Qingqing358's picture
First Push
aefb83a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.915922999382019,
"min": 0.9140640497207642,
"max": 2.8625223636627197,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8775.4580078125,
"min": 8775.4580078125,
"max": 29504.017578125,
"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": 12.736831665039062,
"min": 0.3346032202243805,
"max": 12.749961853027344,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2483.68212890625,
"min": 64.91302490234375,
"max": 2600.9921875,
"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": 0.06694910318544191,
"min": 0.06256308278329123,
"max": 0.07373733439366707,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26779641274176763,
"min": 0.25637237942639474,
"max": 0.36276338433683625,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21902884528333064,
"min": 0.1268216840142165,
"max": 0.27943433667807016,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8761153811333225,
"min": 0.507286736056866,
"max": 1.3818660726149874,
"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": 24.65909090909091,
"min": 3.772727272727273,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1085.0,
"min": 166.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.65909090909091,
"min": 3.772727272727273,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1085.0,
"min": 166.0,
"max": 1381.0,
"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": "1729499481",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729500155"
},
"total": 673.9050274319999,
"count": 1,
"self": 0.5913659599999619,
"children": {
"run_training.setup": {
"total": 0.09748053299995263,
"count": 1,
"self": 0.09748053299995263
},
"TrainerController.start_learning": {
"total": 673.216180939,
"count": 1,
"self": 1.0892680090208842,
"children": {
"TrainerController._reset_env": {
"total": 5.915150920999963,
"count": 1,
"self": 5.915150920999963
},
"TrainerController.advance": {
"total": 666.1144427639795,
"count": 18205,
"self": 0.4982623209710937,
"children": {
"env_step": {
"total": 665.6161804430084,
"count": 18205,
"self": 508.64677410997297,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.46678268801713,
"count": 18205,
"self": 2.875270762002401,
"children": {
"TorchPolicy.evaluate": {
"total": 153.59151192601473,
"count": 18205,
"self": 153.59151192601473
}
}
},
"workers": {
"total": 0.5026236450182751,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 670.9503424030075,
"count": 18205,
"is_parallel": true,
"self": 319.88418511001953,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003487521000010929,
"count": 1,
"is_parallel": true,
"self": 0.0011512489999176978,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023362720000932313,
"count": 10,
"is_parallel": true,
"self": 0.0023362720000932313
}
}
},
"UnityEnvironment.step": {
"total": 0.049689851999914936,
"count": 1,
"is_parallel": true,
"self": 0.001021440999807055,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005732050000233357,
"count": 1,
"is_parallel": true,
"self": 0.0005732050000233357
},
"communicator.exchange": {
"total": 0.04523686400000315,
"count": 1,
"is_parallel": true,
"self": 0.04523686400000315
},
"steps_from_proto": {
"total": 0.002858342000081393,
"count": 1,
"is_parallel": true,
"self": 0.0005451210001865547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023132209998948383,
"count": 10,
"is_parallel": true,
"self": 0.0023132209998948383
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 351.066157292988,
"count": 18204,
"is_parallel": true,
"self": 16.97426800698088,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.430919759992435,
"count": 18204,
"is_parallel": true,
"self": 8.430919759992435
},
"communicator.exchange": {
"total": 277.239566818011,
"count": 18204,
"is_parallel": true,
"self": 277.239566818011
},
"steps_from_proto": {
"total": 48.42140270800371,
"count": 18204,
"is_parallel": true,
"self": 9.869169573014688,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.552233134989024,
"count": 182040,
"is_parallel": true,
"self": 38.552233134989024
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00027786399982687726,
"count": 1,
"self": 0.00027786399982687726,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 658.1305632079994,
"count": 904935,
"is_parallel": true,
"self": 21.479706078060417,
"children": {
"process_trajectory": {
"total": 359.5051264549386,
"count": 904935,
"is_parallel": true,
"self": 358.77685849093893,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7282679639996559,
"count": 4,
"is_parallel": true,
"self": 0.7282679639996559
}
}
},
"_update_policy": {
"total": 277.14573067500044,
"count": 90,
"is_parallel": true,
"self": 72.26105028700874,
"children": {
"TorchPPOOptimizer.update": {
"total": 204.8846803879917,
"count": 4587,
"is_parallel": true,
"self": 204.8846803879917
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09704138099982629,
"count": 1,
"self": 0.0015809589997388684,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09546042200008742,
"count": 1,
"self": 0.09546042200008742
}
}
}
}
}
}
}