AndrewL088's picture
First Push 20230903
b70a6de
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1552319526672363,
"min": 1.1552319526672363,
"max": 2.872316360473633,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11042.8623046875,
"min": 11042.8623046875,
"max": 29446.98828125,
"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": 6.402102947235107,
"min": 0.2349742352962494,
"max": 6.46518611907959,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1248.4100341796875,
"min": 45.58500289916992,
"max": 1318.89794921875,
"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": 0.09791296802822591,
"min": 0.09303315661127273,
"max": 0.10604800490235741,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.39165187211290364,
"min": 0.37213262644509093,
"max": 0.5154216504078624,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17685941331745947,
"min": 0.10634225930042446,
"max": 0.2128629582331461,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7074376532698379,
"min": 0.42536903720169783,
"max": 1.0641498260638294,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382799997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10134700000000002,
"min": 0.10134700000000002,
"max": 0.148647,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4053880000000001,
"min": 0.4053880000000001,
"max": 0.7308600000000001,
"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": 3.4545454545454546,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1083.0,
"min": 152.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.613636363636363,
"min": 3.4545454545454546,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1083.0,
"min": 152.0,
"max": 1396.0,
"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": "1693712204",
"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 --force",
"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": "1693712877"
},
"total": 673.325666313,
"count": 1,
"self": 0.7026468480003132,
"children": {
"run_training.setup": {
"total": 0.040508010999928956,
"count": 1,
"self": 0.040508010999928956
},
"TrainerController.start_learning": {
"total": 672.5825114539998,
"count": 1,
"self": 0.6361034939945966,
"children": {
"TrainerController._reset_env": {
"total": 3.9397197879998203,
"count": 1,
"self": 3.9397197879998203
},
"TrainerController.advance": {
"total": 667.6996789210052,
"count": 18222,
"self": 0.3205168710092039,
"children": {
"env_step": {
"total": 667.379162049996,
"count": 18222,
"self": 534.7089586350535,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.35376623499496,
"count": 18222,
"self": 1.851569437942544,
"children": {
"TorchPolicy.evaluate": {
"total": 130.50219679705242,
"count": 18222,
"self": 130.50219679705242
}
}
},
"workers": {
"total": 0.31643717994757026,
"count": 18222,
"self": 0.0,
"children": {
"worker_root": {
"total": 670.617412964978,
"count": 18222,
"is_parallel": true,
"self": 391.44799577496815,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021178430001782544,
"count": 1,
"is_parallel": true,
"self": 0.0006015479993948247,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015162950007834297,
"count": 10,
"is_parallel": true,
"self": 0.0015162950007834297
}
}
},
"UnityEnvironment.step": {
"total": 0.05535302899988892,
"count": 1,
"is_parallel": true,
"self": 0.000711471000158781,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034696300008363323,
"count": 1,
"is_parallel": true,
"self": 0.00034696300008363323
},
"communicator.exchange": {
"total": 0.05176436500005366,
"count": 1,
"is_parallel": true,
"self": 0.05176436500005366
},
"steps_from_proto": {
"total": 0.002530229999592848,
"count": 1,
"is_parallel": true,
"self": 0.0005589999987023475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019712300008905004,
"count": 10,
"is_parallel": true,
"self": 0.0019712300008905004
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 279.1694171900099,
"count": 18221,
"is_parallel": true,
"self": 11.73278946598839,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.058035436011778,
"count": 18221,
"is_parallel": true,
"self": 6.058035436011778
},
"communicator.exchange": {
"total": 219.4567923779996,
"count": 18221,
"is_parallel": true,
"self": 219.4567923779996
},
"steps_from_proto": {
"total": 41.92179991001012,
"count": 18221,
"is_parallel": true,
"self": 7.854247349979687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.067552560030435,
"count": 182210,
"is_parallel": true,
"self": 34.067552560030435
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014054100029170513,
"count": 1,
"self": 0.00014054100029170513,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 663.4952208280688,
"count": 469931,
"is_parallel": true,
"self": 11.36439237806053,
"children": {
"process_trajectory": {
"total": 284.41271324400986,
"count": 469931,
"is_parallel": true,
"self": 282.4649860440095,
"children": {
"RLTrainer._checkpoint": {
"total": 1.9477272000003722,
"count": 4,
"is_parallel": true,
"self": 1.9477272000003722
}
}
},
"_update_policy": {
"total": 367.7181152059984,
"count": 90,
"is_parallel": true,
"self": 113.55896686299684,
"children": {
"TorchPPOOptimizer.update": {
"total": 254.15914834300156,
"count": 15295,
"is_parallel": true,
"self": 254.15914834300156
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.3068687099998897,
"count": 1,
"self": 0.003447293000135687,
"children": {
"RLTrainer._checkpoint": {
"total": 0.303421416999754,
"count": 1,
"self": 0.303421416999754
}
}
}
}
}
}
}