HusseinEid's picture
First Push
0b130f9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9339697957038879,
"min": 0.9284952878952026,
"max": 2.855424165725708,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8938.0908203125,
"min": 8938.0908203125,
"max": 29273.80859375,
"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": 12.75361156463623,
"min": 0.23668180406093597,
"max": 12.75361156463623,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2486.954345703125,
"min": 45.9162712097168,
"max": 2570.59033203125,
"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.Losses.PolicyLoss.mean": {
"value": 0.07367732200342003,
"min": 0.058034515915114396,
"max": 0.0763127029747885,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2947092880136801,
"min": 0.23213806366045758,
"max": 0.38156351487394247,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2072290951276527,
"min": 0.09608248619627499,
"max": 0.3053911191721757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8289163805106108,
"min": 0.38432994478509996,
"max": 1.3963588639801623,
"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": 25.136363636363637,
"min": 2.977272727272727,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 131.0,
"max": 1380.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 2.977272727272727,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 131.0,
"max": 1380.0,
"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": "1714250568",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714251180"
},
"total": 612.218346405,
"count": 1,
"self": 0.5932115690000046,
"children": {
"run_training.setup": {
"total": 0.07353953699998783,
"count": 1,
"self": 0.07353953699998783
},
"TrainerController.start_learning": {
"total": 611.551595299,
"count": 1,
"self": 0.9519515139985515,
"children": {
"TrainerController._reset_env": {
"total": 3.076379096999972,
"count": 1,
"self": 3.076379096999972
},
"TrainerController.advance": {
"total": 607.4142596570016,
"count": 18201,
"self": 0.45043841400297424,
"children": {
"env_step": {
"total": 606.9638212429986,
"count": 18201,
"self": 469.56731607799077,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.9278784710093,
"count": 18201,
"self": 2.473025231011718,
"children": {
"TorchPolicy.evaluate": {
"total": 134.4548532399976,
"count": 18201,
"self": 134.4548532399976
}
}
},
"workers": {
"total": 0.4686266939985444,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 609.3667166650073,
"count": 18201,
"is_parallel": true,
"self": 273.4654536430082,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008390619000010702,
"count": 1,
"is_parallel": true,
"self": 0.0064367270000502685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001953891999960433,
"count": 10,
"is_parallel": true,
"self": 0.001953891999960433
}
}
},
"UnityEnvironment.step": {
"total": 0.04495670199997903,
"count": 1,
"is_parallel": true,
"self": 0.0007893159999525778,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048019799999110546,
"count": 1,
"is_parallel": true,
"self": 0.00048019799999110546
},
"communicator.exchange": {
"total": 0.04143665300000521,
"count": 1,
"is_parallel": true,
"self": 0.04143665300000521
},
"steps_from_proto": {
"total": 0.0022505350000301405,
"count": 1,
"is_parallel": true,
"self": 0.00042458500013253797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018259499998976025,
"count": 10,
"is_parallel": true,
"self": 0.0018259499998976025
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 335.9012630219991,
"count": 18200,
"is_parallel": true,
"self": 16.359189497024033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.120299230989815,
"count": 18200,
"is_parallel": true,
"self": 8.120299230989815
},
"communicator.exchange": {
"total": 264.81197199599774,
"count": 18200,
"is_parallel": true,
"self": 264.81197199599774
},
"steps_from_proto": {
"total": 46.60980229798753,
"count": 18200,
"is_parallel": true,
"self": 9.469000784012678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.14080151397485,
"count": 182000,
"is_parallel": true,
"self": 37.14080151397485
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00022396999997909006,
"count": 1,
"self": 0.00022396999997909006,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 600.1937150220016,
"count": 862959,
"is_parallel": true,
"self": 19.205845210980556,
"children": {
"process_trajectory": {
"total": 338.30321192802097,
"count": 862959,
"is_parallel": true,
"self": 337.2124939470211,
"children": {
"RLTrainer._checkpoint": {
"total": 1.090717980999898,
"count": 4,
"is_parallel": true,
"self": 1.090717980999898
}
}
},
"_update_policy": {
"total": 242.684657883,
"count": 90,
"is_parallel": true,
"self": 62.021550059001754,
"children": {
"TorchPPOOptimizer.update": {
"total": 180.66310782399825,
"count": 4587,
"is_parallel": true,
"self": 180.66310782399825
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10878106099994511,
"count": 1,
"self": 0.0015950929998780339,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10718596800006708,
"count": 1,
"self": 0.10718596800006708
}
}
}
}
}
}
}