PabloCalvo's picture
First Push
374dfb6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9450443387031555,
"min": 0.9450443387031555,
"max": 2.8627214431762695,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9054.4697265625,
"min": 9054.4697265625,
"max": 29317.130859375,
"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": 12.501364707946777,
"min": 0.34601134061813354,
"max": 12.501364707946777,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2437.76611328125,
"min": 67.1261978149414,
"max": 2524.373046875,
"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": 0.07067725803975847,
"min": 0.0639127909471783,
"max": 0.07442955521115686,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28270903215903387,
"min": 0.2556511637887132,
"max": 0.35561739227405803,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22463964860813293,
"min": 0.12683701107744128,
"max": 0.27537026481301174,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8985585944325317,
"min": 0.5073480443097651,
"max": 1.3768513240650588,
"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": 23.931818181818183,
"min": 3.5681818181818183,
"max": 24.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1053.0,
"min": 157.0,
"max": 1373.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.931818181818183,
"min": 3.5681818181818183,
"max": 24.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1053.0,
"min": 157.0,
"max": 1373.0,
"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": "1717508967",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717509428"
},
"total": 460.59715647999997,
"count": 1,
"self": 0.8366786179999508,
"children": {
"run_training.setup": {
"total": 0.06435047200000099,
"count": 1,
"self": 0.06435047200000099
},
"TrainerController.start_learning": {
"total": 459.69612739,
"count": 1,
"self": 0.5734234739987869,
"children": {
"TrainerController._reset_env": {
"total": 3.4833670650000386,
"count": 1,
"self": 3.4833670650000386
},
"TrainerController.advance": {
"total": 455.4937910890012,
"count": 18213,
"self": 0.2629610089996959,
"children": {
"env_step": {
"total": 455.2308300800015,
"count": 18213,
"self": 298.01238906000015,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.9230764960039,
"count": 18213,
"self": 1.504508351001732,
"children": {
"TorchPolicy.evaluate": {
"total": 155.41856814500215,
"count": 18213,
"self": 155.41856814500215
}
}
},
"workers": {
"total": 0.2953645239974776,
"count": 18213,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.32157942001083,
"count": 18213,
"is_parallel": true,
"self": 232.86945690600226,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00611804800007576,
"count": 1,
"is_parallel": true,
"self": 0.00377122500015048,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00234682299992528,
"count": 10,
"is_parallel": true,
"self": 0.00234682299992528
}
}
},
"UnityEnvironment.step": {
"total": 0.03676374200006194,
"count": 1,
"is_parallel": true,
"self": 0.0007036370001287651,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004460059999473742,
"count": 1,
"is_parallel": true,
"self": 0.0004460059999473742
},
"communicator.exchange": {
"total": 0.033644735000052606,
"count": 1,
"is_parallel": true,
"self": 0.033644735000052606
},
"steps_from_proto": {
"total": 0.0019693639999331936,
"count": 1,
"is_parallel": true,
"self": 0.0004106269998374046,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001558737000095789,
"count": 10,
"is_parallel": true,
"self": 0.001558737000095789
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.45212251400858,
"count": 18212,
"is_parallel": true,
"self": 10.24772748799137,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.530895867019694,
"count": 18212,
"is_parallel": true,
"self": 5.530895867019694
},
"communicator.exchange": {
"total": 175.5395393320007,
"count": 18212,
"is_parallel": true,
"self": 175.5395393320007
},
"steps_from_proto": {
"total": 34.13395982699683,
"count": 18212,
"is_parallel": true,
"self": 6.542895158991314,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.591064668005515,
"count": 182120,
"is_parallel": true,
"self": 27.591064668005515
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016003399991859624,
"count": 1,
"self": 0.00016003399991859624,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.0316958839986,
"count": 668237,
"is_parallel": true,
"self": 14.261874887959948,
"children": {
"process_trajectory": {
"total": 250.8500755110383,
"count": 668237,
"is_parallel": true,
"self": 249.9248509140383,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9252245970000104,
"count": 4,
"is_parallel": true,
"self": 0.9252245970000104
}
}
},
"_update_policy": {
"total": 184.91974548500036,
"count": 90,
"is_parallel": true,
"self": 59.26592796600107,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.65381751899929,
"count": 4584,
"is_parallel": true,
"self": 125.65381751899929
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14538572800006477,
"count": 1,
"self": 0.001341992000106984,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1440437359999578,
"count": 1,
"self": 0.1440437359999578
}
}
}
}
}
}
}