mus-shd's picture
First Push
e5ab908
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9835110902786255,
"min": 0.9835110902786255,
"max": 2.8501687049865723,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9423.01953125,
"min": 9423.01953125,
"max": 29188.578125,
"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": 12.592998504638672,
"min": 0.35965368151664734,
"max": 12.592998504638672,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2455.634765625,
"min": 69.77281188964844,
"max": 2551.11767578125,
"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": 0.0696357848282787,
"min": 0.06305780880519544,
"max": 0.07489940169633721,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2785431393131148,
"min": 0.2625608736907095,
"max": 0.3712520841442051,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2182887641384321,
"min": 0.09835725815911942,
"max": 0.26510916708731186,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8731550565537284,
"min": 0.39342903263647766,
"max": 1.299573315709245,
"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": 24.818181818181817,
"min": 2.727272727272727,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1092.0,
"min": 120.0,
"max": 1359.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.818181818181817,
"min": 2.727272727272727,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1092.0,
"min": 120.0,
"max": 1359.0,
"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": "1704565725",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704566174"
},
"total": 448.41261320700005,
"count": 1,
"self": 0.7609495209999295,
"children": {
"run_training.setup": {
"total": 0.054709287000036966,
"count": 1,
"self": 0.054709287000036966
},
"TrainerController.start_learning": {
"total": 447.5969543990001,
"count": 1,
"self": 0.5514985520002256,
"children": {
"TrainerController._reset_env": {
"total": 3.205675133999989,
"count": 1,
"self": 3.205675133999989
},
"TrainerController.advance": {
"total": 443.7031529889997,
"count": 18211,
"self": 0.2598149750058383,
"children": {
"env_step": {
"total": 443.44333801399387,
"count": 18211,
"self": 290.3984573020002,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.7699850469993,
"count": 18211,
"self": 1.4409740079935318,
"children": {
"TorchPolicy.evaluate": {
"total": 151.32901103900576,
"count": 18211,
"self": 151.32901103900576
}
}
},
"workers": {
"total": 0.2748956649943466,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.4236641379998,
"count": 18211,
"is_parallel": true,
"self": 221.94001918599156,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00482442700001684,
"count": 1,
"is_parallel": true,
"self": 0.0035935169998992933,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012309100001175466,
"count": 10,
"is_parallel": true,
"self": 0.0012309100001175466
}
}
},
"UnityEnvironment.step": {
"total": 0.036504888999957075,
"count": 1,
"is_parallel": true,
"self": 0.0006421069998623352,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039755399996010965,
"count": 1,
"is_parallel": true,
"self": 0.00039755399996010965
},
"communicator.exchange": {
"total": 0.033414821000064876,
"count": 1,
"is_parallel": true,
"self": 0.033414821000064876
},
"steps_from_proto": {
"total": 0.002050407000069754,
"count": 1,
"is_parallel": true,
"self": 0.0003867789999958404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016636280000739134,
"count": 10,
"is_parallel": true,
"self": 0.0016636280000739134
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.48364495200826,
"count": 18210,
"is_parallel": true,
"self": 10.653969097999038,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.359336601004202,
"count": 18210,
"is_parallel": true,
"self": 5.359336601004202
},
"communicator.exchange": {
"total": 175.17048867900553,
"count": 18210,
"is_parallel": true,
"self": 175.17048867900553
},
"steps_from_proto": {
"total": 33.29985057399949,
"count": 18210,
"is_parallel": true,
"self": 6.182510184018952,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.11734038998054,
"count": 182100,
"is_parallel": true,
"self": 27.11734038998054
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015255200014507864,
"count": 1,
"self": 0.00015255200014507864,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 438.31931986792097,
"count": 652136,
"is_parallel": true,
"self": 13.617704083895092,
"children": {
"process_trajectory": {
"total": 242.6239854200262,
"count": 652136,
"is_parallel": true,
"self": 241.40897760502605,
"children": {
"RLTrainer._checkpoint": {
"total": 1.215007815000149,
"count": 4,
"is_parallel": true,
"self": 1.215007815000149
}
}
},
"_update_policy": {
"total": 182.07763036399967,
"count": 90,
"is_parallel": true,
"self": 56.633474312995986,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.44415605100369,
"count": 4584,
"is_parallel": true,
"self": 125.44415605100369
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13647517200001857,
"count": 1,
"self": 0.0012178749998383864,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1352572970001802,
"count": 1,
"self": 0.1352572970001802
}
}
}
}
}
}
}