ppo-Huggy / run_logs /timers.json
rajveer43's picture
Huggy
142b712 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4058140516281128,
"min": 1.4058140516281128,
"max": 1.4276233911514282,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71697.921875,
"min": 68079.6953125,
"max": 76810.5859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.33884297520662,
"min": 87.91119005328596,
"max": 401.3412698412698,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49532.0,
"min": 48893.0,
"max": 50569.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999896.0,
"min": 49945.0,
"max": 1999896.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999896.0,
"min": 49945.0,
"max": 1999896.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.358872652053833,
"min": 0.19607065618038177,
"max": 2.4110264778137207,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1141.6943359375,
"min": 24.508832931518555,
"max": 1336.904296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6447698163592124,
"min": 1.8111399322748185,
"max": 3.892011484820792,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1764.068591117859,
"min": 226.3924915343523,
"max": 2121.8845189213753,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6447698163592124,
"min": 1.8111399322748185,
"max": 3.892011484820792,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1764.068591117859,
"min": 226.3924915343523,
"max": 2121.8845189213753,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016699505443426056,
"min": 0.013862945905647293,
"max": 0.02002294796402566,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05009851633027817,
"min": 0.029796613568214524,
"max": 0.056321256140169376,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.049336637597944995,
"min": 0.02252273081491391,
"max": 0.0546608367934823,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.148009912793835,
"min": 0.04504546162982782,
"max": 0.15783367902040482,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1906489364833255e-06,
"min": 3.1906489364833255e-06,
"max": 0.00029532232655922496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.571946809449977e-06,
"min": 9.571946809449977e-06,
"max": 0.0008439522186825998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10106351666666669,
"min": 0.10106351666666669,
"max": 0.19844077499999999,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30319055000000006,
"min": 0.20728000000000002,
"max": 0.5813174000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.306948166666654e-05,
"min": 6.306948166666654e-05,
"max": 0.004922194672500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001892084449999996,
"min": 0.0001892084449999996,
"max": 0.01406773826,
"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": "1724260407",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724262732"
},
"total": 2324.698939084,
"count": 1,
"self": 0.4388652560000992,
"children": {
"run_training.setup": {
"total": 0.05715623000003234,
"count": 1,
"self": 0.05715623000003234
},
"TrainerController.start_learning": {
"total": 2324.2029175979997,
"count": 1,
"self": 4.2484453360443695,
"children": {
"TrainerController._reset_env": {
"total": 3.191840737000007,
"count": 1,
"self": 3.191840737000007
},
"TrainerController.advance": {
"total": 2316.636959156955,
"count": 231893,
"self": 4.514840907911093,
"children": {
"env_step": {
"total": 1826.8950327450466,
"count": 231893,
"self": 1503.5347144680209,
"children": {
"SubprocessEnvManager._take_step": {
"total": 320.5608469939832,
"count": 231893,
"self": 16.313885922923646,
"children": {
"TorchPolicy.evaluate": {
"total": 304.24696107105956,
"count": 223044,
"self": 304.24696107105956
}
}
},
"workers": {
"total": 2.7994712830424078,
"count": 231893,
"self": 0.0,
"children": {
"worker_root": {
"total": 2317.2148369670786,
"count": 231893,
"is_parallel": true,
"self": 1107.6383741820555,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001008885000032933,
"count": 1,
"is_parallel": true,
"self": 0.0002913619999844741,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007175230000484589,
"count": 2,
"is_parallel": true,
"self": 0.0007175230000484589
}
}
},
"UnityEnvironment.step": {
"total": 0.02836310499992578,
"count": 1,
"is_parallel": true,
"self": 0.00035976499987100397,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025586000003841036,
"count": 1,
"is_parallel": true,
"self": 0.00025586000003841036
},
"communicator.exchange": {
"total": 0.02700635999997303,
"count": 1,
"is_parallel": true,
"self": 0.02700635999997303
},
"steps_from_proto": {
"total": 0.0007411200000433382,
"count": 1,
"is_parallel": true,
"self": 0.00019778500006850663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005433349999748316,
"count": 2,
"is_parallel": true,
"self": 0.0005433349999748316
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1209.576462785023,
"count": 231892,
"is_parallel": true,
"self": 37.692352806084045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.01857333100827,
"count": 231892,
"is_parallel": true,
"self": 79.01857333100827
},
"communicator.exchange": {
"total": 1005.1183061469627,
"count": 231892,
"is_parallel": true,
"self": 1005.1183061469627
},
"steps_from_proto": {
"total": 87.74723050096804,
"count": 231892,
"is_parallel": true,
"self": 31.180267205989253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.56696329497879,
"count": 463784,
"is_parallel": true,
"self": 56.56696329497879
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 485.2270855039974,
"count": 231893,
"self": 6.4851741069502395,
"children": {
"process_trajectory": {
"total": 147.040360693048,
"count": 231893,
"self": 145.69544340304844,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3449172899995574,
"count": 10,
"self": 1.3449172899995574
}
}
},
"_update_policy": {
"total": 331.70155070399915,
"count": 97,
"self": 267.430258392998,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.27129231100116,
"count": 2910,
"self": 64.27129231100116
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.950002327561378e-07,
"count": 1,
"self": 7.950002327561378e-07
},
"TrainerController._save_models": {
"total": 0.12567157300009058,
"count": 1,
"self": 0.0019334050002726144,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12373816799981796,
"count": 1,
"self": 0.12373816799981796
}
}
}
}
}
}
}