JabrilJacobs's picture
First Push
4e53c2b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9717597961425781,
"min": 0.9717597961425781,
"max": 2.8648266792297363,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9278.3623046875,
"min": 9278.3623046875,
"max": 29307.17578125,
"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": 12.37014389038086,
"min": 0.3195522725582123,
"max": 12.37014389038086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2412.177978515625,
"min": 61.993141174316406,
"max": 2508.247802734375,
"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": 0.07069414776525068,
"min": 0.06368432037233301,
"max": 0.07768914468233204,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2827765910610027,
"min": 0.25473728148933206,
"max": 0.35000107887040655,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19711088440289684,
"min": 0.10100562235240038,
"max": 0.2771388627588749,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7884435376115874,
"min": 0.4040224894096015,
"max": 1.3169737852671568,
"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": 24.613636363636363,
"min": 2.8863636363636362,
"max": 24.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1083.0,
"min": 127.0,
"max": 1334.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.613636363636363,
"min": 2.8863636363636362,
"max": 24.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1083.0,
"min": 127.0,
"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": "1691472809",
"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": "1691473313"
},
"total": 503.583444706,
"count": 1,
"self": 0.38686401399991155,
"children": {
"run_training.setup": {
"total": 0.049674720000098205,
"count": 1,
"self": 0.049674720000098205
},
"TrainerController.start_learning": {
"total": 503.146905972,
"count": 1,
"self": 0.5848800199958077,
"children": {
"TrainerController._reset_env": {
"total": 6.609459980999986,
"count": 1,
"self": 6.609459980999986
},
"TrainerController.advance": {
"total": 495.8091531230042,
"count": 18202,
"self": 0.28494574201067735,
"children": {
"env_step": {
"total": 495.5242073809935,
"count": 18202,
"self": 356.943557515988,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.28276772200502,
"count": 18202,
"self": 1.8364639660073863,
"children": {
"TorchPolicy.evaluate": {
"total": 136.44630375599763,
"count": 18202,
"self": 136.44630375599763
}
}
},
"workers": {
"total": 0.29788214300049276,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 501.5881071850057,
"count": 18202,
"is_parallel": true,
"self": 237.314533265004,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00606467000000066,
"count": 1,
"is_parallel": true,
"self": 0.0043940709997514205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00167059900024924,
"count": 10,
"is_parallel": true,
"self": 0.00167059900024924
}
}
},
"UnityEnvironment.step": {
"total": 0.04913976900002126,
"count": 1,
"is_parallel": true,
"self": 0.0007452760000887793,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006072359999507171,
"count": 1,
"is_parallel": true,
"self": 0.0006072359999507171
},
"communicator.exchange": {
"total": 0.04501930499998252,
"count": 1,
"is_parallel": true,
"self": 0.04501930499998252
},
"steps_from_proto": {
"total": 0.002767951999999241,
"count": 1,
"is_parallel": true,
"self": 0.0005028359997822918,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002265116000216949,
"count": 10,
"is_parallel": true,
"self": 0.002265116000216949
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 264.2735739200017,
"count": 18201,
"is_parallel": true,
"self": 11.123847057006515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.807512100000508,
"count": 18201,
"is_parallel": true,
"self": 5.807512100000508
},
"communicator.exchange": {
"total": 207.40062993699382,
"count": 18201,
"is_parallel": true,
"self": 207.40062993699382
},
"steps_from_proto": {
"total": 39.94158482600085,
"count": 18201,
"is_parallel": true,
"self": 7.359344816023167,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.58224000997768,
"count": 182010,
"is_parallel": true,
"self": 32.58224000997768
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012368700004117272,
"count": 1,
"self": 0.00012368700004117272,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 491.7430237118351,
"count": 454539,
"is_parallel": true,
"self": 11.118740963844289,
"children": {
"process_trajectory": {
"total": 269.9504946669907,
"count": 454539,
"is_parallel": true,
"self": 268.6952105119906,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2552841550001403,
"count": 4,
"is_parallel": true,
"self": 1.2552841550001403
}
}
},
"_update_policy": {
"total": 210.6737880810001,
"count": 90,
"is_parallel": true,
"self": 81.76952391000975,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.90426417099036,
"count": 4587,
"is_parallel": true,
"self": 128.90426417099036
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14328916099998423,
"count": 1,
"self": 0.0008879199999682896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14240124100001594,
"count": 1,
"self": 0.14240124100001594
}
}
}
}
}
}
}