{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9383033514022827,
"min": 0.9383033514022827,
"max": 2.8698911666870117,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9020.8486328125,
"min": 9020.8486328125,
"max": 29422.125,
"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": 12.434627532958984,
"min": 0.504234254360199,
"max": 12.434627532958984,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2424.75244140625,
"min": 97.82144165039062,
"max": 2490.06396484375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0713021666731448,
"min": 0.061719359818893926,
"max": 0.0745307987972945,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2852086666925792,
"min": 0.2468774392755757,
"max": 0.3598320501649355,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21915413285879526,
"min": 0.13850963941556127,
"max": 0.2970841063003914,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.876616531435181,
"min": 0.5540385576622451,
"max": 1.485420531501957,
"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": 24.113636363636363,
"min": 3.522727272727273,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1061.0,
"min": 155.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.113636363636363,
"min": 3.522727272727273,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1061.0,
"min": 155.0,
"max": 1395.0,
"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": "1692805031",
"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": "1692805557"
},
"total": 525.699682636,
"count": 1,
"self": 0.8396688959996936,
"children": {
"run_training.setup": {
"total": 0.04572707400006948,
"count": 1,
"self": 0.04572707400006948
},
"TrainerController.start_learning": {
"total": 524.8142866660003,
"count": 1,
"self": 0.6947426310109677,
"children": {
"TrainerController._reset_env": {
"total": 4.426339631000019,
"count": 1,
"self": 4.426339631000019
},
"TrainerController.advance": {
"total": 519.4422412329898,
"count": 18237,
"self": 0.3492610609825988,
"children": {
"env_step": {
"total": 519.0929801720072,
"count": 18237,
"self": 379.6912964999701,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.04771234801956,
"count": 18237,
"self": 2.0000493520217333,
"children": {
"TorchPolicy.evaluate": {
"total": 137.04766299599783,
"count": 18237,
"self": 137.04766299599783
}
}
},
"workers": {
"total": 0.3539713240174933,
"count": 18237,
"self": 0.0,
"children": {
"worker_root": {
"total": 522.7973419689929,
"count": 18237,
"is_parallel": true,
"self": 240.23493594800038,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006303964999915479,
"count": 1,
"is_parallel": true,
"self": 0.004640059999928781,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016639049999866984,
"count": 10,
"is_parallel": true,
"self": 0.0016639049999866984
}
}
},
"UnityEnvironment.step": {
"total": 0.04016306900007294,
"count": 1,
"is_parallel": true,
"self": 0.00069679700004599,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032055800011221436,
"count": 1,
"is_parallel": true,
"self": 0.00032055800011221436
},
"communicator.exchange": {
"total": 0.03668686099990737,
"count": 1,
"is_parallel": true,
"self": 0.03668686099990737
},
"steps_from_proto": {
"total": 0.002458853000007366,
"count": 1,
"is_parallel": true,
"self": 0.0004285200002414058,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020303329997659603,
"count": 10,
"is_parallel": true,
"self": 0.0020303329997659603
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 282.5624060209925,
"count": 18236,
"is_parallel": true,
"self": 11.740250928976593,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.716409527985206,
"count": 18236,
"is_parallel": true,
"self": 5.716409527985206
},
"communicator.exchange": {
"total": 224.70281856602605,
"count": 18236,
"is_parallel": true,
"self": 224.70281856602605
},
"steps_from_proto": {
"total": 40.40292699800466,
"count": 18236,
"is_parallel": true,
"self": 7.704708559969504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.698218438035155,
"count": 182360,
"is_parallel": true,
"self": 32.698218438035155
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015173699966908316,
"count": 1,
"self": 0.00015173699966908316,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 515.3783015951217,
"count": 488339,
"is_parallel": true,
"self": 11.112266228943326,
"children": {
"process_trajectory": {
"total": 283.8378017521768,
"count": 488339,
"is_parallel": true,
"self": 281.8020598571761,
"children": {
"RLTrainer._checkpoint": {
"total": 2.035741895000683,
"count": 4,
"is_parallel": true,
"self": 2.035741895000683
}
}
},
"_update_policy": {
"total": 220.42823361400156,
"count": 90,
"is_parallel": true,
"self": 84.1904150730063,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.23781854099525,
"count": 4584,
"is_parallel": true,
"self": 136.23781854099525
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.25081143399984285,
"count": 1,
"self": 0.001292740999815578,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24951869300002727,
"count": 1,
"self": 0.24951869300002727
}
}
}
}
}
}
}