Logic-TARS's picture
First Push
141e927 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7540929913520813,
"min": 0.7029389142990112,
"max": 2.831083297729492,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7166.89990234375,
"min": 6742.58984375,
"max": 28899.697265625,
"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": 12.052879333496094,
"min": 0.4205572307109833,
"max": 12.059191703796387,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2350.3115234375,
"min": 81.58810424804688,
"max": 2472.13427734375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06969605411505458,
"min": 0.06203366491053934,
"max": 0.07561859331098295,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27878421646021834,
"min": 0.2574240028559728,
"max": 0.3780929665549147,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17377426066235,
"min": 0.11277938538628138,
"max": 0.2537661145715152,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6950970426494,
"min": 0.4511175415451255,
"max": 1.2688305728575762,
"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": 23.386363636363637,
"min": 3.25,
"max": 23.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1029.0,
"min": 143.0,
"max": 1303.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.386363636363637,
"min": 3.25,
"max": 23.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1029.0,
"min": 143.0,
"max": 1303.0,
"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": "1744078171",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744078749"
},
"total": 577.6138855390001,
"count": 1,
"self": 0.5354153060001181,
"children": {
"run_training.setup": {
"total": 0.0498835839999856,
"count": 1,
"self": 0.0498835839999856
},
"TrainerController.start_learning": {
"total": 577.028586649,
"count": 1,
"self": 0.6383038079862899,
"children": {
"TrainerController._reset_env": {
"total": 3.6681428959999494,
"count": 1,
"self": 3.6681428959999494
},
"TrainerController.advance": {
"total": 572.6384099230137,
"count": 18192,
"self": 0.6365724410017037,
"children": {
"env_step": {
"total": 397.5300555269873,
"count": 18192,
"self": 337.468410006019,
"children": {
"SubprocessEnvManager._take_step": {
"total": 59.69704473797253,
"count": 18192,
"self": 2.0350141419766032,
"children": {
"TorchPolicy.evaluate": {
"total": 57.66203059599593,
"count": 18192,
"self": 57.66203059599593
}
}
},
"workers": {
"total": 0.364600782995808,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 574.8923661449863,
"count": 18192,
"is_parallel": true,
"self": 283.20901028396133,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007253062000017962,
"count": 1,
"is_parallel": true,
"self": 0.004846179000196571,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024068829998213914,
"count": 10,
"is_parallel": true,
"self": 0.0024068829998213914
}
}
},
"UnityEnvironment.step": {
"total": 0.04566703999989841,
"count": 1,
"is_parallel": true,
"self": 0.0007446989998243225,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046141200004967686,
"count": 1,
"is_parallel": true,
"self": 0.00046141200004967686
},
"communicator.exchange": {
"total": 0.04211859099996218,
"count": 1,
"is_parallel": true,
"self": 0.04211859099996218
},
"steps_from_proto": {
"total": 0.0023423380000622274,
"count": 1,
"is_parallel": true,
"self": 0.00041506100001242885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019272770000497985,
"count": 10,
"is_parallel": true,
"self": 0.0019272770000497985
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 291.683355861025,
"count": 18191,
"is_parallel": true,
"self": 13.914631708037405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.284573199988131,
"count": 18191,
"is_parallel": true,
"self": 7.284573199988131
},
"communicator.exchange": {
"total": 228.53977971099823,
"count": 18191,
"is_parallel": true,
"self": 228.53977971099823
},
"steps_from_proto": {
"total": 41.94437124200124,
"count": 18191,
"is_parallel": true,
"self": 8.089010012970334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.855361229030905,
"count": 181910,
"is_parallel": true,
"self": 33.855361229030905
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 174.47178195502465,
"count": 18192,
"self": 0.8470006430326293,
"children": {
"process_trajectory": {
"total": 31.80672178199336,
"count": 18192,
"self": 31.34281953299353,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4639022489998297,
"count": 4,
"self": 0.4639022489998297
}
}
},
"_update_policy": {
"total": 141.81805952999866,
"count": 90,
"self": 49.88069478900616,
"children": {
"TorchPPOOptimizer.update": {
"total": 91.9373647409925,
"count": 4587,
"self": 91.9373647409925
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3210001270635985e-06,
"count": 1,
"self": 1.3210001270635985e-06
},
"TrainerController._save_models": {
"total": 0.08372870099992724,
"count": 1,
"self": 0.0011965639998834376,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0825321370000438,
"count": 1,
"self": 0.0825321370000438
}
}
}
}
}
}
}