hubertau's picture
First Push
19f4599 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8593719005584717,
"min": 0.8593719005584717,
"max": 2.843832015991211,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8167.470703125,
"min": 8167.470703125,
"max": 29029.837890625,
"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": 13.158065795898438,
"min": 0.37169769406318665,
"max": 13.158065795898438,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2565.82275390625,
"min": 72.1093521118164,
"max": 2667.55810546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06836021183225433,
"min": 0.0629902882452406,
"max": 0.07650395662765767,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2734408473290173,
"min": 0.26253712589595146,
"max": 0.3552587487422131,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20238318995517843,
"min": 0.11760896156592221,
"max": 0.29233355872771327,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8095327598207137,
"min": 0.47043584626368884,
"max": 1.4616677936385662,
"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": 26.15909090909091,
"min": 3.227272727272727,
"max": 26.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1151.0,
"min": 142.0,
"max": 1433.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.15909090909091,
"min": 3.227272727272727,
"max": 26.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1151.0,
"min": 142.0,
"max": 1433.0,
"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": "1745399308",
"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": "1745399919"
},
"total": 611.7179122559999,
"count": 1,
"self": 0.5937165559998903,
"children": {
"run_training.setup": {
"total": 0.04443291400002636,
"count": 1,
"self": 0.04443291400002636
},
"TrainerController.start_learning": {
"total": 611.079762786,
"count": 1,
"self": 0.6817814869991707,
"children": {
"TrainerController._reset_env": {
"total": 4.536509641000066,
"count": 1,
"self": 4.536509641000066
},
"TrainerController.advance": {
"total": 605.7663320420008,
"count": 18192,
"self": 0.7015931209757582,
"children": {
"env_step": {
"total": 424.94867915501004,
"count": 18192,
"self": 361.5635349680135,
"children": {
"SubprocessEnvManager._take_step": {
"total": 62.982006239997645,
"count": 18192,
"self": 2.6046171779987617,
"children": {
"TorchPolicy.evaluate": {
"total": 60.37738906199888,
"count": 18192,
"self": 60.37738906199888
}
}
},
"workers": {
"total": 0.40313794699886785,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 608.8109754719897,
"count": 18192,
"is_parallel": true,
"self": 297.28052073197705,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008863930999950753,
"count": 1,
"is_parallel": true,
"self": 0.006178700999726061,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002685230000224692,
"count": 10,
"is_parallel": true,
"self": 0.002685230000224692
}
}
},
"UnityEnvironment.step": {
"total": 0.05411578500002179,
"count": 1,
"is_parallel": true,
"self": 0.0007189990001279511,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006207129999893368,
"count": 1,
"is_parallel": true,
"self": 0.0006207129999893368
},
"communicator.exchange": {
"total": 0.05041124099989247,
"count": 1,
"is_parallel": true,
"self": 0.05041124099989247
},
"steps_from_proto": {
"total": 0.0023648320000120293,
"count": 1,
"is_parallel": true,
"self": 0.0004453009996723267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019195310003397026,
"count": 10,
"is_parallel": true,
"self": 0.0019195310003397026
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 311.5304547400126,
"count": 18191,
"is_parallel": true,
"self": 14.695637474030036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.01630448900687,
"count": 18191,
"is_parallel": true,
"self": 8.01630448900687
},
"communicator.exchange": {
"total": 243.95375010400153,
"count": 18191,
"is_parallel": true,
"self": 243.95375010400153
},
"steps_from_proto": {
"total": 44.864762672974166,
"count": 18191,
"is_parallel": true,
"self": 8.791863298976295,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.07289937399787,
"count": 181910,
"is_parallel": true,
"self": 36.07289937399787
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 180.11605976601504,
"count": 18192,
"self": 0.9052814890094396,
"children": {
"process_trajectory": {
"total": 35.3154289170061,
"count": 18192,
"self": 34.8043594460064,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5110694709997006,
"count": 4,
"self": 0.5110694709997006
}
}
},
"_update_policy": {
"total": 143.8953493599995,
"count": 90,
"self": 51.231444000007514,
"children": {
"TorchPPOOptimizer.update": {
"total": 92.66390535999199,
"count": 4587,
"self": 92.66390535999199
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2999998943996616e-06,
"count": 1,
"self": 1.2999998943996616e-06
},
"TrainerController._save_models": {
"total": 0.09513831599997502,
"count": 1,
"self": 0.00119164300031116,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09394667299966386,
"count": 1,
"self": 0.09394667299966386
}
}
}
}
}
}
}