ppo-Huggy / run_logs /timers.json
BBBBirdIsTheWord's picture
Huggy
f9430b1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4057317972183228,
"min": 1.4057317972183228,
"max": 1.4285993576049805,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71616.4140625,
"min": 68975.421875,
"max": 77396.640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.82680412371134,
"min": 83.16243654822335,
"max": 411.58196721311475,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49871.0,
"min": 48995.0,
"max": 50213.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999624.0,
"min": 49863.0,
"max": 1999624.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999624.0,
"min": 49863.0,
"max": 1999624.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.358287811279297,
"min": 0.03605135530233383,
"max": 2.445579767227173,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1143.76953125,
"min": 4.362214088439941,
"max": 1415.99072265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.558546008154289,
"min": 1.7080816731226345,
"max": 3.9922988148927687,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1725.8948139548302,
"min": 206.67788244783878,
"max": 2242.4900067448616,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.558546008154289,
"min": 1.7080816731226345,
"max": 3.9922988148927687,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1725.8948139548302,
"min": 206.67788244783878,
"max": 2242.4900067448616,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016830631176708268,
"min": 0.013568720975632054,
"max": 0.019894206718405864,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0504918935301248,
"min": 0.029131956778292077,
"max": 0.05680776809094823,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04805708556539482,
"min": 0.022731806865582863,
"max": 0.06375706618030866,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14417125669618447,
"min": 0.045463613731165725,
"max": 0.17925125857194266,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2815489061833305e-06,
"min": 3.2815489061833305e-06,
"max": 0.00029531490156169994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.844646718549992e-06,
"min": 9.844646718549992e-06,
"max": 0.0008440839186386999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109381666666668,
"min": 0.10109381666666668,
"max": 0.19843829999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30328145000000006,
"min": 0.2073275,
"max": 0.5813612999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.458145166666663e-05,
"min": 6.458145166666663e-05,
"max": 0.00492207117,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001937443549999999,
"min": 0.0001937443549999999,
"max": 0.014069928870000002,
"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": "1694926775",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1694929585"
},
"total": 2810.571242696,
"count": 1,
"self": 0.48822463099986635,
"children": {
"run_training.setup": {
"total": 0.07150026400000797,
"count": 1,
"self": 0.07150026400000797
},
"TrainerController.start_learning": {
"total": 2810.011517801,
"count": 1,
"self": 5.832245214961404,
"children": {
"TrainerController._reset_env": {
"total": 5.047674045999997,
"count": 1,
"self": 5.047674045999997
},
"TrainerController.advance": {
"total": 2798.963599639039,
"count": 231735,
"self": 5.622812546008845,
"children": {
"env_step": {
"total": 2171.569099096965,
"count": 231735,
"self": 1826.3255861739062,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.39614788704614,
"count": 231735,
"self": 19.896646952046524,
"children": {
"TorchPolicy.evaluate": {
"total": 321.4995009349996,
"count": 223026,
"self": 321.4995009349996
}
}
},
"workers": {
"total": 3.84736503601286,
"count": 231735,
"self": 0.0,
"children": {
"worker_root": {
"total": 2800.7233249939945,
"count": 231735,
"is_parallel": true,
"self": 1314.456509237024,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001142869999995355,
"count": 1,
"is_parallel": true,
"self": 0.00033337599998617407,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000809494000009181,
"count": 2,
"is_parallel": true,
"self": 0.000809494000009181
}
}
},
"UnityEnvironment.step": {
"total": 0.030942381000016894,
"count": 1,
"is_parallel": true,
"self": 0.00036896299999966686,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002351310000108242,
"count": 1,
"is_parallel": true,
"self": 0.0002351310000108242
},
"communicator.exchange": {
"total": 0.02952136800001881,
"count": 1,
"is_parallel": true,
"self": 0.02952136800001881
},
"steps_from_proto": {
"total": 0.0008169189999875925,
"count": 1,
"is_parallel": true,
"self": 0.00023148999997602004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005854290000115725,
"count": 2,
"is_parallel": true,
"self": 0.0005854290000115725
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1486.2668157569706,
"count": 231734,
"is_parallel": true,
"self": 45.38521623903739,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.36880133090145,
"count": 231734,
"is_parallel": true,
"self": 86.36880133090145
},
"communicator.exchange": {
"total": 1241.7393490870086,
"count": 231734,
"is_parallel": true,
"self": 1241.7393490870086
},
"steps_from_proto": {
"total": 112.77344910002307,
"count": 231734,
"is_parallel": true,
"self": 38.86237533097784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.91107376904523,
"count": 463468,
"is_parallel": true,
"self": 73.91107376904523
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 621.7716879960649,
"count": 231735,
"self": 8.697390855961999,
"children": {
"process_trajectory": {
"total": 147.95227974210334,
"count": 231735,
"self": 146.5213734021037,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4309063399996376,
"count": 10,
"self": 1.4309063399996376
}
}
},
"_update_policy": {
"total": 465.12201739799957,
"count": 97,
"self": 397.85882657499985,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.26319082299972,
"count": 2910,
"self": 67.26319082299972
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3439998838293832e-06,
"count": 1,
"self": 1.3439998838293832e-06
},
"TrainerController._save_models": {
"total": 0.16799755700003516,
"count": 1,
"self": 0.0024250179999398824,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16557253900009528,
"count": 1,
"self": 0.16557253900009528
}
}
}
}
}
}
}