PeterDerLustige's picture
First training of SnowballTarget
e86ba1d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.127535104751587,
"min": 1.127535104751587,
"max": 2.8720741271972656,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10765.705078125,
"min": 10765.705078125,
"max": 29412.91015625,
"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": 11.910781860351562,
"min": 0.2928186058998108,
"max": 11.910781860351562,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2322.6025390625,
"min": 56.80680847167969,
"max": 2418.7998046875,
"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": 0.06890729000930579,
"min": 0.061872251336585485,
"max": 0.07744017709356901,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27562916003722315,
"min": 0.24748900534634194,
"max": 0.3504018984465659,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20303611603437688,
"min": 0.09445011897204333,
"max": 0.2977411981891183,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8121444641375075,
"min": 0.37780047588817334,
"max": 1.4887059909455915,
"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": 23.40909090909091,
"min": 3.1818181818181817,
"max": 23.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1030.0,
"min": 140.0,
"max": 1285.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.40909090909091,
"min": 3.1818181818181817,
"max": 23.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1030.0,
"min": 140.0,
"max": 1285.0,
"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": "1675324816",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675325239"
},
"total": 423.6284028980001,
"count": 1,
"self": 0.38389395100011825,
"children": {
"run_training.setup": {
"total": 0.10219318700001168,
"count": 1,
"self": 0.10219318700001168
},
"TrainerController.start_learning": {
"total": 423.14231576,
"count": 1,
"self": 0.577193034014158,
"children": {
"TrainerController._reset_env": {
"total": 5.889234203000001,
"count": 1,
"self": 5.889234203000001
},
"TrainerController.advance": {
"total": 416.5600955289856,
"count": 18201,
"self": 0.27498485000342043,
"children": {
"env_step": {
"total": 416.28511067898216,
"count": 18201,
"self": 273.28118099998153,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.73025177200714,
"count": 18201,
"self": 1.5273322710178263,
"children": {
"TorchPolicy.evaluate": {
"total": 141.2029195009893,
"count": 18201,
"self": 31.528145436984573,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.67477406400474,
"count": 18201,
"self": 109.67477406400474
}
}
}
}
},
"workers": {
"total": 0.27367790699349825,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 421.9041437449995,
"count": 18201,
"is_parallel": true,
"self": 200.69380671299803,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020159219999413835,
"count": 1,
"is_parallel": true,
"self": 0.0007278280002083193,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012880939997330643,
"count": 10,
"is_parallel": true,
"self": 0.0012880939997330643
}
}
},
"UnityEnvironment.step": {
"total": 0.046446991999914644,
"count": 1,
"is_parallel": true,
"self": 0.0003452149999247922,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003774760000396782,
"count": 1,
"is_parallel": true,
"self": 0.0003774760000396782
},
"communicator.exchange": {
"total": 0.043952640000043175,
"count": 1,
"is_parallel": true,
"self": 0.043952640000043175
},
"steps_from_proto": {
"total": 0.0017716609999069988,
"count": 1,
"is_parallel": true,
"self": 0.0004195209999124927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001352139999994506,
"count": 10,
"is_parallel": true,
"self": 0.001352139999994506
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.21033703200146,
"count": 18200,
"is_parallel": true,
"self": 8.355377439016479,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.867982146976374,
"count": 18200,
"is_parallel": true,
"self": 4.867982146976374
},
"communicator.exchange": {
"total": 178.66840780699943,
"count": 18200,
"is_parallel": true,
"self": 178.66840780699943
},
"steps_from_proto": {
"total": 29.318569639009183,
"count": 18200,
"is_parallel": true,
"self": 6.352252358022611,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.966317280986573,
"count": 182000,
"is_parallel": true,
"self": 22.966317280986573
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.870100019616075e-05,
"count": 1,
"self": 4.870100019616075e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 413.74784457992666,
"count": 346852,
"is_parallel": true,
"self": 8.966511536887538,
"children": {
"process_trajectory": {
"total": 237.73436392903932,
"count": 346852,
"is_parallel": true,
"self": 236.95927966003921,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7750842690001036,
"count": 4,
"is_parallel": true,
"self": 0.7750842690001036
}
}
},
"_update_policy": {
"total": 167.0469691139998,
"count": 90,
"is_parallel": true,
"self": 40.982788115998346,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.06418099800146,
"count": 4587,
"is_parallel": true,
"self": 126.06418099800146
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1157442930000343,
"count": 1,
"self": 0.001084310999885929,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11465998200014837,
"count": 1,
"self": 0.11465998200014837
}
}
}
}
}
}
}