AndiB93's picture
First Push
dc31fc7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8941086530685425,
"min": 0.8848428726196289,
"max": 2.858731508255005,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8576.2900390625,
"min": 8576.2900390625,
"max": 29402.0546875,
"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": 12.732136726379395,
"min": 0.2953682243824005,
"max": 12.732136726379395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2482.7666015625,
"min": 57.30143356323242,
"max": 2567.55859375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06471250139104229,
"min": 0.06403041771494934,
"max": 0.07236592538743827,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25885000556416915,
"min": 0.25702820802860726,
"max": 0.3618296269371914,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19647127806263812,
"min": 0.1104405737669189,
"max": 0.3087609759148429,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7858851122505525,
"min": 0.4417622950676756,
"max": 1.5438048795742145,
"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.CumulativeReward.mean": {
"value": 25.34090909090909,
"min": 3.4318181818181817,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 151.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.4318181818181817,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 151.0,
"max": 1382.0,
"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": "1730312573",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"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": "2.5.0+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1730312985"
},
"total": 411.8562778639998,
"count": 1,
"self": 0.32134741599975314,
"children": {
"run_training.setup": {
"total": 0.06869861099994523,
"count": 1,
"self": 0.06869861099994523
},
"TrainerController.start_learning": {
"total": 411.4662318370001,
"count": 1,
"self": 0.4998630320146731,
"children": {
"TrainerController._reset_env": {
"total": 9.502919421000115,
"count": 1,
"self": 9.502919421000115
},
"TrainerController.advance": {
"total": 401.3996658349854,
"count": 18208,
"self": 0.25848468098593,
"children": {
"env_step": {
"total": 401.14118115399947,
"count": 18208,
"self": 317.380149599024,
"children": {
"SubprocessEnvManager._take_step": {
"total": 83.53311918797863,
"count": 18208,
"self": 1.2710997279832554,
"children": {
"TorchPolicy.evaluate": {
"total": 82.26201945999537,
"count": 18208,
"self": 82.26201945999537
}
}
},
"workers": {
"total": 0.22791236699686124,
"count": 18208,
"self": 0.0,
"children": {
"worker_root": {
"total": 410.79237152702444,
"count": 18208,
"is_parallel": true,
"self": 182.8054347570437,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002441199000031702,
"count": 1,
"is_parallel": true,
"self": 0.0007618739998633828,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001679325000168319,
"count": 10,
"is_parallel": true,
"self": 0.001679325000168319
}
}
},
"UnityEnvironment.step": {
"total": 0.03167101400003958,
"count": 1,
"is_parallel": true,
"self": 0.000556353999854764,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003017850001469924,
"count": 1,
"is_parallel": true,
"self": 0.0003017850001469924
},
"communicator.exchange": {
"total": 0.02936665700008234,
"count": 1,
"is_parallel": true,
"self": 0.02936665700008234
},
"steps_from_proto": {
"total": 0.0014462179999554792,
"count": 1,
"is_parallel": true,
"self": 0.0003358159999606869,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011104019999947923,
"count": 10,
"is_parallel": true,
"self": 0.0011104019999947923
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.98693676998073,
"count": 18207,
"is_parallel": true,
"self": 6.57522188897633,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.624764824001886,
"count": 18207,
"is_parallel": true,
"self": 3.624764824001886
},
"communicator.exchange": {
"total": 197.05758223899556,
"count": 18207,
"is_parallel": true,
"self": 197.05758223899556
},
"steps_from_proto": {
"total": 20.72936781800695,
"count": 18207,
"is_parallel": true,
"self": 4.140185370023346,
"children": {
"_process_rank_one_or_two_observation": {
"total": 16.589182447983603,
"count": 182070,
"is_parallel": true,
"self": 16.589182447983603
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00025832599999375816,
"count": 1,
"self": 0.00025832599999375816,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 400.88872368900843,
"count": 193245,
"is_parallel": true,
"self": 2.4134900639912757,
"children": {
"process_trajectory": {
"total": 231.17608197801724,
"count": 193245,
"is_parallel": true,
"self": 230.51841711701718,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6576648610000575,
"count": 4,
"is_parallel": true,
"self": 0.6576648610000575
}
}
},
"_update_policy": {
"total": 167.29915164699992,
"count": 90,
"is_parallel": true,
"self": 34.12927607699862,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.1698755700013,
"count": 4584,
"is_parallel": true,
"self": 133.1698755700013
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.06352522299994234,
"count": 1,
"self": 0.0009246909999092168,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06260053200003313,
"count": 1,
"self": 0.06260053200003313
}
}
}
}
}
}
}