wangbadao's picture
First Push
1315a8d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9097163677215576,
"min": 0.8943989276885986,
"max": 2.8589723110198975,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8645.9443359375,
"min": 8645.9443359375,
"max": 29184.388671875,
"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": 12.939566612243652,
"min": 0.4422692656517029,
"max": 12.957082748413086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.215576171875,
"min": 85.80023956298828,
"max": 2643.302734375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06883282171895867,
"min": 0.06469637814777397,
"max": 0.07497711228614778,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2753312868758347,
"min": 0.2587855125910959,
"max": 0.35734707030453994,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1852420492134258,
"min": 0.12611400377000773,
"max": 0.2916208493358949,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7409681968537032,
"min": 0.5044560150800309,
"max": 1.4581042466794745,
"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": 25.181818181818183,
"min": 3.772727272727273,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 166.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 3.772727272727273,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 166.0,
"max": 1406.0,
"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": "1764923380",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764923823"
},
"total": 442.1821802909999,
"count": 1,
"self": 0.4337233189999097,
"children": {
"run_training.setup": {
"total": 0.02760954599989418,
"count": 1,
"self": 0.02760954599989418
},
"TrainerController.start_learning": {
"total": 441.7208474260001,
"count": 1,
"self": 0.3787258020106492,
"children": {
"TrainerController._reset_env": {
"total": 3.7274927250000474,
"count": 1,
"self": 3.7274927250000474
},
"TrainerController.advance": {
"total": 437.53934124898933,
"count": 18192,
"self": 0.3883401959751609,
"children": {
"env_step": {
"total": 317.78092385600803,
"count": 18192,
"self": 248.39529352202135,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.16046957698154,
"count": 18192,
"self": 1.2616263839834119,
"children": {
"TorchPolicy.evaluate": {
"total": 67.89884319299813,
"count": 18192,
"self": 67.89884319299813
}
}
},
"workers": {
"total": 0.22516075700514193,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.03270869600624,
"count": 18192,
"is_parallel": true,
"self": 222.1151377970184,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003668368999797167,
"count": 1,
"is_parallel": true,
"self": 0.0017054979998647468,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00196287099993242,
"count": 10,
"is_parallel": true,
"self": 0.00196287099993242
}
}
},
"UnityEnvironment.step": {
"total": 0.056169607999891014,
"count": 1,
"is_parallel": true,
"self": 0.0006125489999249112,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0010833950000233017,
"count": 1,
"is_parallel": true,
"self": 0.0010833950000233017
},
"communicator.exchange": {
"total": 0.052620588000081625,
"count": 1,
"is_parallel": true,
"self": 0.052620588000081625
},
"steps_from_proto": {
"total": 0.0018530759998611757,
"count": 1,
"is_parallel": true,
"self": 0.00036680200014416187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014862739997170138,
"count": 10,
"is_parallel": true,
"self": 0.0014862739997170138
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.91757089898783,
"count": 18191,
"is_parallel": true,
"self": 10.288150921991473,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.363747556009685,
"count": 18191,
"is_parallel": true,
"self": 5.363747556009685
},
"communicator.exchange": {
"total": 165.92242727499774,
"count": 18191,
"is_parallel": true,
"self": 165.92242727499774
},
"steps_from_proto": {
"total": 36.34324514598893,
"count": 18191,
"is_parallel": true,
"self": 6.532766006030215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.810479139958716,
"count": 181910,
"is_parallel": true,
"self": 29.810479139958716
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.37007719700614,
"count": 18192,
"self": 0.45455444598701433,
"children": {
"process_trajectory": {
"total": 26.34153541601927,
"count": 18192,
"self": 25.812454350019152,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5290810660001171,
"count": 4,
"self": 0.5290810660001171
}
}
},
"_update_policy": {
"total": 92.57398733499986,
"count": 90,
"self": 37.89685952900527,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.67712780599459,
"count": 4587,
"self": 54.67712780599459
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.809999260643963e-07,
"count": 1,
"self": 7.809999260643963e-07
},
"TrainerController._save_models": {
"total": 0.07528686900013781,
"count": 1,
"self": 0.0006994430000304419,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07458742600010737,
"count": 1,
"self": 0.07458742600010737
}
}
}
}
}
}
}