.16967858000055,
"count": 96,
"self": 265.5109092550116,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.65876932498895,
"count": 2880,
"self": 66.65876932498895
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3439998838293832e-06,
"count": 1,
"self": 1.3439998838293832e-06
},
"TrainerController._save_models": {
"total": 0.11448387999962506,
"count": 1,
"self": 0.0020715259993266955,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11241235400029836,
"count": 1,
"self": 0.11241235400029836
}
}
}
}
}
}
}