YinuoTHU's picture
First Push
b0c00e9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8816694617271423,
"min": 0.8560543060302734,
"max": 2.8411037921905518,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8379.38671875,
"min": 8379.38671875,
"max": 29001.986328125,
"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": 11.773322105407715,
"min": 0.40624573826789856,
"max": 11.773322105407715,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2295.7978515625,
"min": 78.81167602539062,
"max": 2377.97216796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06956805763069959,
"min": 0.06327805420432478,
"max": 0.0736974971893919,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27827223052279837,
"min": 0.2587877946618178,
"max": 0.3651845252732564,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1959996140178512,
"min": 0.11964588526262007,
"max": 0.273694551239411,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7839984560714048,
"min": 0.4785835410504803,
"max": 1.3352829290955675,
"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": 23.227272727272727,
"min": 3.477272727272727,
"max": 23.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1022.0,
"min": 153.0,
"max": 1288.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.227272727272727,
"min": 3.477272727272727,
"max": 23.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1022.0,
"min": 153.0,
"max": 1288.0,
"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": "1766478264",
"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": "1766478715"
},
"total": 450.651732392,
"count": 1,
"self": 0.43307380199985346,
"children": {
"run_training.setup": {
"total": 0.026734306000093966,
"count": 1,
"self": 0.026734306000093966
},
"TrainerController.start_learning": {
"total": 450.19192428400004,
"count": 1,
"self": 0.3798712080123323,
"children": {
"TrainerController._reset_env": {
"total": 2.8077333720000297,
"count": 1,
"self": 2.8077333720000297
},
"TrainerController.advance": {
"total": 446.92317103698747,
"count": 18192,
"self": 0.384851947011839,
"children": {
"env_step": {
"total": 326.442575793974,
"count": 18192,
"self": 255.8094096359847,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.4104608630023,
"count": 18192,
"self": 1.2840990129974443,
"children": {
"TorchPolicy.evaluate": {
"total": 69.12636185000486,
"count": 18192,
"self": 69.12636185000486
}
}
},
"workers": {
"total": 0.22270529498700853,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.5283493219978,
"count": 18192,
"is_parallel": true,
"self": 223.46976822400143,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00490267700001823,
"count": 1,
"is_parallel": true,
"self": 0.003409888000078354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014927889999398758,
"count": 10,
"is_parallel": true,
"self": 0.0014927889999398758
}
}
},
"UnityEnvironment.step": {
"total": 0.03738357299994277,
"count": 1,
"is_parallel": true,
"self": 0.0006569799998032977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043352600005164277,
"count": 1,
"is_parallel": true,
"self": 0.00043352600005164277
},
"communicator.exchange": {
"total": 0.03433266100000765,
"count": 1,
"is_parallel": true,
"self": 0.03433266100000765
},
"steps_from_proto": {
"total": 0.0019604060000801837,
"count": 1,
"is_parallel": true,
"self": 0.000371188000372058,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015892179997081257,
"count": 10,
"is_parallel": true,
"self": 0.0015892179997081257
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.05858109799635,
"count": 18191,
"is_parallel": true,
"self": 10.729300071973512,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.617442718992379,
"count": 18191,
"is_parallel": true,
"self": 5.617442718992379
},
"communicator.exchange": {
"total": 170.78900582302913,
"count": 18191,
"is_parallel": true,
"self": 170.78900582302913
},
"steps_from_proto": {
"total": 37.92283248400133,
"count": 18191,
"is_parallel": true,
"self": 6.682981907930412,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.23985057607092,
"count": 181910,
"is_parallel": true,
"self": 31.23985057607092
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.09574329600161,
"count": 18192,
"self": 0.44860376599763185,
"children": {
"process_trajectory": {
"total": 26.525729840004033,
"count": 18192,
"self": 25.96637282300412,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5593570169999111,
"count": 4,
"self": 0.5593570169999111
}
}
},
"_update_policy": {
"total": 93.12140968999995,
"count": 90,
"self": 38.575577744999464,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.54583194500049,
"count": 4587,
"self": 54.54583194500049
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.620000582799548e-07,
"count": 1,
"self": 9.620000582799548e-07
},
"TrainerController._save_models": {
"total": 0.08114770500014856,
"count": 1,
"self": 0.0007950270000947057,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08035267800005386,
"count": 1,
"self": 0.08035267800005386
}
}
}
}
}
}
}