kuanyk's picture
First Training of snowballtarget
9d110d0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9912649393081665,
"min": 0.9912649393081665,
"max": 2.8727216720581055,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9464.59765625,
"min": 9464.59765625,
"max": 29419.54296875,
"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": 13.20663070678711,
"min": 0.2761761248111725,
"max": 13.20663070678711,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2575.29296875,
"min": 53.57817077636719,
"max": 2687.699462890625,
"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": 0.0667665645088681,
"min": 0.0635640676071703,
"max": 0.07050619868252897,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2670662580354724,
"min": 0.25518983242092835,
"max": 0.3516808653125647,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2236609177700445,
"min": 0.11218014968942633,
"max": 0.2853815340528302,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.894643671080178,
"min": 0.4487205987577053,
"max": 1.4269076702641508,
"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": 25.727272727272727,
"min": 3.1363636363636362,
"max": 26.01818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 138.0,
"max": 1431.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 3.1363636363636362,
"max": 26.01818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 138.0,
"max": 1431.0,
"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": "1677639606",
"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",
"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": "1.22.4",
"end_time_seconds": "1677640261"
},
"total": 654.4348459919997,
"count": 1,
"self": 0.5497577030000684,
"children": {
"run_training.setup": {
"total": 0.14786311399984697,
"count": 1,
"self": 0.14786311399984697
},
"TrainerController.start_learning": {
"total": 653.7372251749998,
"count": 1,
"self": 0.9620252489748964,
"children": {
"TrainerController._reset_env": {
"total": 10.948370990000058,
"count": 1,
"self": 10.948370990000058
},
"TrainerController.advance": {
"total": 641.6921044010251,
"count": 18203,
"self": 0.49249921303908195,
"children": {
"env_step": {
"total": 641.199605187986,
"count": 18203,
"self": 501.7980845749785,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.9417993490024,
"count": 18203,
"self": 2.769701377006186,
"children": {
"TorchPolicy.evaluate": {
"total": 136.1720979719962,
"count": 18203,
"self": 23.665329458944598,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.50676851305161,
"count": 18203,
"self": 112.50676851305161
}
}
}
}
},
"workers": {
"total": 0.45972126400511115,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 651.1792481620087,
"count": 18203,
"is_parallel": true,
"self": 290.16119607198243,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007525506000092719,
"count": 1,
"is_parallel": true,
"self": 0.004676543000186939,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028489629999057797,
"count": 10,
"is_parallel": true,
"self": 0.0028489629999057797
}
}
},
"UnityEnvironment.step": {
"total": 0.0528457260002142,
"count": 1,
"is_parallel": true,
"self": 0.00083383400033199,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003449400001045433,
"count": 1,
"is_parallel": true,
"self": 0.0003449400001045433
},
"communicator.exchange": {
"total": 0.048982065999553015,
"count": 1,
"is_parallel": true,
"self": 0.048982065999553015
},
"steps_from_proto": {
"total": 0.002684886000224651,
"count": 1,
"is_parallel": true,
"self": 0.0006394570000338717,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020454290001907793,
"count": 10,
"is_parallel": true,
"self": 0.0020454290001907793
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 361.01805209002623,
"count": 18202,
"is_parallel": true,
"self": 14.803887535968443,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.08389147102207,
"count": 18202,
"is_parallel": true,
"self": 8.08389147102207
},
"communicator.exchange": {
"total": 290.6873731210162,
"count": 18202,
"is_parallel": true,
"self": 290.6873731210162
},
"steps_from_proto": {
"total": 47.44289996201951,
"count": 18202,
"is_parallel": true,
"self": 11.373208148962476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.069691813057034,
"count": 182020,
"is_parallel": true,
"self": 36.069691813057034
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015062099964779918,
"count": 1,
"self": 0.00015062099964779918,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 635.8520403571092,
"count": 646536,
"is_parallel": true,
"self": 17.482531521436613,
"children": {
"process_trajectory": {
"total": 353.4669670606745,
"count": 646536,
"is_parallel": true,
"self": 352.09686740167444,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3700996590000614,
"count": 4,
"is_parallel": true,
"self": 1.3700996590000614
}
}
},
"_update_policy": {
"total": 264.9025417749981,
"count": 90,
"is_parallel": true,
"self": 89.8152243269933,
"children": {
"TorchPPOOptimizer.update": {
"total": 175.0873174480048,
"count": 4587,
"is_parallel": true,
"self": 175.0873174480048
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13457391400015695,
"count": 1,
"self": 0.0013434710003821237,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13323044299977482,
"count": 1,
"self": 0.13323044299977482
}
}
}
}
}
}
}