ZachXie's picture
First Push
f49ed28 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8730513453483582,
"min": 0.8551894426345825,
"max": 2.863522529602051,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8383.912109375,
"min": 8383.912109375,
"max": 29356.83203125,
"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": 12.955491065979004,
"min": 0.46135133504867554,
"max": 12.955491065979004,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2526.32080078125,
"min": 89.50215911865234,
"max": 2642.5234375,
"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": 0.0700700267788146,
"min": 0.06260429673763128,
"max": 0.0745151947543776,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2802801071152584,
"min": 0.2504171869505251,
"max": 0.37128655702348196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20397652488420992,
"min": 0.1280534756461195,
"max": 0.26645662832786055,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8159060995368397,
"min": 0.512213902584478,
"max": 1.330805066169477,
"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": 24.84090909090909,
"min": 3.6136363636363638,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 159.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.6136363636363638,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 159.0,
"max": 1415.0,
"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": "1732908527",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732909126"
},
"total": 598.8879483640001,
"count": 1,
"self": 0.5395854240000517,
"children": {
"run_training.setup": {
"total": 0.07300994199999877,
"count": 1,
"self": 0.07300994199999877
},
"TrainerController.start_learning": {
"total": 598.275352998,
"count": 1,
"self": 0.8037607359985941,
"children": {
"TrainerController._reset_env": {
"total": 6.966457268999989,
"count": 1,
"self": 6.966457268999989
},
"TrainerController.advance": {
"total": 590.3786697770013,
"count": 18217,
"self": 0.4036319710068028,
"children": {
"env_step": {
"total": 589.9750378059945,
"count": 18217,
"self": 456.270334564987,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.2920244520106,
"count": 18217,
"self": 2.198925352012509,
"children": {
"TorchPolicy.evaluate": {
"total": 131.09309909999808,
"count": 18217,
"self": 131.09309909999808
}
}
},
"workers": {
"total": 0.41267878899685684,
"count": 18217,
"self": 0.0,
"children": {
"worker_root": {
"total": 596.4747015130035,
"count": 18217,
"is_parallel": true,
"self": 284.3375451589995,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0033610120000275856,
"count": 1,
"is_parallel": true,
"self": 0.0008166970001184382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025443149999091474,
"count": 10,
"is_parallel": true,
"self": 0.0025443149999091474
}
}
},
"UnityEnvironment.step": {
"total": 0.04149731799998335,
"count": 1,
"is_parallel": true,
"self": 0.0008158399999729227,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004585010000255352,
"count": 1,
"is_parallel": true,
"self": 0.0004585010000255352
},
"communicator.exchange": {
"total": 0.037836174999995364,
"count": 1,
"is_parallel": true,
"self": 0.037836174999995364
},
"steps_from_proto": {
"total": 0.0023868019999895296,
"count": 1,
"is_parallel": true,
"self": 0.0004513690000749193,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019354329999146103,
"count": 10,
"is_parallel": true,
"self": 0.0019354329999146103
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 312.13715635400405,
"count": 18216,
"is_parallel": true,
"self": 14.4297763680064,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.545491495999443,
"count": 18216,
"is_parallel": true,
"self": 7.545491495999443
},
"communicator.exchange": {
"total": 246.23577980499198,
"count": 18216,
"is_parallel": true,
"self": 246.23577980499198
},
"steps_from_proto": {
"total": 43.92610868500623,
"count": 18216,
"is_parallel": true,
"self": 8.470732076968204,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.45537660803802,
"count": 182160,
"is_parallel": true,
"self": 35.45537660803802
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00022275900005297444,
"count": 1,
"self": 0.00022275900005297444,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 584.0051406840108,
"count": 761851,
"is_parallel": true,
"self": 16.51402197693494,
"children": {
"process_trajectory": {
"total": 312.37129984807575,
"count": 761851,
"is_parallel": true,
"self": 311.2670435980757,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1042562500000486,
"count": 4,
"is_parallel": true,
"self": 1.1042562500000486
}
}
},
"_update_policy": {
"total": 255.1198188590002,
"count": 90,
"is_parallel": true,
"self": 72.05596205100011,
"children": {
"TorchPPOOptimizer.update": {
"total": 183.06385680800008,
"count": 4584,
"is_parallel": true,
"self": 183.06385680800008
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12624245700010306,
"count": 1,
"self": 0.0012174380001397367,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12502501899996332,
"count": 1,
"self": 0.12502501899996332
}
}
}
}
}
}
}