wahaha1987's picture
First Push
afde218 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0212855339050293,
"min": 1.0212855339050293,
"max": 2.852947950363159,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9751.234375,
"min": 9751.234375,
"max": 29248.421875,
"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": 12.361785888671875,
"min": 0.2252151221036911,
"max": 12.361785888671875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2410.54833984375,
"min": 43.691734313964844,
"max": 2514.10546875,
"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": 0.07223145094558633,
"min": 0.06203314389534296,
"max": 0.0736287733183524,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28892580378234534,
"min": 0.24813257558137183,
"max": 0.35817400655793663,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21676642557277398,
"min": 0.1090701062211712,
"max": 0.2656287144066072,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8670657022910959,
"min": 0.4362804248846848,
"max": 1.270143504820618,
"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": 23.818181818181817,
"min": 2.977272727272727,
"max": 24.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1048.0,
"min": 131.0,
"max": 1351.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.818181818181817,
"min": 2.977272727272727,
"max": 24.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1048.0,
"min": 131.0,
"max": 1351.0,
"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": "1706011814",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706012269"
},
"total": 455.11470509599985,
"count": 1,
"self": 0.6525221909996617,
"children": {
"run_training.setup": {
"total": 0.07612541800017425,
"count": 1,
"self": 0.07612541800017425
},
"TrainerController.start_learning": {
"total": 454.386057487,
"count": 1,
"self": 0.5491034480114649,
"children": {
"TrainerController._reset_env": {
"total": 3.178934998999921,
"count": 1,
"self": 3.178934998999921
},
"TrainerController.advance": {
"total": 450.57132638698863,
"count": 18199,
"self": 0.26432869699942785,
"children": {
"env_step": {
"total": 450.3069976899892,
"count": 18199,
"self": 301.6470041689952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.38005804300633,
"count": 18199,
"self": 1.4554819389809381,
"children": {
"TorchPolicy.evaluate": {
"total": 146.9245761040254,
"count": 18199,
"self": 146.9245761040254
}
}
},
"workers": {
"total": 0.27993547798769214,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.21343880700874,
"count": 18199,
"is_parallel": true,
"self": 224.5897282580163,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004778587000146217,
"count": 1,
"is_parallel": true,
"self": 0.0033474419999492966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014311450001969206,
"count": 10,
"is_parallel": true,
"self": 0.0014311450001969206
}
}
},
"UnityEnvironment.step": {
"total": 0.03652600899999925,
"count": 1,
"is_parallel": true,
"self": 0.0006709479998789902,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004344480000781914,
"count": 1,
"is_parallel": true,
"self": 0.0004344480000781914
},
"communicator.exchange": {
"total": 0.03353229000003921,
"count": 1,
"is_parallel": true,
"self": 0.03353229000003921
},
"steps_from_proto": {
"total": 0.0018883230000028561,
"count": 1,
"is_parallel": true,
"self": 0.0003797870001562842,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001508535999846572,
"count": 10,
"is_parallel": true,
"self": 0.001508535999846572
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.62371054899245,
"count": 18198,
"is_parallel": true,
"self": 10.827632420027157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.266948481001236,
"count": 18198,
"is_parallel": true,
"self": 5.266948481001236
},
"communicator.exchange": {
"total": 178.97835741998438,
"count": 18198,
"is_parallel": true,
"self": 178.97835741998438
},
"steps_from_proto": {
"total": 33.55077222797968,
"count": 18198,
"is_parallel": true,
"self": 6.2785074870016615,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.272264740978017,
"count": 181980,
"is_parallel": true,
"self": 27.272264740978017
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000124429999914355,
"count": 1,
"self": 0.000124429999914355,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.0798418320544,
"count": 670508,
"is_parallel": true,
"self": 14.009638174038855,
"children": {
"process_trajectory": {
"total": 244.22001140501516,
"count": 670508,
"is_parallel": true,
"self": 243.71011108601533,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5099003189998257,
"count": 4,
"is_parallel": true,
"self": 0.5099003189998257
}
}
},
"_update_policy": {
"total": 186.8501922530004,
"count": 90,
"is_parallel": true,
"self": 67.02464907398917,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.82554317901122,
"count": 4587,
"is_parallel": true,
"self": 119.82554317901122
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08656822300008571,
"count": 1,
"self": 0.0009855940002125863,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08558262899987312,
"count": 1,
"self": 0.08558262899987312
}
}
}
}
}
}
}