neopolita's picture
First Push
a63222a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9291772842407227,
"min": 0.904502809047699,
"max": 2.8690266609191895,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8892.2265625,
"min": 8892.2265625,
"max": 29444.8203125,
"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": 12.968717575073242,
"min": 0.526978075504303,
"max": 12.968717575073242,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.89990234375,
"min": 102.23374938964844,
"max": 2636.4677734375,
"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": 0.07017575486194498,
"min": 0.059725171338743846,
"max": 0.07880271900235218,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2807030194477799,
"min": 0.23890068535497538,
"max": 0.37011595741519243,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20775830826046418,
"min": 0.1303937013110365,
"max": 0.2681741471237996,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8310332330418567,
"min": 0.521574805244146,
"max": 1.3324227216196995,
"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": 25.5,
"min": 3.5,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 154.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.5,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 154.0,
"max": 1409.0,
"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": "1702419560",
"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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702420050"
},
"total": 489.96633215799994,
"count": 1,
"self": 0.44565355399993223,
"children": {
"run_training.setup": {
"total": 0.05804271099998459,
"count": 1,
"self": 0.05804271099998459
},
"TrainerController.start_learning": {
"total": 489.462635893,
"count": 1,
"self": 0.5754094260060469,
"children": {
"TrainerController._reset_env": {
"total": 3.683009545999994,
"count": 1,
"self": 3.683009545999994
},
"TrainerController.advance": {
"total": 485.1137604339939,
"count": 18201,
"self": 0.2798488949916873,
"children": {
"env_step": {
"total": 484.8339115390022,
"count": 18201,
"self": 325.3944803990013,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.15413716099977,
"count": 18201,
"self": 1.5275655109926447,
"children": {
"TorchPolicy.evaluate": {
"total": 157.62657165000712,
"count": 18201,
"self": 157.62657165000712
}
}
},
"workers": {
"total": 0.2852939790011533,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 488.1257646490015,
"count": 18201,
"is_parallel": true,
"self": 241.08219004300037,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0055687020000050325,
"count": 1,
"is_parallel": true,
"self": 0.003964851000091585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016038509999134476,
"count": 10,
"is_parallel": true,
"self": 0.0016038509999134476
}
}
},
"UnityEnvironment.step": {
"total": 0.04096662999995715,
"count": 1,
"is_parallel": true,
"self": 0.0007004720000054476,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032623099997408644,
"count": 1,
"is_parallel": true,
"self": 0.00032623099997408644
},
"communicator.exchange": {
"total": 0.0378089980000027,
"count": 1,
"is_parallel": true,
"self": 0.0378089980000027
},
"steps_from_proto": {
"total": 0.0021309289999749126,
"count": 1,
"is_parallel": true,
"self": 0.0003804899999408917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017504390000340209,
"count": 10,
"is_parallel": true,
"self": 0.0017504390000340209
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.04357460600113,
"count": 18200,
"is_parallel": true,
"self": 10.888850785008401,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.721437000009416,
"count": 18200,
"is_parallel": true,
"self": 5.721437000009416
},
"communicator.exchange": {
"total": 194.03765006199296,
"count": 18200,
"is_parallel": true,
"self": 194.03765006199296
},
"steps_from_proto": {
"total": 36.39563675899035,
"count": 18200,
"is_parallel": true,
"self": 6.807062325987545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.588574433002805,
"count": 182000,
"is_parallel": true,
"self": 29.588574433002805
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001644760000090173,
"count": 1,
"self": 0.0001644760000090173,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 480.5854753399878,
"count": 530698,
"is_parallel": true,
"self": 11.666155827951059,
"children": {
"process_trajectory": {
"total": 272.6474505660371,
"count": 530698,
"is_parallel": true,
"self": 271.8523622570371,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7950883089999934,
"count": 4,
"is_parallel": true,
"self": 0.7950883089999934
}
}
},
"_update_policy": {
"total": 196.27186894599964,
"count": 90,
"is_parallel": true,
"self": 61.47036279299584,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.8015061530038,
"count": 4587,
"is_parallel": true,
"self": 134.8015061530038
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09029201100008777,
"count": 1,
"self": 0.0009459250001100372,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08934608599997773,
"count": 1,
"self": 0.08934608599997773
}
}
}
}
}
}
}