Akchunks's picture
First Push
9375e2d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8076501488685608,
"min": 0.8076501488685608,
"max": 2.8711905479431152,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7675.90673828125,
"min": 7675.90673828125,
"max": 29309.11328125,
"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": 12.710213661193848,
"min": 0.23102784156799316,
"max": 12.7863187789917,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2478.49169921875,
"min": 44.819400787353516,
"max": 2608.408935546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0717532801512896,
"min": 0.06386854573331006,
"max": 0.0717532801512896,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2870131206051584,
"min": 0.2610832088120172,
"max": 0.35547931709694314,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23464498778476434,
"min": 0.09451588114047899,
"max": 0.300561555927875,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9385799511390573,
"min": 0.37806352456191594,
"max": 1.5028077796393748,
"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": 24.045454545454547,
"min": 2.840909090909091,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1058.0,
"min": 125.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.045454545454547,
"min": 2.840909090909091,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1058.0,
"min": 125.0,
"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": "1748440197",
"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": "1748440635"
},
"total": 438.806869882,
"count": 1,
"self": 0.6552680870000813,
"children": {
"run_training.setup": {
"total": 0.02337665199991079,
"count": 1,
"self": 0.02337665199991079
},
"TrainerController.start_learning": {
"total": 438.128225143,
"count": 1,
"self": 0.3868841790135775,
"children": {
"TrainerController._reset_env": {
"total": 3.4170304110000416,
"count": 1,
"self": 3.4170304110000416
},
"TrainerController.advance": {
"total": 434.2421341309863,
"count": 18192,
"self": 0.39968576899809705,
"children": {
"env_step": {
"total": 307.93409843999154,
"count": 18192,
"self": 236.52615859398384,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.18803994600523,
"count": 18192,
"self": 1.2976192249996075,
"children": {
"TorchPolicy.evaluate": {
"total": 69.89042072100563,
"count": 18192,
"self": 69.89042072100563
}
}
},
"workers": {
"total": 0.21989990000247417,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.71939330401096,
"count": 18192,
"is_parallel": true,
"self": 229.33733279001672,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005546814000013001,
"count": 1,
"is_parallel": true,
"self": 0.004034511000099883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015123029999131177,
"count": 10,
"is_parallel": true,
"self": 0.0015123029999131177
}
}
},
"UnityEnvironment.step": {
"total": 0.037220459000081973,
"count": 1,
"is_parallel": true,
"self": 0.0006971710001835163,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041489499994895596,
"count": 1,
"is_parallel": true,
"self": 0.00041489499994895596
},
"communicator.exchange": {
"total": 0.03432812500000182,
"count": 1,
"is_parallel": true,
"self": 0.03432812500000182
},
"steps_from_proto": {
"total": 0.0017802679999476823,
"count": 1,
"is_parallel": true,
"self": 0.00035590200013757567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014243659998101066,
"count": 10,
"is_parallel": true,
"self": 0.0014243659998101066
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.38206051399425,
"count": 18191,
"is_parallel": true,
"self": 10.011584418981784,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.557521994998751,
"count": 18191,
"is_parallel": true,
"self": 5.557521994998751
},
"communicator.exchange": {
"total": 159.75647744700643,
"count": 18191,
"is_parallel": true,
"self": 159.75647744700643
},
"steps_from_proto": {
"total": 32.05647665300728,
"count": 18191,
"is_parallel": true,
"self": 5.810194196992825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.246282456014455,
"count": 181910,
"is_parallel": true,
"self": 26.246282456014455
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.90834992199666,
"count": 18192,
"self": 0.49806140698046875,
"children": {
"process_trajectory": {
"total": 27.51400336101608,
"count": 18192,
"self": 27.095022383016044,
"children": {
"RLTrainer._checkpoint": {
"total": 0.418980978000036,
"count": 4,
"self": 0.418980978000036
}
}
},
"_update_policy": {
"total": 97.89628515400011,
"count": 90,
"self": 40.27727073400149,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.61901441999862,
"count": 4587,
"self": 57.61901441999862
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.020000106829684e-07,
"count": 1,
"self": 9.020000106829684e-07
},
"TrainerController._save_models": {
"total": 0.082175520000078,
"count": 1,
"self": 0.0008271400000694484,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08134838000000855,
"count": 1,
"self": 0.08134838000000855
}
}
}
}
}
}
}