AnnaMats's picture
First Push
f5921c0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8162743449211121,
"min": 0.8162743449211121,
"max": 2.875807046890259,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7820.724609375,
"min": 7820.724609375,
"max": 29419.505859375,
"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": 12.68019962310791,
"min": 0.29457831382751465,
"max": 12.68019962310791,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2472.638916015625,
"min": 57.148193359375,
"max": 2568.5439453125,
"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": 0.06944737386063435,
"min": 0.06157914983524082,
"max": 0.07616594778430905,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2777894954425374,
"min": 0.2508892385290785,
"max": 0.3808297389215452,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21613662755664656,
"min": 0.12251877194320711,
"max": 0.2878585106601902,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8645465102265862,
"min": 0.49007508777282843,
"max": 1.439292553300951,
"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": 25.272727272727273,
"min": 3.3636363636363638,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 148.0,
"max": 1359.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.3636363636363638,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 148.0,
"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": "1692692270",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692692758"
},
"total": 487.73212043600006,
"count": 1,
"self": 0.839610132000189,
"children": {
"run_training.setup": {
"total": 0.053195195999933276,
"count": 1,
"self": 0.053195195999933276
},
"TrainerController.start_learning": {
"total": 486.83931510799994,
"count": 1,
"self": 0.5761168419959404,
"children": {
"TrainerController._reset_env": {
"total": 4.222338270000023,
"count": 1,
"self": 4.222338270000023
},
"TrainerController.advance": {
"total": 481.813695852004,
"count": 18217,
"self": 0.28669830200203705,
"children": {
"env_step": {
"total": 481.52699755000197,
"count": 18217,
"self": 350.19512296499533,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.0403110249987,
"count": 18217,
"self": 1.7242598529898032,
"children": {
"TorchPolicy.evaluate": {
"total": 129.31605117200888,
"count": 18217,
"self": 129.31605117200888
}
}
},
"workers": {
"total": 0.29156356000794403,
"count": 18217,
"self": 0.0,
"children": {
"worker_root": {
"total": 485.08967289100656,
"count": 18217,
"is_parallel": true,
"self": 229.2185918289964,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006142745000033756,
"count": 1,
"is_parallel": true,
"self": 0.0045728070001587184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015699379998750373,
"count": 10,
"is_parallel": true,
"self": 0.0015699379998750373
}
}
},
"UnityEnvironment.step": {
"total": 0.047716454000010344,
"count": 1,
"is_parallel": true,
"self": 0.0005103820000158521,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041655199993329006,
"count": 1,
"is_parallel": true,
"self": 0.00041655199993329006
},
"communicator.exchange": {
"total": 0.04490693299999293,
"count": 1,
"is_parallel": true,
"self": 0.04490693299999293
},
"steps_from_proto": {
"total": 0.0018825870000682698,
"count": 1,
"is_parallel": true,
"self": 0.0005038890001287655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013786979999395044,
"count": 10,
"is_parallel": true,
"self": 0.0013786979999395044
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.87108106201015,
"count": 18216,
"is_parallel": true,
"self": 10.627065130008532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.377133357987418,
"count": 18216,
"is_parallel": true,
"self": 5.377133357987418
},
"communicator.exchange": {
"total": 203.10781073800388,
"count": 18216,
"is_parallel": true,
"self": 203.10781073800388
},
"steps_from_proto": {
"total": 36.75907183601032,
"count": 18216,
"is_parallel": true,
"self": 6.711326716018675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.047745119991646,
"count": 182160,
"is_parallel": true,
"self": 30.047745119991646
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001531959999283572,
"count": 1,
"self": 0.0001531959999283572,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 477.99172277095806,
"count": 447321,
"is_parallel": true,
"self": 10.2772171130066,
"children": {
"process_trajectory": {
"total": 262.156770799952,
"count": 447321,
"is_parallel": true,
"self": 260.62123192095214,
"children": {
"RLTrainer._checkpoint": {
"total": 1.535538878999887,
"count": 4,
"is_parallel": true,
"self": 1.535538878999887
}
}
},
"_update_policy": {
"total": 205.55773485799944,
"count": 90,
"is_parallel": true,
"self": 81.38878695998994,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.16894789800949,
"count": 4587,
"is_parallel": true,
"self": 124.16894789800949
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22701094800004284,
"count": 1,
"self": 0.001147168999978021,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22586377900006482,
"count": 1,
"self": 0.22586377900006482
}
}
}
}
}
}
}