hieu10x's picture
First Push
0ecace1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7522202730178833,
"min": 0.7431303262710571,
"max": 2.8416366577148438,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7149.1015625,
"min": 7128.10595703125,
"max": 29007.427734375,
"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": 13.27149772644043,
"min": 0.32359743118286133,
"max": 13.286967277526855,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2587.942138671875,
"min": 62.77790069580078,
"max": 2710.541259765625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0701387191946232,
"min": 0.06184057782400701,
"max": 0.07484787938815048,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2805548767784928,
"min": 0.24736231129602804,
"max": 0.36392783153232633,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17488661963565674,
"min": 0.11969930516195246,
"max": 0.27773931201766516,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.699546478542627,
"min": 0.47879722064780983,
"max": 1.3886965600883259,
"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": 25.931818181818183,
"min": 3.3863636363636362,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 149.0,
"max": 1435.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.3863636363636362,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 149.0,
"max": 1435.0,
"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": "1745762544",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745762980"
},
"total": 435.526656594,
"count": 1,
"self": 0.4375698830000374,
"children": {
"run_training.setup": {
"total": 0.02281206599991492,
"count": 1,
"self": 0.02281206599991492
},
"TrainerController.start_learning": {
"total": 435.066274645,
"count": 1,
"self": 0.3753406350078876,
"children": {
"TrainerController._reset_env": {
"total": 3.272705868999992,
"count": 1,
"self": 3.272705868999992
},
"TrainerController.advance": {
"total": 431.3307312329923,
"count": 18192,
"self": 0.3899415790029934,
"children": {
"env_step": {
"total": 308.14735500000074,
"count": 18192,
"self": 235.40160174300024,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.5274317180008,
"count": 18192,
"self": 1.3202147179995336,
"children": {
"TorchPolicy.evaluate": {
"total": 71.20721700000126,
"count": 18192,
"self": 71.20721700000126
}
}
},
"workers": {
"total": 0.21832153899970308,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.56357362501,
"count": 18192,
"is_parallel": true,
"self": 227.49530575201538,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005592475999947055,
"count": 1,
"is_parallel": true,
"self": 0.003970068000171523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016224079997755325,
"count": 10,
"is_parallel": true,
"self": 0.0016224079997755325
}
}
},
"UnityEnvironment.step": {
"total": 0.03540722100001403,
"count": 1,
"is_parallel": true,
"self": 0.0005873779998637474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004469300000664589,
"count": 1,
"is_parallel": true,
"self": 0.0004469300000664589
},
"communicator.exchange": {
"total": 0.032523813000011614,
"count": 1,
"is_parallel": true,
"self": 0.032523813000011614
},
"steps_from_proto": {
"total": 0.0018491000000722124,
"count": 1,
"is_parallel": true,
"self": 0.0004060130002017104,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001443086999870502,
"count": 10,
"is_parallel": true,
"self": 0.001443086999870502
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.06826787299462,
"count": 18191,
"is_parallel": true,
"self": 9.955092226973306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.571501942006762,
"count": 18191,
"is_parallel": true,
"self": 5.571501942006762
},
"communicator.exchange": {
"total": 158.1879535110055,
"count": 18191,
"is_parallel": true,
"self": 158.1879535110055
},
"steps_from_proto": {
"total": 32.35372019300905,
"count": 18191,
"is_parallel": true,
"self": 6.013502776062751,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.340217416946302,
"count": 181910,
"is_parallel": true,
"self": 26.340217416946302
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.79343465398858,
"count": 18192,
"self": 0.47544577900055174,
"children": {
"process_trajectory": {
"total": 27.820271520987376,
"count": 18192,
"self": 27.27780324098751,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5424682799998664,
"count": 4,
"self": 0.5424682799998664
}
}
},
"_update_policy": {
"total": 94.49771735400066,
"count": 90,
"self": 38.18880307699874,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.30891427700192,
"count": 4587,
"self": 56.30891427700192
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.399998361914186e-07,
"count": 1,
"self": 9.399998361914186e-07
},
"TrainerController._save_models": {
"total": 0.08749596799998471,
"count": 1,
"self": 0.0008741189999454946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08662184900003922,
"count": 1,
"self": 0.08662184900003922
}
}
}
}
}
}
}