ppo-Huggy / run_logs /timers.json
dcv21's picture
Huggy
b9d4caf
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045740365982056,
"min": 1.4045740365982056,
"max": 1.4257943630218506,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69776.4296875,
"min": 69102.75,
"max": 77413.125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.28952380952381,
"min": 79.0224,
"max": 408.0967741935484,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49502.0,
"min": 48757.0,
"max": 50604.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999287.0,
"min": 49978.0,
"max": 1999287.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999287.0,
"min": 49978.0,
"max": 1999287.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3389642238616943,
"min": 0.043773628771305084,
"max": 2.48293399810791,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1227.9561767578125,
"min": 5.384156227111816,
"max": 1468.1148681640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6445503438086737,
"min": 1.9958993220716956,
"max": 4.044752264669699,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1913.3889304995537,
"min": 245.49561661481857,
"max": 2384.304604768753,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6445503438086737,
"min": 1.9958993220716956,
"max": 4.044752264669699,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1913.3889304995537,
"min": 245.49561661481857,
"max": 2384.304604768753,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01615026400433837,
"min": 0.012370442170686146,
"max": 0.01995338857717191,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04845079201301511,
"min": 0.024740884341372293,
"max": 0.05986016573151573,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04911420647468832,
"min": 0.02164313479637106,
"max": 0.05592957995831967,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14734261942406496,
"min": 0.04328626959274212,
"max": 0.16696900961299738,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.414598861833331e-06,
"min": 3.414598861833331e-06,
"max": 0.0002953224765591749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0243796585499992e-05,
"min": 1.0243796585499992e-05,
"max": 0.00084385216871595,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113816666666668,
"min": 0.10113816666666668,
"max": 0.19844082499999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30341450000000003,
"min": 0.20745349999999996,
"max": 0.5812840499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.679451666666666e-05,
"min": 6.679451666666666e-05,
"max": 0.004922197167499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020038354999999997,
"min": 0.00020038354999999997,
"max": 0.014066074094999999,
"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": "1692180850",
"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 --force",
"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": "1692183308"
},
"total": 2457.769432139,
"count": 1,
"self": 0.47578943299959064,
"children": {
"run_training.setup": {
"total": 0.04097376900006111,
"count": 1,
"self": 0.04097376900006111
},
"TrainerController.start_learning": {
"total": 2457.252668937,
"count": 1,
"self": 4.437578391946772,
"children": {
"TrainerController._reset_env": {
"total": 5.047630355000024,
"count": 1,
"self": 5.047630355000024
},
"TrainerController.advance": {
"total": 2447.6463103370534,
"count": 232657,
"self": 4.564853917192977,
"children": {
"env_step": {
"total": 1882.295947909987,
"count": 232657,
"self": 1590.6416479108598,
"children": {
"SubprocessEnvManager._take_step": {
"total": 288.6011008620749,
"count": 232657,
"self": 17.1382244840122,
"children": {
"TorchPolicy.evaluate": {
"total": 271.4628763780627,
"count": 222936,
"self": 271.4628763780627
}
}
},
"workers": {
"total": 3.0531991370523883,
"count": 232657,
"self": 0.0,
"children": {
"worker_root": {
"total": 2449.7510740139796,
"count": 232657,
"is_parallel": true,
"self": 1150.7930673419864,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008478490000243255,
"count": 1,
"is_parallel": true,
"self": 0.00022168999998939398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006261590000349315,
"count": 2,
"is_parallel": true,
"self": 0.0006261590000349315
}
}
},
"UnityEnvironment.step": {
"total": 0.04685446500002399,
"count": 1,
"is_parallel": true,
"self": 0.000314822999939679,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021483499995156308,
"count": 1,
"is_parallel": true,
"self": 0.00021483499995156308
},
"communicator.exchange": {
"total": 0.04556960800005072,
"count": 1,
"is_parallel": true,
"self": 0.04556960800005072
},
"steps_from_proto": {
"total": 0.0007551990000820297,
"count": 1,
"is_parallel": true,
"self": 0.0002243310000267229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005308680000553068,
"count": 2,
"is_parallel": true,
"self": 0.0005308680000553068
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1298.9580066719932,
"count": 232656,
"is_parallel": true,
"self": 40.03160453703367,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.06462574800969,
"count": 232656,
"is_parallel": true,
"self": 82.06462574800969
},
"communicator.exchange": {
"total": 1077.3165711189063,
"count": 232656,
"is_parallel": true,
"self": 1077.3165711189063
},
"steps_from_proto": {
"total": 99.54520526804356,
"count": 232656,
"is_parallel": true,
"self": 35.13766240189375,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.40754286614981,
"count": 465312,
"is_parallel": true,
"self": 64.40754286614981
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 560.7855085098732,
"count": 232657,
"self": 6.697554919865979,
"children": {
"process_trajectory": {
"total": 142.1182167440055,
"count": 232657,
"self": 140.76245321900615,
"children": {
"RLTrainer._checkpoint": {
"total": 1.355763524999361,
"count": 10,
"self": 1.355763524999361
}
}
},
"_update_policy": {
"total": 411.96973684600175,
"count": 97,
"self": 351.8306739280023,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.13906291799947,
"count": 2910,
"self": 60.13906291799947
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.750001481734216e-07,
"count": 1,
"self": 9.750001481734216e-07
},
"TrainerController._save_models": {
"total": 0.12114887799998542,
"count": 1,
"self": 0.002545881000060035,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11860299699992538,
"count": 1,
"self": 0.11860299699992538
}
}
}
}
}
}
}