ppo-Huggy / run_logs /timers.json
frahman's picture
Huggy
f109254 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4035050868988037,
"min": 1.4035050868988037,
"max": 1.425636887550354,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71201.21875,
"min": 68586.0703125,
"max": 77766.71875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.36068702290076,
"min": 87.13028169014085,
"max": 377.82706766917295,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49445.0,
"min": 49054.0,
"max": 50291.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999950.0,
"min": 49876.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999950.0,
"min": 49876.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.369206428527832,
"min": 0.002742709591984749,
"max": 2.443345785140991,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1241.464111328125,
"min": 0.36203765869140625,
"max": 1349.1209716796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6808954490960097,
"min": 1.8545474620027975,
"max": 3.9188704280786113,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1928.7892153263092,
"min": 244.80026498436928,
"max": 2161.843347966671,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6808954490960097,
"min": 1.8545474620027975,
"max": 3.9188704280786113,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1928.7892153263092,
"min": 244.80026498436928,
"max": 2161.843347966671,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01757405740289768,
"min": 0.01201335361153421,
"max": 0.019998583802953364,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05272217220869304,
"min": 0.02402670722306842,
"max": 0.057180309369384,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04983062292966578,
"min": 0.023029396848546133,
"max": 0.06176014362523953,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14949186878899734,
"min": 0.04678443217029174,
"max": 0.1806519900759061,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.287898904066663e-06,
"min": 3.287898904066663e-06,
"max": 0.0002953263015579,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.863696712199989e-06,
"min": 9.863696712199989e-06,
"max": 0.0008440809186396998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109593333333335,
"min": 0.10109593333333335,
"max": 0.19844209999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30328780000000005,
"min": 0.20737700000000003,
"max": 0.5813603,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.468707333333327e-05,
"min": 6.468707333333327e-05,
"max": 0.004922260789999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019406121999999984,
"min": 0.00019406121999999984,
"max": 0.014069878970000001,
"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": "1707312003",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707314315"
},
"total": 2312.3185933,
"count": 1,
"self": 0.4925934389998474,
"children": {
"run_training.setup": {
"total": 0.0578977609999356,
"count": 1,
"self": 0.0578977609999356
},
"TrainerController.start_learning": {
"total": 2311.7681021000003,
"count": 1,
"self": 4.295675612963805,
"children": {
"TrainerController._reset_env": {
"total": 3.614880898000024,
"count": 1,
"self": 3.614880898000024
},
"TrainerController.advance": {
"total": 2303.7418641230365,
"count": 231702,
"self": 4.485976983908131,
"children": {
"env_step": {
"total": 1827.934872067011,
"count": 231702,
"self": 1509.1478208661051,
"children": {
"SubprocessEnvManager._take_step": {
"total": 316.15070428098136,
"count": 231702,
"self": 16.450577986896064,
"children": {
"TorchPolicy.evaluate": {
"total": 299.7001262940853,
"count": 222978,
"self": 299.7001262940853
}
}
},
"workers": {
"total": 2.636346919924563,
"count": 231702,
"self": 0.0,
"children": {
"worker_root": {
"total": 2304.775094872063,
"count": 231702,
"is_parallel": true,
"self": 1072.6248737871629,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009210770000436241,
"count": 1,
"is_parallel": true,
"self": 0.0002527809999719466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006682960000716776,
"count": 2,
"is_parallel": true,
"self": 0.0006682960000716776
}
}
},
"UnityEnvironment.step": {
"total": 0.028924015000029613,
"count": 1,
"is_parallel": true,
"self": 0.00036927799999375566,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022056099999190337,
"count": 1,
"is_parallel": true,
"self": 0.00022056099999190337
},
"communicator.exchange": {
"total": 0.02761329099996601,
"count": 1,
"is_parallel": true,
"self": 0.02761329099996601
},
"steps_from_proto": {
"total": 0.0007208850000779421,
"count": 1,
"is_parallel": true,
"self": 0.00019290700004148675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005279780000364553,
"count": 2,
"is_parallel": true,
"self": 0.0005279780000364553
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1232.1502210849003,
"count": 231701,
"is_parallel": true,
"self": 40.35338049786537,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.96148612110164,
"count": 231701,
"is_parallel": true,
"self": 81.96148612110164
},
"communicator.exchange": {
"total": 1021.810752878987,
"count": 231701,
"is_parallel": true,
"self": 1021.810752878987
},
"steps_from_proto": {
"total": 88.02460158694635,
"count": 231701,
"is_parallel": true,
"self": 30.68898908595179,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.33561250099456,
"count": 463402,
"is_parallel": true,
"self": 57.33561250099456
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 471.3210150721177,
"count": 231702,
"self": 6.367409612040888,
"children": {
"process_trajectory": {
"total": 143.3227046850766,
"count": 231702,
"self": 141.84546122907682,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4772434559997691,
"count": 10,
"self": 1.4772434559997691
}
}
},
"_update_policy": {
"total": 321.6309007750002,
"count": 97,
"self": 257.9568688310013,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.6740319439989,
"count": 2910,
"self": 63.6740319439989
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3849999049853068e-06,
"count": 1,
"self": 1.3849999049853068e-06
},
"TrainerController._save_models": {
"total": 0.11568008099993676,
"count": 1,
"self": 0.0019286729998384544,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11375140800009831,
"count": 1,
"self": 0.11375140800009831
}
}
}
}
}
}
}