joelewis2000's picture
First Push
f626b7e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8696076273918152,
"min": 0.8696076273918152,
"max": 2.8691611289978027,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8369.9736328125,
"min": 8369.9736328125,
"max": 29446.201171875,
"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": 12.498958587646484,
"min": 0.3655332624912262,
"max": 12.498958587646484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2437.296875,
"min": 70.9134521484375,
"max": 2526.56591796875,
"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": 0.07081154547203743,
"min": 0.06170549191101956,
"max": 0.07520024897880206,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2832461818881497,
"min": 0.24682196764407824,
"max": 0.37274288569004094,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1900632509633022,
"min": 0.09305206771173022,
"max": 0.29970910917310156,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7602530038532088,
"min": 0.3722082708469209,
"max": 1.4985455458655077,
"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": 25.022727272727273,
"min": 2.9545454545454546,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1101.0,
"min": 130.0,
"max": 1350.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.022727272727273,
"min": 2.9545454545454546,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1101.0,
"min": 130.0,
"max": 1350.0,
"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": "1683790899",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683791542"
},
"total": 643.2585404329999,
"count": 1,
"self": 1.051755843999672,
"children": {
"run_training.setup": {
"total": 0.08930105600006755,
"count": 1,
"self": 0.08930105600006755
},
"TrainerController.start_learning": {
"total": 642.1174835330002,
"count": 1,
"self": 0.9415429730013329,
"children": {
"TrainerController._reset_env": {
"total": 1.438828424999997,
"count": 1,
"self": 1.438828424999997
},
"TrainerController.advance": {
"total": 639.483828450999,
"count": 18224,
"self": 0.42497269600744403,
"children": {
"env_step": {
"total": 639.0588557549916,
"count": 18224,
"self": 519.3875293470069,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.25091539499476,
"count": 18224,
"self": 3.009497661990622,
"children": {
"TorchPolicy.evaluate": {
"total": 116.24141773300414,
"count": 18224,
"self": 116.24141773300414
}
}
},
"workers": {
"total": 0.42041101298991634,
"count": 18224,
"self": 0.0,
"children": {
"worker_root": {
"total": 639.6046923989874,
"count": 18224,
"is_parallel": true,
"self": 276.607566360993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00828963300000396,
"count": 1,
"is_parallel": true,
"self": 0.005269333999876835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0030202990001271246,
"count": 10,
"is_parallel": true,
"self": 0.0030202990001271246
}
}
},
"UnityEnvironment.step": {
"total": 0.13321312599998691,
"count": 1,
"is_parallel": true,
"self": 0.000732577000121637,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005065139999942403,
"count": 1,
"is_parallel": true,
"self": 0.0005065139999942403
},
"communicator.exchange": {
"total": 0.1291967569999315,
"count": 1,
"is_parallel": true,
"self": 0.1291967569999315
},
"steps_from_proto": {
"total": 0.0027772779999395425,
"count": 1,
"is_parallel": true,
"self": 0.0005332880001560625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00224398999978348,
"count": 10,
"is_parallel": true,
"self": 0.00224398999978348
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 362.99712603799435,
"count": 18223,
"is_parallel": true,
"self": 14.898545305026005,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.815147795962844,
"count": 18223,
"is_parallel": true,
"self": 7.815147795962844
},
"communicator.exchange": {
"total": 290.56327330800957,
"count": 18223,
"is_parallel": true,
"self": 290.56327330800957
},
"steps_from_proto": {
"total": 49.72015962899593,
"count": 18223,
"is_parallel": true,
"self": 9.813661782000167,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.90649784699576,
"count": 182230,
"is_parallel": true,
"self": 39.90649784699576
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002797239999381418,
"count": 1,
"self": 0.0002797239999381418,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 633.5774971520228,
"count": 656520,
"is_parallel": true,
"self": 16.086156301074766,
"children": {
"process_trajectory": {
"total": 343.99155299594884,
"count": 656520,
"is_parallel": true,
"self": 342.43926087694877,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5522921190000716,
"count": 4,
"is_parallel": true,
"self": 1.5522921190000716
}
}
},
"_update_policy": {
"total": 273.4997878549992,
"count": 90,
"is_parallel": true,
"self": 96.09743422900226,
"children": {
"TorchPPOOptimizer.update": {
"total": 177.40235362599697,
"count": 4587,
"is_parallel": true,
"self": 177.40235362599697
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.25300395999988723,
"count": 1,
"self": 0.0016449249999368476,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2513590349999504,
"count": 1,
"self": 0.2513590349999504
}
}
}
}
}
}
}