zgerem's picture
First Push
c2af006 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.834319531917572,
"min": 0.827366292476654,
"max": 2.862302541732788,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7929.373046875,
"min": 7929.373046875,
"max": 29218.384765625,
"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": 12.490042686462402,
"min": 0.4562120735645294,
"max": 12.490042686462402,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2435.558349609375,
"min": 88.50514221191406,
"max": 2513.63037109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06634031651757302,
"min": 0.06399500073919841,
"max": 0.0772366643593391,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2653612660702921,
"min": 0.26182071333374446,
"max": 0.360489684134247,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18415266859765148,
"min": 0.13789977409018606,
"max": 0.2757096111628355,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7366106743906059,
"min": 0.5515990963607442,
"max": 1.3375760343144922,
"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": 3.8636363636363638,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 170.0,
"max": 1327.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.8636363636363638,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 170.0,
"max": 1327.0,
"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": "1743351412",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "1743351837"
},
"total": 425.0196482929998,
"count": 1,
"self": 0.43796483299979627,
"children": {
"run_training.setup": {
"total": 0.024828418999959467,
"count": 1,
"self": 0.024828418999959467
},
"TrainerController.start_learning": {
"total": 424.55685504100006,
"count": 1,
"self": 0.3465929180006242,
"children": {
"TrainerController._reset_env": {
"total": 3.5139537380000547,
"count": 1,
"self": 3.5139537380000547
},
"TrainerController.advance": {
"total": 420.6098233469995,
"count": 18192,
"self": 0.37977747498712233,
"children": {
"env_step": {
"total": 297.32549101800964,
"count": 18192,
"self": 226.68289382598186,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.43478564001134,
"count": 18192,
"self": 1.2265751740337691,
"children": {
"TorchPolicy.evaluate": {
"total": 69.20821046597757,
"count": 18192,
"self": 69.20821046597757
}
}
},
"workers": {
"total": 0.20781155201643742,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.01959092200536,
"count": 18192,
"is_parallel": true,
"self": 223.85385310500146,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005881438999949751,
"count": 1,
"is_parallel": true,
"self": 0.004472739999300757,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014086990006489941,
"count": 10,
"is_parallel": true,
"self": 0.0014086990006489941
}
}
},
"UnityEnvironment.step": {
"total": 0.07006238700000722,
"count": 1,
"is_parallel": true,
"self": 0.0005139890001828462,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034540999990895216,
"count": 1,
"is_parallel": true,
"self": 0.00034540999990895216
},
"communicator.exchange": {
"total": 0.06755479999992531,
"count": 1,
"is_parallel": true,
"self": 0.06755479999992531
},
"steps_from_proto": {
"total": 0.001648187999990114,
"count": 1,
"is_parallel": true,
"self": 0.00030941699969844194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001338771000291672,
"count": 10,
"is_parallel": true,
"self": 0.001338771000291672
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 199.1657378170039,
"count": 18191,
"is_parallel": true,
"self": 9.512705433033489,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2349378059986975,
"count": 18191,
"is_parallel": true,
"self": 5.2349378059986975
},
"communicator.exchange": {
"total": 153.95851718997824,
"count": 18191,
"is_parallel": true,
"self": 153.95851718997824
},
"steps_from_proto": {
"total": 30.459577387993477,
"count": 18191,
"is_parallel": true,
"self": 5.424146338984883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.035431049008594,
"count": 181910,
"is_parallel": true,
"self": 25.035431049008594
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.90455485400275,
"count": 18192,
"self": 0.4342566650088884,
"children": {
"process_trajectory": {
"total": 26.505093270992347,
"count": 18192,
"self": 25.97215038199215,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5329428890001964,
"count": 4,
"self": 0.5329428890001964
}
}
},
"_update_policy": {
"total": 95.96520491800152,
"count": 90,
"self": 38.490396928000564,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.474807990000954,
"count": 4587,
"self": 57.474807990000954
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.690000529692043e-07,
"count": 1,
"self": 7.690000529692043e-07
},
"TrainerController._save_models": {
"total": 0.08648426899981132,
"count": 1,
"self": 0.0008594889998221333,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08562477999998919,
"count": 1,
"self": 0.08562477999998919
}
}
}
}
}
}
}