ppo-Huggy / run_logs /timers.json
moonlightlane's picture
Huggy
23275ee
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015222787857056,
"min": 1.4015222787857056,
"max": 1.4248689413070679,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68846.9765625,
"min": 67771.046875,
"max": 79246.375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.41316270566728,
"min": 75.57886676875957,
"max": 434.5130434782609,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49456.0,
"min": 49319.0,
"max": 49969.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999970.0,
"min": 49334.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999970.0,
"min": 49334.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.482023000717163,
"min": 0.06205550953745842,
"max": 2.5279324054718018,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1357.6666259765625,
"min": 7.0743279457092285,
"max": 1599.97265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7326945793258206,
"min": 1.7098502485375655,
"max": 3.97219507825955,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2041.783934891224,
"min": 194.92292833328247,
"max": 2526.652763426304,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7326945793258206,
"min": 1.7098502485375655,
"max": 3.97219507825955,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2041.783934891224,
"min": 194.92292833328247,
"max": 2526.652763426304,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01570047750137746,
"min": 0.013352003652188513,
"max": 0.020565281134622637,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04710143250413239,
"min": 0.028916554841756203,
"max": 0.055458757018641336,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05977338891890314,
"min": 0.02213281967366735,
"max": 0.06328611204193697,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17932016675670942,
"min": 0.0442656393473347,
"max": 0.18985833612581093,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.657948780716662e-06,
"min": 3.657948780716662e-06,
"max": 0.0002953376265541249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0973846342149986e-05,
"min": 1.0973846342149986e-05,
"max": 0.0008438400187199998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121928333333334,
"min": 0.10121928333333334,
"max": 0.19844587500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30365785,
"min": 0.2075627,
"max": 0.5812799999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.084223833333325e-05,
"min": 7.084223833333325e-05,
"max": 0.0049224491625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021252671499999974,
"min": 0.00021252671499999974,
"max": 0.014065872,
"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": "1674759229",
"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": "1.21.6",
"end_time_seconds": "1674761538"
},
"total": 2309.786263917,
"count": 1,
"self": 0.3929569559995798,
"children": {
"run_training.setup": {
"total": 0.10462227500011068,
"count": 1,
"self": 0.10462227500011068
},
"TrainerController.start_learning": {
"total": 2309.288684686,
"count": 1,
"self": 4.098430397965785,
"children": {
"TrainerController._reset_env": {
"total": 9.96126812700004,
"count": 1,
"self": 9.96126812700004
},
"TrainerController.advance": {
"total": 2295.1261196280348,
"count": 232819,
"self": 4.648783374195318,
"children": {
"env_step": {
"total": 1827.6125063657064,
"count": 232819,
"self": 1529.7478884147804,
"children": {
"SubprocessEnvManager._take_step": {
"total": 295.0806985980921,
"count": 232819,
"self": 15.6523187950811,
"children": {
"TorchPolicy.evaluate": {
"total": 279.428379803011,
"count": 222969,
"self": 69.95948025784492,
"children": {
"TorchPolicy.sample_actions": {
"total": 209.4688995451661,
"count": 222969,
"self": 209.4688995451661
}
}
}
}
},
"workers": {
"total": 2.783919352833891,
"count": 232819,
"self": 0.0,
"children": {
"worker_root": {
"total": 2300.6426102629275,
"count": 232819,
"is_parallel": true,
"self": 1046.84168168016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020902820001538203,
"count": 1,
"is_parallel": true,
"self": 0.0003164890003972687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017737929997565516,
"count": 2,
"is_parallel": true,
"self": 0.0017737929997565516
}
}
},
"UnityEnvironment.step": {
"total": 0.02711482699987755,
"count": 1,
"is_parallel": true,
"self": 0.00031358200021713856,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018590299987408798,
"count": 1,
"is_parallel": true,
"self": 0.00018590299987408798
},
"communicator.exchange": {
"total": 0.025730861999818444,
"count": 1,
"is_parallel": true,
"self": 0.025730861999818444
},
"steps_from_proto": {
"total": 0.0008844799999678798,
"count": 1,
"is_parallel": true,
"self": 0.00023445800025001517,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006500219997178647,
"count": 2,
"is_parallel": true,
"self": 0.0006500219997178647
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1253.8009285827675,
"count": 232818,
"is_parallel": true,
"self": 35.992098710964,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.70477813200068,
"count": 232818,
"is_parallel": true,
"self": 78.70477813200068
},
"communicator.exchange": {
"total": 1042.0286330619633,
"count": 232818,
"is_parallel": true,
"self": 1042.0286330619633
},
"steps_from_proto": {
"total": 97.07541867783948,
"count": 232818,
"is_parallel": true,
"self": 41.60500648876223,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.47041218907725,
"count": 465636,
"is_parallel": true,
"self": 55.47041218907725
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 462.86482988813304,
"count": 232819,
"self": 6.941270999403059,
"children": {
"process_trajectory": {
"total": 152.89319963572962,
"count": 232819,
"self": 151.7917037177299,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1014959179997277,
"count": 10,
"self": 1.1014959179997277
}
}
},
"_update_policy": {
"total": 303.03035925300037,
"count": 97,
"self": 248.97373283898742,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.05662641401295,
"count": 2910,
"self": 54.05662641401295
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.420001904596575e-07,
"count": 1,
"self": 8.420001904596575e-07
},
"TrainerController._save_models": {
"total": 0.1028656909993515,
"count": 1,
"self": 0.002040785999270156,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10082490500008134,
"count": 1,
"self": 0.10082490500008134
}
}
}
}
}
}
}