Vaxm's picture
First Push
ef286c9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8892443180084229,
"min": 0.857853889465332,
"max": 2.860563039779663,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8451.3779296875,
"min": 8451.3779296875,
"max": 29200.626953125,
"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": 13.047493934631348,
"min": 0.15272492170333862,
"max": 13.160690307617188,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2544.26123046875,
"min": 29.62863540649414,
"max": 2684.78076171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07186302778077958,
"min": 0.06241790245636081,
"max": 0.07720612232900322,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2874521111231183,
"min": 0.24967160982544323,
"max": 0.36100907232863466,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2469525905508621,
"min": 0.1245385202197997,
"max": 0.2975203865883397,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9878103622034484,
"min": 0.4981540808791988,
"max": 1.4876019329416985,
"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": 24.931818181818183,
"min": 3.5681818181818183,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 157.0,
"max": 1425.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.5681818181818183,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 157.0,
"max": 1425.0,
"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": "1758953724",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758954195"
},
"total": 470.67559319500015,
"count": 1,
"self": 0.4341872760002161,
"children": {
"run_training.setup": {
"total": 0.03883532400004697,
"count": 1,
"self": 0.03883532400004697
},
"TrainerController.start_learning": {
"total": 470.2025705949999,
"count": 1,
"self": 0.37280620200374415,
"children": {
"TrainerController._reset_env": {
"total": 3.049644884000031,
"count": 1,
"self": 3.049644884000031
},
"TrainerController.advance": {
"total": 466.69727711699613,
"count": 18192,
"self": 0.4108142849754586,
"children": {
"env_step": {
"total": 340.7936213010056,
"count": 18192,
"self": 266.94015719301217,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.62849435799887,
"count": 18192,
"self": 1.3236954010020554,
"children": {
"TorchPolicy.evaluate": {
"total": 72.30479895699682,
"count": 18192,
"self": 72.30479895699682
}
}
},
"workers": {
"total": 0.22496974999455688,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.26490323600467,
"count": 18192,
"is_parallel": true,
"self": 233.80002391100334,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005985380999959489,
"count": 1,
"is_parallel": true,
"self": 0.0044514089997846895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015339720001747992,
"count": 10,
"is_parallel": true,
"self": 0.0015339720001747992
}
}
},
"UnityEnvironment.step": {
"total": 0.0388580799999545,
"count": 1,
"is_parallel": true,
"self": 0.0007460870000386421,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044428900002912997,
"count": 1,
"is_parallel": true,
"self": 0.00044428900002912997
},
"communicator.exchange": {
"total": 0.03564672399988922,
"count": 1,
"is_parallel": true,
"self": 0.03564672399988922
},
"steps_from_proto": {
"total": 0.0020209799999975075,
"count": 1,
"is_parallel": true,
"self": 0.00040886100009629445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001612118999901213,
"count": 10,
"is_parallel": true,
"self": 0.001612118999901213
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.46487932500133,
"count": 18191,
"is_parallel": true,
"self": 10.996908561972418,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.925034846004337,
"count": 18191,
"is_parallel": true,
"self": 5.925034846004337
},
"communicator.exchange": {
"total": 177.82299520901552,
"count": 18191,
"is_parallel": true,
"self": 177.82299520901552
},
"steps_from_proto": {
"total": 39.71994070800906,
"count": 18191,
"is_parallel": true,
"self": 7.020580300003644,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.69936040800542,
"count": 181910,
"is_parallel": true,
"self": 32.69936040800542
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.49284153101507,
"count": 18192,
"self": 0.4696001880007543,
"children": {
"process_trajectory": {
"total": 28.050332228014554,
"count": 18192,
"self": 27.64500534301453,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40532688500002223,
"count": 4,
"self": 0.40532688500002223
}
}
},
"_update_policy": {
"total": 96.97290911499977,
"count": 90,
"self": 40.793777154999816,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.17913195999995,
"count": 4587,
"self": 56.17913195999995
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.859999525157036e-07,
"count": 1,
"self": 8.859999525157036e-07
},
"TrainerController._save_models": {
"total": 0.08284150600002249,
"count": 1,
"self": 0.0007487459999993007,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08209276000002319,
"count": 1,
"self": 0.08209276000002319
}
}
}
}
}
}
}