ItzikB's picture
First Push
e39deb0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9679388999938965,
"min": 0.9679388999938965,
"max": 2.8604612350463867,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9241.880859375,
"min": 9241.880859375,
"max": 29293.982421875,
"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": 12.787121772766113,
"min": 0.4427122473716736,
"max": 12.854084968566895,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.48876953125,
"min": 85.88617706298828,
"max": 2622.2333984375,
"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": 0.06407527561764166,
"min": 0.06372899367445772,
"max": 0.07618835803170405,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25630110247056664,
"min": 0.2549159746978309,
"max": 0.3672758052205466,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23865057053227054,
"min": 0.13903381494923917,
"max": 0.301177087952109,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9546022821290822,
"min": 0.5561352597969567,
"max": 1.505885439760545,
"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": 24.613636363636363,
"min": 3.772727272727273,
"max": 25.5,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1083.0,
"min": 166.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.613636363636363,
"min": 3.772727272727273,
"max": 25.5,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1083.0,
"min": 166.0,
"max": 1387.0,
"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": "1674376242",
"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.yaml --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": "1.21.6",
"end_time_seconds": "1674376649"
},
"total": 407.443344341,
"count": 1,
"self": 0.3941573349999885,
"children": {
"run_training.setup": {
"total": 0.11150547700003699,
"count": 1,
"self": 0.11150547700003699
},
"TrainerController.start_learning": {
"total": 406.937681529,
"count": 1,
"self": 0.5303648019996672,
"children": {
"TrainerController._reset_env": {
"total": 9.939942617000042,
"count": 1,
"self": 9.939942617000042
},
"TrainerController.advance": {
"total": 396.3488576040003,
"count": 18202,
"self": 0.2640785930023526,
"children": {
"env_step": {
"total": 396.0847790109979,
"count": 18202,
"self": 257.4854830359901,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.34090177700057,
"count": 18202,
"self": 1.3456829079991053,
"children": {
"TorchPolicy.evaluate": {
"total": 136.99521886900146,
"count": 18202,
"self": 30.814837024000497,
"children": {
"TorchPolicy.sample_actions": {
"total": 106.18038184500097,
"count": 18202,
"self": 106.18038184500097
}
}
}
}
},
"workers": {
"total": 0.2583941980072382,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 405.7760962490015,
"count": 18202,
"is_parallel": true,
"self": 195.47030880899848,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011352669000018523,
"count": 1,
"is_parallel": true,
"self": 0.0059727419999831,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005379927000035423,
"count": 10,
"is_parallel": true,
"self": 0.005379927000035423
}
}
},
"UnityEnvironment.step": {
"total": 0.0317954789999817,
"count": 1,
"is_parallel": true,
"self": 0.0006224070000371285,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003094429999919157,
"count": 1,
"is_parallel": true,
"self": 0.0003094429999919157
},
"communicator.exchange": {
"total": 0.02908321799998248,
"count": 1,
"is_parallel": true,
"self": 0.02908321799998248
},
"steps_from_proto": {
"total": 0.0017804109999701723,
"count": 1,
"is_parallel": true,
"self": 0.00040570300006947946,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013747079999006928,
"count": 10,
"is_parallel": true,
"self": 0.0013747079999006928
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.30578744000303,
"count": 18201,
"is_parallel": true,
"self": 7.987929163995261,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.614836236011627,
"count": 18201,
"is_parallel": true,
"self": 4.614836236011627
},
"communicator.exchange": {
"total": 169.59551448899714,
"count": 18201,
"is_parallel": true,
"self": 169.59551448899714
},
"steps_from_proto": {
"total": 28.107507550999003,
"count": 18201,
"is_parallel": true,
"self": 6.048813244993028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.058694306005975,
"count": 182010,
"is_parallel": true,
"self": 22.058694306005975
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.727999998976884e-05,
"count": 1,
"self": 4.727999998976884e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 393.61284466097385,
"count": 328434,
"is_parallel": true,
"self": 8.33381758198118,
"children": {
"process_trajectory": {
"total": 226.69194477199215,
"count": 328434,
"is_parallel": true,
"self": 225.97620428999215,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7157404820000011,
"count": 4,
"is_parallel": true,
"self": 0.7157404820000011
}
}
},
"_update_policy": {
"total": 158.58708230700051,
"count": 90,
"is_parallel": true,
"self": 38.49240441799901,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.0946778890015,
"count": 4587,
"is_parallel": true,
"self": 120.0946778890015
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11846922600000198,
"count": 1,
"self": 0.0008267490001117039,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11764247699989028,
"count": 1,
"self": 0.11764247699989028
}
}
}
}
}
}
}