dvesely's picture
First Push
6b9d741
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5781895518302917,
"min": 0.5781895518302917,
"max": 1.4310767650604248,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17336.435546875,
"min": 17336.435546875,
"max": 43413.14453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989874.0,
"min": 29908.0,
"max": 989874.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989874.0,
"min": 29908.0,
"max": 989874.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.25602298974990845,
"min": -0.10046319663524628,
"max": 0.34757521748542786,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 66.8219985961914,
"min": -24.31209373474121,
"max": 91.06470489501953,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009738381020724773,
"min": 0.0008388523710891604,
"max": 0.31525084376335144,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.541717529296875,
"min": 0.20719653367996216,
"max": 74.71444702148438,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07014144473370314,
"min": 0.06606073988277021,
"max": 0.07346060134326411,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.981980226271844,
"min": 0.6537547739017842,
"max": 1.0680560804655268,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011179476053712278,
"min": 0.0002400603709355581,
"max": 0.01313779207499893,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1565126647519719,
"min": 0.003120784822162255,
"max": 0.183929089049985,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.484604648021431e-06,
"min": 7.484604648021431e-06,
"max": 0.0002948780017073334,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010478446507230004,
"min": 0.00010478446507230004,
"max": 0.0036092148969283995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249483571428573,
"min": 0.10249483571428573,
"max": 0.19829266666666667,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349277000000003,
"min": 1.4349277000000003,
"max": 2.5696701000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025923408785714295,
"min": 0.00025923408785714295,
"max": 0.0098294374,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003629277230000001,
"min": 0.003629277230000001,
"max": 0.12031685284000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.005980806890875101,
"min": 0.005777298007160425,
"max": 0.38448333740234375,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.08373129367828369,
"min": 0.08088216930627823,
"max": 3.4603500366210938,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 559.5178571428571,
"min": 494.375,
"max": 987.90625,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31333.0,
"min": 17474.0,
"max": 32962.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.0475106839356678,
"min": -0.9262625491246581,
"max": 1.2555714015449797,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 58.660598300397396,
"min": -29.64040157198906,
"max": 72.3219985961914,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.0475106839356678,
"min": -0.9262625491246581,
"max": 1.2555714015449797,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 58.660598300397396,
"min": -29.64040157198906,
"max": 72.3219985961914,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.035446381945803296,
"min": 0.03236317440626278,
"max": 9.163154803216457,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.9849973889649846,
"min": 1.7192696667189011,
"max": 164.93678645789623,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1682767849",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1682770079"
},
"total": 2229.5854096940006,
"count": 1,
"self": 0.43740534000062326,
"children": {
"run_training.setup": {
"total": 0.05298393199973361,
"count": 1,
"self": 0.05298393199973361
},
"TrainerController.start_learning": {
"total": 2229.0950204220003,
"count": 1,
"self": 1.2857290799447583,
"children": {
"TrainerController._reset_env": {
"total": 4.001959848999832,
"count": 1,
"self": 4.001959848999832
},
"TrainerController.advance": {
"total": 2223.472611262056,
"count": 63413,
"self": 1.3565112620531181,
"children": {
"env_step": {
"total": 1357.602587155,
"count": 63413,
"self": 1247.3433422700418,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.48689040200406,
"count": 63413,
"self": 4.542483242144499,
"children": {
"TorchPolicy.evaluate": {
"total": 104.94440715985957,
"count": 62556,
"self": 104.94440715985957
}
}
},
"workers": {
"total": 0.7723544829541424,
"count": 63413,
"self": 0.0,
"children": {
"worker_root": {
"total": 2224.3576986420753,
"count": 63413,
"is_parallel": true,
"self": 1083.237607138065,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017195939999510301,
"count": 1,
"is_parallel": true,
"self": 0.0006058210014998622,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001113772998451168,
"count": 8,
"is_parallel": true,
"self": 0.001113772998451168
}
}
},
"UnityEnvironment.step": {
"total": 0.07972573799997917,
"count": 1,
"is_parallel": true,
"self": 0.0005180589996598428,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004992320000383188,
"count": 1,
"is_parallel": true,
"self": 0.0004992320000383188
},
"communicator.exchange": {
"total": 0.06955864800011113,
"count": 1,
"is_parallel": true,
"self": 0.06955864800011113
},
"steps_from_proto": {
"total": 0.009149799000169878,
"count": 1,
"is_parallel": true,
"self": 0.0003869900001518545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008762809000018024,
"count": 8,
"is_parallel": true,
"self": 0.008762809000018024
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1141.1200915040104,
"count": 63412,
"is_parallel": true,
"self": 30.655474799015792,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.08667868604016,
"count": 63412,
"is_parallel": true,
"self": 22.08667868604016
},
"communicator.exchange": {
"total": 998.4373520179793,
"count": 63412,
"is_parallel": true,
"self": 998.4373520179793
},
"steps_from_proto": {
"total": 89.94058600097514,
"count": 63412,
"is_parallel": true,
"self": 18.619837544793427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.32074845618172,
"count": 507296,
"is_parallel": true,
"self": 71.32074845618172
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 864.5135128450029,
"count": 63413,
"self": 2.4247682090990565,
"children": {
"process_trajectory": {
"total": 108.15178624292048,
"count": 63413,
"self": 107.43312167191971,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7186645710007724,
"count": 2,
"self": 0.7186645710007724
}
}
},
"_update_policy": {
"total": 753.9369583929833,
"count": 457,
"self": 447.7145140770049,
"children": {
"TorchPPOOptimizer.update": {
"total": 306.22244431597846,
"count": 30404,
"self": 306.22244431597846
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.679997674538754e-07,
"count": 1,
"self": 9.679997674538754e-07
},
"TrainerController._save_models": {
"total": 0.3347192629998972,
"count": 1,
"self": 0.007855175999793573,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3268640870001036,
"count": 1,
"self": 0.3268640870001036
}
}
}
}
}
}
}