amostof's picture
First Push
a94dbf5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9713525176048279,
"min": 0.9713525176048279,
"max": 2.847320079803467,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9231.734375,
"min": 9231.734375,
"max": 29065.443359375,
"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": 12.130517959594727,
"min": 0.4949299395084381,
"max": 12.130517959594727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2365.450927734375,
"min": 96.01641082763672,
"max": 2454.65966796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06603406768693937,
"min": 0.06138692028695254,
"max": 0.0768038016849816,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2641362707477575,
"min": 0.26005337394057204,
"max": 0.3650562349357642,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21167619069855587,
"min": 0.12849372953596508,
"max": 0.2814628713417287,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8467047627942235,
"min": 0.5139749181438603,
"max": 1.400860058618527,
"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.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.Environment.CumulativeReward.mean": {
"value": 24.477272727272727,
"min": 3.5,
"max": 24.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1077.0,
"min": 154.0,
"max": 1293.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.477272727272727,
"min": 3.5,
"max": 24.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1077.0,
"min": 154.0,
"max": 1293.0,
"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": "1739586891",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739587436"
},
"total": 544.7277037450001,
"count": 1,
"self": 0.9157703580000316,
"children": {
"run_training.setup": {
"total": 0.0279713280000351,
"count": 1,
"self": 0.0279713280000351
},
"TrainerController.start_learning": {
"total": 543.783962059,
"count": 1,
"self": 0.580072848998384,
"children": {
"TrainerController._reset_env": {
"total": 3.4380395670000325,
"count": 1,
"self": 3.4380395670000325
},
"TrainerController.advance": {
"total": 539.6484965870019,
"count": 18192,
"self": 0.6053773289985429,
"children": {
"env_step": {
"total": 379.65509734199827,
"count": 18192,
"self": 324.39994153800774,
"children": {
"SubprocessEnvManager._take_step": {
"total": 54.887493308991395,
"count": 18192,
"self": 1.8783055499886245,
"children": {
"TorchPolicy.evaluate": {
"total": 53.00918775900277,
"count": 18192,
"self": 53.00918775900277
}
}
},
"workers": {
"total": 0.36766249499913783,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 541.6462912149962,
"count": 18192,
"is_parallel": true,
"self": 261.51978175100675,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006092515000034382,
"count": 1,
"is_parallel": true,
"self": 0.004160422999802904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019320920002314779,
"count": 10,
"is_parallel": true,
"self": 0.0019320920002314779
}
}
},
"UnityEnvironment.step": {
"total": 0.08921080999999731,
"count": 1,
"is_parallel": true,
"self": 0.0007585949999793229,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043222899995498665,
"count": 1,
"is_parallel": true,
"self": 0.00043222899995498665
},
"communicator.exchange": {
"total": 0.07728615800004945,
"count": 1,
"is_parallel": true,
"self": 0.07728615800004945
},
"steps_from_proto": {
"total": 0.010733828000013546,
"count": 1,
"is_parallel": true,
"self": 0.000490289000026678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.010243538999986868,
"count": 10,
"is_parallel": true,
"self": 0.010243538999986868
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 280.1265094639894,
"count": 18191,
"is_parallel": true,
"self": 13.885623701979398,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.423824334014284,
"count": 18191,
"is_parallel": true,
"self": 7.423824334014284
},
"communicator.exchange": {
"total": 218.05660357499397,
"count": 18191,
"is_parallel": true,
"self": 218.05660357499397
},
"steps_from_proto": {
"total": 40.76045785300175,
"count": 18191,
"is_parallel": true,
"self": 7.803934224992702,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.95652362800905,
"count": 181910,
"is_parallel": true,
"self": 32.95652362800905
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 159.38802191600502,
"count": 18192,
"self": 0.8006990879983391,
"children": {
"process_trajectory": {
"total": 30.3013711770069,
"count": 18192,
"self": 29.850016352006946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45135482499995305,
"count": 4,
"self": 0.45135482499995305
}
}
},
"_update_policy": {
"total": 128.28595165099978,
"count": 90,
"self": 49.16948665199965,
"children": {
"TorchPPOOptimizer.update": {
"total": 79.11646499900013,
"count": 4587,
"self": 79.11646499900013
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4509998891298892e-06,
"count": 1,
"self": 1.4509998891298892e-06
},
"TrainerController._save_models": {
"total": 0.11735160499983976,
"count": 1,
"self": 0.0015491139997720893,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11580249100006768,
"count": 1,
"self": 0.11580249100006768
}
}
}
}
}
}
}