octnn's picture
First Push
414282f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9606199264526367,
"min": 0.9606199264526367,
"max": 2.869412422180176,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9171.9990234375,
"min": 9171.9990234375,
"max": 29417.216796875,
"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": 13.157086372375488,
"min": 0.3576734960079193,
"max": 13.242154121398926,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2565.6318359375,
"min": 69.38865661621094,
"max": 2701.3994140625,
"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.Losses.PolicyLoss.mean": {
"value": 0.07151631899134314,
"min": 0.060937288427250644,
"max": 0.07611968992186674,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28606527596537257,
"min": 0.24374915370900258,
"max": 0.3805984496093337,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20241344245333298,
"min": 0.11511931632070199,
"max": 0.26023525519698276,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8096537698133319,
"min": 0.46047726528280797,
"max": 1.3011762759849137,
"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.CumulativeReward.mean": {
"value": 24.931818181818183,
"min": 3.3181818181818183,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 146.0,
"max": 1445.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.3181818181818183,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 146.0,
"max": 1445.0,
"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": "1706763156",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706763585"
},
"total": 429.23791672899995,
"count": 1,
"self": 0.43744670399991037,
"children": {
"run_training.setup": {
"total": 0.07348152800000207,
"count": 1,
"self": 0.07348152800000207
},
"TrainerController.start_learning": {
"total": 428.72698849700004,
"count": 1,
"self": 0.5374308900053961,
"children": {
"TrainerController._reset_env": {
"total": 3.082109621000029,
"count": 1,
"self": 3.082109621000029
},
"TrainerController.advance": {
"total": 425.01661097499465,
"count": 18200,
"self": 0.25917276599517436,
"children": {
"env_step": {
"total": 424.7574382089995,
"count": 18200,
"self": 275.8834007540003,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.60839787400187,
"count": 18200,
"self": 1.3980963050032074,
"children": {
"TorchPolicy.evaluate": {
"total": 147.21030156899866,
"count": 18200,
"self": 147.21030156899866
}
}
},
"workers": {
"total": 0.2656395809972878,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.5895964579994,
"count": 18200,
"is_parallel": true,
"self": 212.62715448199947,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005340071999967222,
"count": 1,
"is_parallel": true,
"self": 0.003803549000053863,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001536522999913359,
"count": 10,
"is_parallel": true,
"self": 0.001536522999913359
}
}
},
"UnityEnvironment.step": {
"total": 0.0408267370000317,
"count": 1,
"is_parallel": true,
"self": 0.0007490369999914037,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005683840000187956,
"count": 1,
"is_parallel": true,
"self": 0.0005683840000187956
},
"communicator.exchange": {
"total": 0.03764938000000484,
"count": 1,
"is_parallel": true,
"self": 0.03764938000000484
},
"steps_from_proto": {
"total": 0.0018599360000166598,
"count": 1,
"is_parallel": true,
"self": 0.00035189700003002145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015080389999866384,
"count": 10,
"is_parallel": true,
"self": 0.0015080389999866384
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.96244197599992,
"count": 18199,
"is_parallel": true,
"self": 10.495925326999213,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.282791719004706,
"count": 18199,
"is_parallel": true,
"self": 5.282791719004706
},
"communicator.exchange": {
"total": 166.43526101699587,
"count": 18199,
"is_parallel": true,
"self": 166.43526101699587
},
"steps_from_proto": {
"total": 32.74846391300014,
"count": 18199,
"is_parallel": true,
"self": 6.053491812986351,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.694972100013786,
"count": 181990,
"is_parallel": true,
"self": 26.694972100013786
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.567600003862026e-05,
"count": 1,
"self": 3.567600003862026e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 419.5182501350362,
"count": 652609,
"is_parallel": true,
"self": 13.806047379018139,
"children": {
"process_trajectory": {
"total": 231.4293031960181,
"count": 652609,
"is_parallel": true,
"self": 230.90632976601802,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5229734300000928,
"count": 4,
"is_parallel": true,
"self": 0.5229734300000928
}
}
},
"_update_policy": {
"total": 174.28289955999998,
"count": 90,
"is_parallel": true,
"self": 50.05317052099247,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.22972903900751,
"count": 4587,
"is_parallel": true,
"self": 124.22972903900751
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09080133499992371,
"count": 1,
"self": 0.0009763149998889276,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08982502000003478,
"count": 1,
"self": 0.08982502000003478
}
}
}
}
}
}
}