rlucasz93's picture
First Push
8dfdf54
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9601219296455383,
"min": 0.9601219296455383,
"max": 2.8706204891204834,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9156.6826171875,
"min": 9156.6826171875,
"max": 29429.6015625,
"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": 12.957647323608398,
"min": 0.41408205032348633,
"max": 12.957647323608398,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2526.7412109375,
"min": 80.33191680908203,
"max": 2634.365966796875,
"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": 0.06738375161997587,
"min": 0.06060202732538421,
"max": 0.07430245389068481,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26953500647990347,
"min": 0.2615402774748623,
"max": 0.35590179001355504,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19283830564396054,
"min": 0.12379507351365379,
"max": 0.2856262272917757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7713532225758422,
"min": 0.49518029405461517,
"max": 1.361031354642382,
"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": 25.5,
"min": 3.4545454545454546,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 152.0,
"max": 1403.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.4545454545454546,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 152.0,
"max": 1403.0,
"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": "1681236300",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681236800"
},
"total": 500.301858668,
"count": 1,
"self": 0.434807204000208,
"children": {
"run_training.setup": {
"total": 0.12342065799998636,
"count": 1,
"self": 0.12342065799998636
},
"TrainerController.start_learning": {
"total": 499.7436308059998,
"count": 1,
"self": 0.6774032300170347,
"children": {
"TrainerController._reset_env": {
"total": 4.7778129400001035,
"count": 1,
"self": 4.7778129400001035
},
"TrainerController.advance": {
"total": 494.13127622698266,
"count": 18200,
"self": 0.3778828280176185,
"children": {
"env_step": {
"total": 493.75339339896504,
"count": 18200,
"self": 361.82529629093415,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.59758312101098,
"count": 18200,
"self": 1.8861330920390174,
"children": {
"TorchPolicy.evaluate": {
"total": 129.71145002897197,
"count": 18200,
"self": 129.71145002897197
}
}
},
"workers": {
"total": 0.33051398701991275,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 498.008282059011,
"count": 18200,
"is_parallel": true,
"self": 229.1409500350244,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005965165999896271,
"count": 1,
"is_parallel": true,
"self": 0.004413792000150352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015513739997459197,
"count": 10,
"is_parallel": true,
"self": 0.0015513739997459197
}
}
},
"UnityEnvironment.step": {
"total": 0.11640852200002882,
"count": 1,
"is_parallel": true,
"self": 0.0021336670001801394,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004363860000466957,
"count": 1,
"is_parallel": true,
"self": 0.0004363860000466957
},
"communicator.exchange": {
"total": 0.11183039999991706,
"count": 1,
"is_parallel": true,
"self": 0.11183039999991706
},
"steps_from_proto": {
"total": 0.0020080689998849266,
"count": 1,
"is_parallel": true,
"self": 0.0004161950000707293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015918739998141973,
"count": 10,
"is_parallel": true,
"self": 0.0015918739998141973
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 268.8673320239866,
"count": 18199,
"is_parallel": true,
"self": 10.734342142987089,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.94209206700566,
"count": 18199,
"is_parallel": true,
"self": 5.94209206700566
},
"communicator.exchange": {
"total": 216.73587892301703,
"count": 18199,
"is_parallel": true,
"self": 216.73587892301703
},
"steps_from_proto": {
"total": 35.45501889097682,
"count": 18199,
"is_parallel": true,
"self": 7.382982825892896,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.07203606508392,
"count": 181990,
"is_parallel": true,
"self": 28.07203606508392
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.973000002588378e-05,
"count": 1,
"self": 3.973000002588378e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 490.24954619301116,
"count": 456587,
"is_parallel": true,
"self": 11.239387261036427,
"children": {
"process_trajectory": {
"total": 274.3879328189728,
"count": 456587,
"is_parallel": true,
"self": 273.5867561839725,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8011766350002745,
"count": 4,
"is_parallel": true,
"self": 0.8011766350002745
}
}
},
"_update_policy": {
"total": 204.62222611300194,
"count": 90,
"is_parallel": true,
"self": 73.37153351201641,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.25069260098553,
"count": 4587,
"is_parallel": true,
"self": 131.25069260098553
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15709867900000063,
"count": 1,
"self": 0.0009818519999953423,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1561168270000053,
"count": 1,
"self": 0.1561168270000053
}
}
}
}
}
}
}