GhassenHa's picture
First Push
e2fcc71 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5156221389770508,
"min": 0.47896429896354675,
"max": 2.8679707050323486,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5263.470703125,
"min": 4808.521484375,
"max": 29276.24609375,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.639369010925293,
"min": 0.3163318634033203,
"max": 13.710227966308594,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2659.677001953125,
"min": 61.36838150024414,
"max": 2810.5966796875,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06482361581113176,
"min": 0.06099919373631493,
"max": 0.07473392652018981,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25929446324452704,
"min": 0.24399677494525973,
"max": 0.3736696326009491,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17161620108812461,
"min": 0.12953201004226383,
"max": 0.29280051735101964,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6864648043524985,
"min": 0.5181280401690553,
"max": 1.3941052149908215,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.891098702999994e-06,
"min": 3.891098702999994e-06,
"max": 0.000295941001353,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5564394811999976e-05,
"min": 1.5564394811999976e-05,
"max": 0.0014425800191399996,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101297,
"min": 0.101297,
"max": 0.19864700000000002,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.405188,
"min": 0.405188,
"max": 0.98086,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.472029999999992e-05,
"min": 7.472029999999992e-05,
"max": 0.004932485299999999,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00029888119999999966,
"min": 0.00029888119999999966,
"max": 0.024044914,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.454545454545453,
"min": 3.75,
"max": 27.136363636363637,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1164.0,
"min": 165.0,
"max": 1492.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.454545454545453,
"min": 3.75,
"max": 27.136363636363637,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1164.0,
"min": 165.0,
"max": 1492.0,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1744794340",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744795176"
},
"total": 836.0544808980001,
"count": 1,
"self": 0.44008872300025814,
"children": {
"run_training.setup": {
"total": 0.02295548199992936,
"count": 1,
"self": 0.02295548199992936
},
"TrainerController.start_learning": {
"total": 835.5914366929999,
"count": 1,
"self": 0.6665835320064843,
"children": {
"TrainerController._reset_env": {
"total": 3.11613316699993,
"count": 1,
"self": 3.11613316699993
},
"TrainerController.advance": {
"total": 831.7169737199936,
"count": 36392,
"self": 0.696514875987873,
"children": {
"env_step": {
"total": 584.3444248970071,
"count": 36392,
"self": 442.04590801599375,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.89216703400905,
"count": 36392,
"self": 2.4493076740465085,
"children": {
"TorchPolicy.evaluate": {
"total": 139.44285935996254,
"count": 36392,
"self": 139.44285935996254
}
}
},
"workers": {
"total": 0.4063498470043214,
"count": 36392,
"self": 0.0,
"children": {
"worker_root": {
"total": 833.0107165420112,
"count": 36392,
"is_parallel": true,
"self": 445.65146593603015,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005447910000043521,
"count": 1,
"is_parallel": true,
"self": 0.003905759999952352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015421500000911692,
"count": 10,
"is_parallel": true,
"self": 0.0015421500000911692
}
}
},
"UnityEnvironment.step": {
"total": 0.035022331000050144,
"count": 1,
"is_parallel": true,
"self": 0.0005739790000234279,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003782389999287261,
"count": 1,
"is_parallel": true,
"self": 0.0003782389999287261
},
"communicator.exchange": {
"total": 0.032268411000018205,
"count": 1,
"is_parallel": true,
"self": 0.032268411000018205
},
"steps_from_proto": {
"total": 0.0018017020000797856,
"count": 1,
"is_parallel": true,
"self": 0.00036193700020703545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014397649998727502,
"count": 10,
"is_parallel": true,
"self": 0.0014397649998727502
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 387.35925060598106,
"count": 36391,
"is_parallel": true,
"self": 19.096991961965045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.362194093018047,
"count": 36391,
"is_parallel": true,
"self": 10.362194093018047
},
"communicator.exchange": {
"total": 297.31491522400154,
"count": 36391,
"is_parallel": true,
"self": 297.31491522400154
},
"steps_from_proto": {
"total": 60.58514932699643,
"count": 36391,
"is_parallel": true,
"self": 10.75842674303999,
"children": {
"_process_rank_one_or_two_observation": {
"total": 49.82672258395644,
"count": 363910,
"is_parallel": true,
"self": 49.82672258395644
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 246.6760339469986,
"count": 36392,
"self": 0.8518511910058351,
"children": {
"process_trajectory": {
"total": 52.985012958993366,
"count": 36392,
"self": 52.139047147993324,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8459658110000419,
"count": 8,
"self": 0.8459658110000419
}
}
},
"_update_policy": {
"total": 192.83916979699939,
"count": 181,
"self": 75.93411118900042,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.90505860799897,
"count": 9228,
"self": 116.90505860799897
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.809998573473422e-07,
"count": 1,
"self": 9.809998573473422e-07
},
"TrainerController._save_models": {
"total": 0.09174529300003087,
"count": 1,
"self": 0.001008774000183621,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09073651899984725,
"count": 1,
"self": 0.09073651899984725
}
}
}
}
}
}
}