Huav's picture
First Push
9d4b578 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9120166897773743,
"min": 0.9120166897773743,
"max": 2.8636624813079834,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8667.806640625,
"min": 8667.806640625,
"max": 29232.265625,
"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": 12.910381317138672,
"min": 0.49285051226615906,
"max": 12.910381317138672,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2517.5244140625,
"min": 95.61299896240234,
"max": 2616.998046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06967699415148601,
"min": 0.06433809353175628,
"max": 0.07493113358656295,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27870797660594404,
"min": 0.2684421477846199,
"max": 0.3485907525669866,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23040545096292214,
"min": 0.1435191270178549,
"max": 0.2957040695583119,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9216218038516886,
"min": 0.5740765080714196,
"max": 1.4785203477915596,
"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": 25.318181818181817,
"min": 4.0227272727272725,
"max": 25.472727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 177.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 4.0227272727272725,
"max": 25.472727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 177.0,
"max": 1401.0,
"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": "1769407839",
"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 --force",
"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": "1769408108"
},
"total": 268.78133814499597,
"count": 1,
"self": 0.16720303399779368,
"children": {
"run_training.setup": {
"total": 0.011389074003091082,
"count": 1,
"self": 0.011389074003091082
},
"TrainerController.start_learning": {
"total": 268.6027460369951,
"count": 1,
"self": 0.1778077292110538,
"children": {
"TrainerController._reset_env": {
"total": 1.3848611209978117,
"count": 1,
"self": 1.3848611209978117
},
"TrainerController.advance": {
"total": 266.9982431027893,
"count": 18192,
"self": 0.16656430558941793,
"children": {
"env_step": {
"total": 196.26713004661724,
"count": 18192,
"self": 137.73722203020588,
"children": {
"SubprocessEnvManager._take_step": {
"total": 58.41955981979845,
"count": 18192,
"self": 0.6018941982038086,
"children": {
"TorchPolicy.evaluate": {
"total": 57.81766562159464,
"count": 18192,
"self": 57.81766562159464
}
}
},
"workers": {
"total": 0.11034819661290385,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 268.01368951667973,
"count": 18192,
"is_parallel": true,
"self": 141.4217713343969,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0015456539986189455,
"count": 1,
"is_parallel": true,
"self": 0.0008327230316353962,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007129309669835493,
"count": 10,
"is_parallel": true,
"self": 0.0007129309669835493
}
}
},
"UnityEnvironment.step": {
"total": 0.013777219006442465,
"count": 1,
"is_parallel": true,
"self": 0.0001523690007161349,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001141820102930069,
"count": 1,
"is_parallel": true,
"self": 0.0001141820102930069
},
"communicator.exchange": {
"total": 0.013104047990054823,
"count": 1,
"is_parallel": true,
"self": 0.013104047990054823
},
"steps_from_proto": {
"total": 0.00040662000537849963,
"count": 1,
"is_parallel": true,
"self": 9.272899478673935e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003138910105917603,
"count": 10,
"is_parallel": true,
"self": 0.0003138910105917603
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 126.59191818228283,
"count": 18191,
"is_parallel": true,
"self": 2.6535540659097023,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.4223509444855154,
"count": 18191,
"is_parallel": true,
"self": 1.4223509444855154
},
"communicator.exchange": {
"total": 115.42373428888095,
"count": 18191,
"is_parallel": true,
"self": 115.42373428888095
},
"steps_from_proto": {
"total": 7.0922788830066565,
"count": 18191,
"is_parallel": true,
"self": 1.4504084328364115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.641870450170245,
"count": 181910,
"is_parallel": true,
"self": 5.641870450170245
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 70.56454875058262,
"count": 18192,
"self": 0.2013564581866376,
"children": {
"process_trajectory": {
"total": 14.088357786386041,
"count": 18192,
"self": 13.877279078398715,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2110787079873262,
"count": 4,
"self": 0.2110787079873262
}
}
},
"_update_policy": {
"total": 56.27483450600994,
"count": 90,
"self": 12.651598865209962,
"children": {
"TorchPPOOptimizer.update": {
"total": 43.623235640799976,
"count": 4587,
"self": 43.623235640799976
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.644002622924745e-06,
"count": 1,
"self": 1.644002622924745e-06
},
"TrainerController._save_models": {
"total": 0.04183243999432307,
"count": 1,
"self": 0.0004858149914070964,
"children": {
"RLTrainer._checkpoint": {
"total": 0.04134662500291597,
"count": 1,
"self": 0.04134662500291597
}
}
}
}
}
}
}