CloXD's picture
First Commit
3ab2723
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0134525299072266,
"min": 1.0134525299072266,
"max": 2.859520196914673,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9665.296875,
"min": 9665.296875,
"max": 29284.345703125,
"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": 12.122063636779785,
"min": 0.2649603486061096,
"max": 12.122063636779785,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2363.802490234375,
"min": 51.402305603027344,
"max": 2439.451171875,
"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": 0.07041778358917308,
"min": 0.06216464781883749,
"max": 0.07442687687979938,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28167113435669233,
"min": 0.24865859127534995,
"max": 0.3721343843989969,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21882090922079833,
"min": 0.11942169498469607,
"max": 0.27574792182913016,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8752836368831933,
"min": 0.4776867799387843,
"max": 1.3278912206490836,
"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": 24.34090909090909,
"min": 3.4318181818181817,
"max": 24.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1071.0,
"min": 151.0,
"max": 1338.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.34090909090909,
"min": 3.4318181818181817,
"max": 24.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1071.0,
"min": 151.0,
"max": 1338.0,
"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": "1677763362",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677763898"
},
"total": 536.12563933,
"count": 1,
"self": 0.44252775199993266,
"children": {
"run_training.setup": {
"total": 0.12862663600003543,
"count": 1,
"self": 0.12862663600003543
},
"TrainerController.start_learning": {
"total": 535.554484942,
"count": 1,
"self": 0.7327575969958389,
"children": {
"TrainerController._reset_env": {
"total": 10.657778648999965,
"count": 1,
"self": 10.657778648999965
},
"TrainerController.advance": {
"total": 524.0317630620042,
"count": 18201,
"self": 0.38294407999944724,
"children": {
"env_step": {
"total": 523.6488189820047,
"count": 18201,
"self": 362.4767092170035,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.81917203400485,
"count": 18201,
"self": 1.8403637699996693,
"children": {
"TorchPolicy.evaluate": {
"total": 158.97880826400518,
"count": 18201,
"self": 37.05767942901383,
"children": {
"TorchPolicy.sample_actions": {
"total": 121.92112883499135,
"count": 18201,
"self": 121.92112883499135
}
}
}
}
},
"workers": {
"total": 0.3529377309964161,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 533.5233200529865,
"count": 18201,
"is_parallel": true,
"self": 251.33887308198257,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005361572999959208,
"count": 1,
"is_parallel": true,
"self": 0.00392084799989334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014407250000658678,
"count": 10,
"is_parallel": true,
"self": 0.0014407250000658678
}
}
},
"UnityEnvironment.step": {
"total": 0.048632444000020314,
"count": 1,
"is_parallel": true,
"self": 0.000413423999987117,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003317300000276191,
"count": 1,
"is_parallel": true,
"self": 0.0003317300000276191
},
"communicator.exchange": {
"total": 0.046594282999990355,
"count": 1,
"is_parallel": true,
"self": 0.046594282999990355
},
"steps_from_proto": {
"total": 0.0012930070000152227,
"count": 1,
"is_parallel": true,
"self": 0.00034036899990042,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009526380001148027,
"count": 10,
"is_parallel": true,
"self": 0.0009526380001148027
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 282.1844469710039,
"count": 18200,
"is_parallel": true,
"self": 11.293800544004,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.962811915996383,
"count": 18200,
"is_parallel": true,
"self": 5.962811915996383
},
"communicator.exchange": {
"total": 228.55188868800053,
"count": 18200,
"is_parallel": true,
"self": 228.55188868800053
},
"steps_from_proto": {
"total": 36.37594582300301,
"count": 18200,
"is_parallel": true,
"self": 8.470427434999635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.905518388003372,
"count": 182000,
"is_parallel": true,
"self": 27.905518388003372
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001951430000417531,
"count": 1,
"self": 0.0001951430000417531,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 519.6140277790215,
"count": 478184,
"is_parallel": true,
"self": 12.42498396305291,
"children": {
"process_trajectory": {
"total": 299.20930744396776,
"count": 478184,
"is_parallel": true,
"self": 298.06392474896785,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1453826949999097,
"count": 4,
"is_parallel": true,
"self": 1.1453826949999097
}
}
},
"_update_policy": {
"total": 207.97973637200084,
"count": 90,
"is_parallel": true,
"self": 74.74300711100102,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.23672926099982,
"count": 4587,
"is_parallel": true,
"self": 133.23672926099982
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13199049100001048,
"count": 1,
"self": 0.0009119989999817335,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13107849200002875,
"count": 1,
"self": 0.13107849200002875
}
}
}
}
}
}
}