dkimds's picture
First Push
18a74c0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9755628705024719,
"min": 0.9755628705024719,
"max": 2.8627395629882812,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9336.13671875,
"min": 9336.13671875,
"max": 29348.806640625,
"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": 12.25727367401123,
"min": 0.5366461873054504,
"max": 12.25727367401123,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2390.16845703125,
"min": 104.10935974121094,
"max": 2454.58056640625,
"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": 0.0720453594046429,
"min": 0.0638092922367208,
"max": 0.07388512473188194,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2881814376185716,
"min": 0.2552371689468832,
"max": 0.36942562365940973,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19167077406218236,
"min": 0.15378693445795671,
"max": 0.2797870465937783,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7666830962487294,
"min": 0.6151477378318269,
"max": 1.3989352329688913,
"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": 24.295454545454547,
"min": 3.8863636363636362,
"max": 24.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1069.0,
"min": 171.0,
"max": 1334.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.295454545454547,
"min": 3.8863636363636362,
"max": 24.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1069.0,
"min": 171.0,
"max": 1334.0,
"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": "1692520988",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692521478"
},
"total": 490.20618791999993,
"count": 1,
"self": 0.6797167169999057,
"children": {
"run_training.setup": {
"total": 0.04358992900006342,
"count": 1,
"self": 0.04358992900006342
},
"TrainerController.start_learning": {
"total": 489.48288127399996,
"count": 1,
"self": 0.624034167012951,
"children": {
"TrainerController._reset_env": {
"total": 4.197929431000034,
"count": 1,
"self": 4.197929431000034
},
"TrainerController.advance": {
"total": 484.4211304819868,
"count": 18213,
"self": 0.326615713991373,
"children": {
"env_step": {
"total": 484.0945147679954,
"count": 18213,
"self": 351.5979682190201,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.17909362198702,
"count": 18213,
"self": 1.8729852599825563,
"children": {
"TorchPolicy.evaluate": {
"total": 130.30610836200447,
"count": 18213,
"self": 130.30610836200447
}
}
},
"workers": {
"total": 0.3174529269882669,
"count": 18213,
"self": 0.0,
"children": {
"worker_root": {
"total": 487.7234418209973,
"count": 18213,
"is_parallel": true,
"self": 228.75743418599438,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007072642999901291,
"count": 1,
"is_parallel": true,
"self": 0.0053827880000199,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016898549998813905,
"count": 10,
"is_parallel": true,
"self": 0.0016898549998813905
}
}
},
"UnityEnvironment.step": {
"total": 0.034395442999993975,
"count": 1,
"is_parallel": true,
"self": 0.0006305510000856884,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004136359999620254,
"count": 1,
"is_parallel": true,
"self": 0.0004136359999620254
},
"communicator.exchange": {
"total": 0.031107747999953972,
"count": 1,
"is_parallel": true,
"self": 0.031107747999953972
},
"steps_from_proto": {
"total": 0.002243507999992289,
"count": 1,
"is_parallel": true,
"self": 0.0004233590001376797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018201489998546094,
"count": 10,
"is_parallel": true,
"self": 0.0018201489998546094
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 258.96600763500294,
"count": 18212,
"is_parallel": true,
"self": 10.692159922002133,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.420226794009636,
"count": 18212,
"is_parallel": true,
"self": 5.420226794009636
},
"communicator.exchange": {
"total": 205.67402278100155,
"count": 18212,
"is_parallel": true,
"self": 205.67402278100155
},
"steps_from_proto": {
"total": 37.179598137989615,
"count": 18212,
"is_parallel": true,
"self": 6.879877049998299,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.299721087991315,
"count": 182120,
"is_parallel": true,
"self": 30.299721087991315
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018435500010127726,
"count": 1,
"self": 0.00018435500010127726,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 480.86896103000356,
"count": 452733,
"is_parallel": true,
"self": 10.063020291950238,
"children": {
"process_trajectory": {
"total": 263.8687533540532,
"count": 452733,
"is_parallel": true,
"self": 262.7464182200532,
"children": {
"RLTrainer._checkpoint": {
"total": 1.122335133999968,
"count": 4,
"is_parallel": true,
"self": 1.122335133999968
}
}
},
"_update_policy": {
"total": 206.93718738400014,
"count": 90,
"is_parallel": true,
"self": 79.57537138400357,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.36181599999657,
"count": 4587,
"is_parallel": true,
"self": 127.36181599999657
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23960283900009927,
"count": 1,
"self": 0.0013574399999924935,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23824539900010677,
"count": 1,
"self": 0.23824539900010677
}
}
}
}
}
}
}