Rinnnt's picture
First Push
c9d37d5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9026528596878052,
"min": 0.9026528596878052,
"max": 2.8480939865112305,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8578.8125,
"min": 8578.8125,
"max": 29073.34375,
"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": 12.499055862426758,
"min": 0.19289237260818481,
"max": 12.499055862426758,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2437.31591796875,
"min": 37.421119689941406,
"max": 2532.62451171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0658185828882886,
"min": 0.06270918893073138,
"max": 0.07833561573152467,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2632743315531544,
"min": 0.25202620616811844,
"max": 0.3689317647932672,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21595854706623974,
"min": 0.1175070268709176,
"max": 0.2765993917835694,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.863834188264959,
"min": 0.4700281074836704,
"max": 1.2809658886170856,
"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": 24.613636363636363,
"min": 3.1363636363636362,
"max": 25.01818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1083.0,
"min": 138.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.613636363636363,
"min": 3.1363636363636362,
"max": 25.01818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1083.0,
"min": 138.0,
"max": 1376.0,
"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": "1745920969",
"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": "1745921413"
},
"total": 444.22506653900007,
"count": 1,
"self": 0.4816905409999208,
"children": {
"run_training.setup": {
"total": 0.023352452000040103,
"count": 1,
"self": 0.023352452000040103
},
"TrainerController.start_learning": {
"total": 443.7200235460001,
"count": 1,
"self": 0.40705862399317994,
"children": {
"TrainerController._reset_env": {
"total": 3.522179802999972,
"count": 1,
"self": 3.522179802999972
},
"TrainerController.advance": {
"total": 439.704395033007,
"count": 18192,
"self": 0.43695456599709814,
"children": {
"env_step": {
"total": 312.6381710670129,
"count": 18192,
"self": 238.40096727200023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.0074437260082,
"count": 18192,
"self": 1.3608171420165718,
"children": {
"TorchPolicy.evaluate": {
"total": 72.64662658399163,
"count": 18192,
"self": 72.64662658399163
}
}
},
"workers": {
"total": 0.2297600690044419,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 442.27686730202026,
"count": 18192,
"is_parallel": true,
"self": 233.15358618303583,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005661447999955271,
"count": 1,
"is_parallel": true,
"self": 0.00411549999989802,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015459480000572512,
"count": 10,
"is_parallel": true,
"self": 0.0015459480000572512
}
}
},
"UnityEnvironment.step": {
"total": 0.03578332100005355,
"count": 1,
"is_parallel": true,
"self": 0.0006536360000382047,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046163100000740087,
"count": 1,
"is_parallel": true,
"self": 0.00046163100000740087
},
"communicator.exchange": {
"total": 0.03270671600000696,
"count": 1,
"is_parallel": true,
"self": 0.03270671600000696
},
"steps_from_proto": {
"total": 0.0019613380000009784,
"count": 1,
"is_parallel": true,
"self": 0.00038069200013524096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015806459998657374,
"count": 10,
"is_parallel": true,
"self": 0.0015806459998657374
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.12328111898444,
"count": 18191,
"is_parallel": true,
"self": 10.041441491982255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3867883459990935,
"count": 18191,
"is_parallel": true,
"self": 5.3867883459990935
},
"communicator.exchange": {
"total": 161.9044901990094,
"count": 18191,
"is_parallel": true,
"self": 161.9044901990094
},
"steps_from_proto": {
"total": 31.7905610819937,
"count": 18191,
"is_parallel": true,
"self": 5.785246562025122,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.00531451996858,
"count": 181910,
"is_parallel": true,
"self": 26.00531451996858
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 126.62926939999704,
"count": 18192,
"self": 0.5051241050016415,
"children": {
"process_trajectory": {
"total": 27.00562736199629,
"count": 18192,
"self": 26.550406072996225,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45522128900006464,
"count": 4,
"self": 0.45522128900006464
}
}
},
"_update_policy": {
"total": 99.11851793299911,
"count": 90,
"self": 40.413718375994904,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.70479955700421,
"count": 4587,
"self": 58.70479955700421
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.51999936660286e-07,
"count": 1,
"self": 9.51999936660286e-07
},
"TrainerController._save_models": {
"total": 0.08638913400000092,
"count": 1,
"self": 0.0008341749999090098,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08555495900009191,
"count": 1,
"self": 0.08555495900009191
}
}
}
}
}
}
}