thortywell's picture
First Push
fc8f071 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6586259007453918,
"min": 0.6442537307739258,
"max": 2.8658699989318848,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6259.58056640625,
"min": 6259.58056640625,
"max": 29254.80078125,
"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": 13.340539932250977,
"min": 0.3482213318347931,
"max": 13.340539932250977,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2601.4052734375,
"min": 67.55493927001953,
"max": 2700.70556640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06372174548924509,
"min": 0.06138415462685539,
"max": 0.07614827450278086,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25488698195698034,
"min": 0.25337269171837296,
"max": 0.38074137251390433,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.189777440154085,
"min": 0.11220555222940211,
"max": 0.31542908724616553,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.75910976061634,
"min": 0.44882220891760843,
"max": 1.5771454362308277,
"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.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.Environment.CumulativeReward.mean": {
"value": 26.15909090909091,
"min": 3.1363636363636362,
"max": 26.30909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1151.0,
"min": 138.0,
"max": 1447.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.15909090909091,
"min": 3.1363636363636362,
"max": 26.30909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1151.0,
"min": 138.0,
"max": 1447.0,
"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": "1762616282",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1762616724"
},
"total": 441.98374107400014,
"count": 1,
"self": 0.43558253200012587,
"children": {
"run_training.setup": {
"total": 0.02356657600012113,
"count": 1,
"self": 0.02356657600012113
},
"TrainerController.start_learning": {
"total": 441.5245919659999,
"count": 1,
"self": 0.42620911500830516,
"children": {
"TrainerController._reset_env": {
"total": 2.995572015999869,
"count": 1,
"self": 2.995572015999869
},
"TrainerController.advance": {
"total": 438.02608912899177,
"count": 18192,
"self": 0.4401945729923682,
"children": {
"env_step": {
"total": 318.2571144500057,
"count": 18192,
"self": 248.80433296699562,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.20153445800929,
"count": 18192,
"self": 1.2919439490015066,
"children": {
"TorchPolicy.evaluate": {
"total": 67.90959050900778,
"count": 18192,
"self": 67.90959050900778
}
}
},
"workers": {
"total": 0.25124702500079366,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 439.7747359599912,
"count": 18192,
"is_parallel": true,
"self": 221.91577422395767,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005177320000029795,
"count": 1,
"is_parallel": true,
"self": 0.0037151110002469068,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001462208999782888,
"count": 10,
"is_parallel": true,
"self": 0.001462208999782888
}
}
},
"UnityEnvironment.step": {
"total": 0.03465534099996148,
"count": 1,
"is_parallel": true,
"self": 0.0005897250000543863,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038795599994045915,
"count": 1,
"is_parallel": true,
"self": 0.00038795599994045915
},
"communicator.exchange": {
"total": 0.03186955800015312,
"count": 1,
"is_parallel": true,
"self": 0.03186955800015312
},
"steps_from_proto": {
"total": 0.0018081019998135162,
"count": 1,
"is_parallel": true,
"self": 0.0003878419997818128,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014202600000317034,
"count": 10,
"is_parallel": true,
"self": 0.0014202600000317034
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.8589617360335,
"count": 18191,
"is_parallel": true,
"self": 10.034353274043951,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3988659530189125,
"count": 18191,
"is_parallel": true,
"self": 5.3988659530189125
},
"communicator.exchange": {
"total": 167.0946662179881,
"count": 18191,
"is_parallel": true,
"self": 167.0946662179881
},
"steps_from_proto": {
"total": 35.33107629098254,
"count": 18191,
"is_parallel": true,
"self": 6.536388482004895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.794687808977642,
"count": 181910,
"is_parallel": true,
"self": 28.794687808977642
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.3287801059937,
"count": 18192,
"self": 0.5197574430023906,
"children": {
"process_trajectory": {
"total": 25.607048617989904,
"count": 18192,
"self": 25.189515550990336,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4175330669995674,
"count": 4,
"self": 0.4175330669995674
}
}
},
"_update_policy": {
"total": 93.2019740450014,
"count": 90,
"self": 38.772803934001104,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.4291701110003,
"count": 4587,
"self": 54.4291701110003
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.629998203308787e-07,
"count": 1,
"self": 9.629998203308787e-07
},
"TrainerController._save_models": {
"total": 0.07672074300012355,
"count": 1,
"self": 0.0007633230002284108,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07595741999989514,
"count": 1,
"self": 0.07595741999989514
}
}
}
}
}
}
}