Statos6's picture
First Push
6571cc2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9813522100448608,
"min": 0.9813522100448608,
"max": 2.8713881969451904,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9369.951171875,
"min": 9369.951171875,
"max": 29437.47265625,
"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": 11.976715087890625,
"min": 0.38006144762039185,
"max": 11.976715087890625,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2335.45947265625,
"min": 73.73191833496094,
"max": 2415.39208984375,
"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": 0.06295664096771861,
"min": 0.05941503118340145,
"max": 0.07686108551227816,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25182656387087443,
"min": 0.2376601247336058,
"max": 0.3645600181195072,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20869448119957074,
"min": 0.11459970816755302,
"max": 0.28208685454492477,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8347779247982829,
"min": 0.4583988326702121,
"max": 1.2940226568310869,
"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": 23.636363636363637,
"min": 3.5454545454545454,
"max": 24.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1040.0,
"min": 156.0,
"max": 1320.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.636363636363637,
"min": 3.5454545454545454,
"max": 24.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1040.0,
"min": 156.0,
"max": 1320.0,
"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": "1709059403",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709059841"
},
"total": 438.649011191,
"count": 1,
"self": 0.4362298880000708,
"children": {
"run_training.setup": {
"total": 0.04922320800005764,
"count": 1,
"self": 0.04922320800005764
},
"TrainerController.start_learning": {
"total": 438.16355809499987,
"count": 1,
"self": 0.5409318419949614,
"children": {
"TrainerController._reset_env": {
"total": 3.1744423159998405,
"count": 1,
"self": 3.1744423159998405
},
"TrainerController.advance": {
"total": 434.35907263900503,
"count": 18199,
"self": 0.25752206499350905,
"children": {
"env_step": {
"total": 434.1015505740115,
"count": 18199,
"self": 279.54837585100904,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.285715971007,
"count": 18199,
"self": 1.4715578620116503,
"children": {
"TorchPolicy.evaluate": {
"total": 152.81415810899534,
"count": 18199,
"self": 152.81415810899534
}
}
},
"workers": {
"total": 0.2674587519954912,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.06977543701237,
"count": 18199,
"is_parallel": true,
"self": 217.09849080200775,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006383797999887975,
"count": 1,
"is_parallel": true,
"self": 0.00474532100020042,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016384769996875548,
"count": 10,
"is_parallel": true,
"self": 0.0016384769996875548
}
}
},
"UnityEnvironment.step": {
"total": 0.03682277399980194,
"count": 1,
"is_parallel": true,
"self": 0.0006636129996877571,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040041799979917414,
"count": 1,
"is_parallel": true,
"self": 0.00040041799979917414
},
"communicator.exchange": {
"total": 0.03358108700012963,
"count": 1,
"is_parallel": true,
"self": 0.03358108700012963
},
"steps_from_proto": {
"total": 0.0021776560001853795,
"count": 1,
"is_parallel": true,
"self": 0.0004268159998446208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017508400003407587,
"count": 10,
"is_parallel": true,
"self": 0.0017508400003407587
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.97128463500462,
"count": 18198,
"is_parallel": true,
"self": 10.718742818999317,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.28275445200984,
"count": 18198,
"is_parallel": true,
"self": 5.28275445200984
},
"communicator.exchange": {
"total": 170.42113898498565,
"count": 18198,
"is_parallel": true,
"self": 170.42113898498565
},
"steps_from_proto": {
"total": 33.54864837900982,
"count": 18198,
"is_parallel": true,
"self": 6.098861302083151,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.44978707692667,
"count": 181980,
"is_parallel": true,
"self": 27.44978707692667
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012129300012020394,
"count": 1,
"self": 0.00012129300012020394,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 428.98881489999735,
"count": 661478,
"is_parallel": true,
"self": 13.926666802926547,
"children": {
"process_trajectory": {
"total": 237.3105782430705,
"count": 661478,
"is_parallel": true,
"self": 236.8049663560705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5056118869999864,
"count": 4,
"is_parallel": true,
"self": 0.5056118869999864
}
}
},
"_update_policy": {
"total": 177.7515698540003,
"count": 90,
"is_parallel": true,
"self": 50.71552139300684,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.03604846099347,
"count": 4587,
"is_parallel": true,
"self": 127.03604846099347
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08899000499991416,
"count": 1,
"self": 0.0009264489999623038,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08806355599995186,
"count": 1,
"self": 0.08806355599995186
}
}
}
}
}
}
}