pasto2003's picture
First Push
70a494c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9948941469192505,
"min": 0.9948941469192505,
"max": 2.8633999824523926,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9532.0810546875,
"min": 9532.0810546875,
"max": 29387.07421875,
"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": 11.266270637512207,
"min": 0.4365639090538025,
"max": 11.266270637512207,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2196.9228515625,
"min": 84.69339752197266,
"max": 2259.160888671875,
"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": 0.0663770284615263,
"min": 0.060311190069293,
"max": 0.0798918596703979,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2655081138461052,
"min": 0.241244760277172,
"max": 0.3994592983519895,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19670111634859852,
"min": 0.14745640844293853,
"max": 0.2821072756075392,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7868044653943941,
"min": 0.5898256337717541,
"max": 1.4105363780376958,
"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": 22.068181818181817,
"min": 3.840909090909091,
"max": 22.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 971.0,
"min": 169.0,
"max": 1208.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.068181818181817,
"min": 3.840909090909091,
"max": 22.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 971.0,
"min": 169.0,
"max": 1208.0,
"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": "1692522110",
"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",
"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": "1692522521"
},
"total": 410.7364247359999,
"count": 1,
"self": 0.32591469899989534,
"children": {
"run_training.setup": {
"total": 0.044270128000107434,
"count": 1,
"self": 0.044270128000107434
},
"TrainerController.start_learning": {
"total": 410.3662399089999,
"count": 1,
"self": 0.5919243740036109,
"children": {
"TrainerController._reset_env": {
"total": 4.353206150000005,
"count": 1,
"self": 4.353206150000005
},
"TrainerController.advance": {
"total": 405.27659368399645,
"count": 18205,
"self": 0.2745596249974369,
"children": {
"env_step": {
"total": 405.002034058999,
"count": 18205,
"self": 296.66852821699604,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.05348770699425,
"count": 18205,
"self": 1.4933786900051018,
"children": {
"TorchPolicy.evaluate": {
"total": 106.56010901698914,
"count": 18205,
"self": 106.56010901698914
}
}
},
"workers": {
"total": 0.2800181350087314,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 409.48660447301745,
"count": 18205,
"is_parallel": true,
"self": 203.48609273001352,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002236884000012651,
"count": 1,
"is_parallel": true,
"self": 0.0006694889996197162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015673950003929349,
"count": 10,
"is_parallel": true,
"self": 0.0015673950003929349
}
}
},
"UnityEnvironment.step": {
"total": 0.029550972999913938,
"count": 1,
"is_parallel": true,
"self": 0.0004752839997763658,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005321109999840701,
"count": 1,
"is_parallel": true,
"self": 0.0005321109999840701
},
"communicator.exchange": {
"total": 0.026944642999978896,
"count": 1,
"is_parallel": true,
"self": 0.026944642999978896
},
"steps_from_proto": {
"total": 0.001598935000174606,
"count": 1,
"is_parallel": true,
"self": 0.00031524800033366773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012836869998409384,
"count": 10,
"is_parallel": true,
"self": 0.0012836869998409384
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.00051174300393,
"count": 18204,
"is_parallel": true,
"self": 8.462674388020787,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.564233068009344,
"count": 18204,
"is_parallel": true,
"self": 4.564233068009344
},
"communicator.exchange": {
"total": 164.75448669999082,
"count": 18204,
"is_parallel": true,
"self": 164.75448669999082
},
"steps_from_proto": {
"total": 28.219117586982975,
"count": 18204,
"is_parallel": true,
"self": 5.196348701991155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.02276888499182,
"count": 182040,
"is_parallel": true,
"self": 23.02276888499182
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016170499975487473,
"count": 1,
"self": 0.00016170499975487473,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 404.1953175540675,
"count": 233426,
"is_parallel": true,
"self": 4.055409282077335,
"children": {
"process_trajectory": {
"total": 225.0420796559922,
"count": 233426,
"is_parallel": true,
"self": 224.22989206299212,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8121875930000897,
"count": 4,
"is_parallel": true,
"self": 0.8121875930000897
}
}
},
"_update_policy": {
"total": 175.09782861599797,
"count": 90,
"is_parallel": true,
"self": 48.346942966989445,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.75088564900852,
"count": 4587,
"is_parallel": true,
"self": 126.75088564900852
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1443539960000635,
"count": 1,
"self": 0.0009496170000602433,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14340437900000325,
"count": 1,
"self": 0.14340437900000325
}
}
}
}
}
}
}