LeoCAv's picture
First Push
1206258 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9519467353820801,
"min": 0.9519467353820801,
"max": 2.8492519855499268,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9047.3017578125,
"min": 9047.3017578125,
"max": 29085.1640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.717350006103516,
"min": 0.2629289925098419,
"max": 12.717350006103516,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2479.88330078125,
"min": 51.00822448730469,
"max": 2578.2783203125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06859008261224017,
"min": 0.05869124609835483,
"max": 0.07550260604395732,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2743603304489607,
"min": 0.2347649843934193,
"max": 0.3775130302197866,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2062197274291048,
"min": 0.11861479490100607,
"max": 0.26456517514352706,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8248789097164192,
"min": 0.4744591796040243,
"max": 1.2886959258832182,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.954545454545453,
"min": 3.0681818181818183,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 135.0,
"max": 1373.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.0681818181818183,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 135.0,
"max": 1373.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1741346940",
"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": "1741347406"
},
"total": 466.78128591999996,
"count": 1,
"self": 0.4897854799999095,
"children": {
"run_training.setup": {
"total": 0.02415080499997657,
"count": 1,
"self": 0.02415080499997657
},
"TrainerController.start_learning": {
"total": 466.2673496350001,
"count": 1,
"self": 0.3804212599914081,
"children": {
"TrainerController._reset_env": {
"total": 3.5553935450000154,
"count": 1,
"self": 3.5553935450000154
},
"TrainerController.advance": {
"total": 462.2318734310087,
"count": 18192,
"self": 0.41367921800315344,
"children": {
"env_step": {
"total": 330.79329568800756,
"count": 18192,
"self": 251.6019817420189,
"children": {
"SubprocessEnvManager._take_step": {
"total": 78.9669730249957,
"count": 18192,
"self": 1.3933146479945435,
"children": {
"TorchPolicy.evaluate": {
"total": 77.57365837700115,
"count": 18192,
"self": 77.57365837700115
}
}
},
"workers": {
"total": 0.22434092099297231,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 464.7628329659917,
"count": 18192,
"is_parallel": true,
"self": 243.65681929799405,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00576941799999986,
"count": 1,
"is_parallel": true,
"self": 0.004079916999785382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016895010002144772,
"count": 10,
"is_parallel": true,
"self": 0.0016895010002144772
}
}
},
"UnityEnvironment.step": {
"total": 0.03949708500010729,
"count": 1,
"is_parallel": true,
"self": 0.0006156300001975978,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042145800000525924,
"count": 1,
"is_parallel": true,
"self": 0.00042145800000525924
},
"communicator.exchange": {
"total": 0.036450038999987555,
"count": 1,
"is_parallel": true,
"self": 0.036450038999987555
},
"steps_from_proto": {
"total": 0.002009957999916878,
"count": 1,
"is_parallel": true,
"self": 0.0003564759997516376,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016534820001652406,
"count": 10,
"is_parallel": true,
"self": 0.0016534820001652406
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.10601366799767,
"count": 18191,
"is_parallel": true,
"self": 10.421157027998106,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.962045259004071,
"count": 18191,
"is_parallel": true,
"self": 5.962045259004071
},
"communicator.exchange": {
"total": 169.30982938600198,
"count": 18191,
"is_parallel": true,
"self": 169.30982938600198
},
"steps_from_proto": {
"total": 35.412981994993515,
"count": 18191,
"is_parallel": true,
"self": 6.395998180987135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.01698381400638,
"count": 181910,
"is_parallel": true,
"self": 29.01698381400638
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 131.02489852499798,
"count": 18192,
"self": 0.4600840620026929,
"children": {
"process_trajectory": {
"total": 29.74389003499482,
"count": 18192,
"self": 29.148186854994947,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5957031799998731,
"count": 4,
"self": 0.5957031799998731
}
}
},
"_update_policy": {
"total": 100.82092442800047,
"count": 90,
"self": 40.97858769600532,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.84233673199515,
"count": 4587,
"self": 59.84233673199515
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.19799994990899e-06,
"count": 1,
"self": 1.19799994990899e-06
},
"TrainerController._save_models": {
"total": 0.09966020100000605,
"count": 1,
"self": 0.0011100169999735954,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09855018400003246,
"count": 1,
"self": 0.09855018400003246
}
}
}
}
}
}
}