Bashiro's picture
First Push
d50b411
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9657623767852783,
"min": 0.9657623767852783,
"max": 2.8585739135742188,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9231.72265625,
"min": 9231.72265625,
"max": 29274.65625,
"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": 12.638641357421875,
"min": 0.34596920013427734,
"max": 12.670578002929688,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2464.53515625,
"min": 67.11802673339844,
"max": 2584.7978515625,
"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": 0.06261620628270868,
"min": 0.06250152897201569,
"max": 0.07648614158068656,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25046482513083473,
"min": 0.25000611588806276,
"max": 0.3824307079034328,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21202143749185637,
"min": 0.11723936385219441,
"max": 0.29439032815542876,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8480857499674255,
"min": 0.46895745540877765,
"max": 1.4401762871181265,
"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": 24.363636363636363,
"min": 3.5681818181818183,
"max": 25.490909090909092,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1072.0,
"min": 157.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.363636363636363,
"min": 3.5681818181818183,
"max": 25.490909090909092,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1072.0,
"min": 157.0,
"max": 1402.0,
"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": "1703502595",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703503046"
},
"total": 450.9166608140001,
"count": 1,
"self": 0.44464456500008964,
"children": {
"run_training.setup": {
"total": 0.053944705000049,
"count": 1,
"self": 0.053944705000049
},
"TrainerController.start_learning": {
"total": 450.418071544,
"count": 1,
"self": 0.5902470600015022,
"children": {
"TrainerController._reset_env": {
"total": 3.264664547000166,
"count": 1,
"self": 3.264664547000166
},
"TrainerController.advance": {
"total": 446.4756607609984,
"count": 18200,
"self": 0.2715779910013225,
"children": {
"env_step": {
"total": 446.20408276999706,
"count": 18200,
"self": 295.8472797839959,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.07129480601157,
"count": 18200,
"self": 1.463045487011641,
"children": {
"TorchPolicy.evaluate": {
"total": 148.60824931899992,
"count": 18200,
"self": 148.60824931899992
}
}
},
"workers": {
"total": 0.28550817998961975,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.1722354329954,
"count": 18200,
"is_parallel": true,
"self": 222.27556526898093,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00541353599987815,
"count": 1,
"is_parallel": true,
"self": 0.0040128999996795756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001400636000198574,
"count": 10,
"is_parallel": true,
"self": 0.001400636000198574
}
}
},
"UnityEnvironment.step": {
"total": 0.035216428000012456,
"count": 1,
"is_parallel": true,
"self": 0.0006342970000332571,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041266200014433707,
"count": 1,
"is_parallel": true,
"self": 0.00041266200014433707
},
"communicator.exchange": {
"total": 0.03220220100001825,
"count": 1,
"is_parallel": true,
"self": 0.03220220100001825
},
"steps_from_proto": {
"total": 0.001967267999816613,
"count": 1,
"is_parallel": true,
"self": 0.000387326000009125,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015799419998074882,
"count": 10,
"is_parallel": true,
"self": 0.0015799419998074882
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.8966701640145,
"count": 18199,
"is_parallel": true,
"self": 10.815198370007465,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.232388980005226,
"count": 18199,
"is_parallel": true,
"self": 5.232388980005226
},
"communicator.exchange": {
"total": 177.26576542998896,
"count": 18199,
"is_parallel": true,
"self": 177.26576542998896
},
"steps_from_proto": {
"total": 33.583317384012844,
"count": 18199,
"is_parallel": true,
"self": 6.232197035012632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.35112034900021,
"count": 181990,
"is_parallel": true,
"self": 27.35112034900021
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016610700004093815,
"count": 1,
"self": 0.00016610700004093815,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 441.33691279699747,
"count": 638209,
"is_parallel": true,
"self": 13.436478569944256,
"children": {
"process_trajectory": {
"total": 244.40823783605242,
"count": 638209,
"is_parallel": true,
"self": 243.90432152505286,
"children": {
"RLTrainer._checkpoint": {
"total": 0.503916310999557,
"count": 4,
"is_parallel": true,
"self": 0.503916310999557
}
}
},
"_update_policy": {
"total": 183.4921963910008,
"count": 90,
"is_parallel": true,
"self": 58.02812822800138,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.46406816299941,
"count": 4587,
"is_parallel": true,
"self": 125.46406816299941
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08733306899989657,
"count": 1,
"self": 0.0009782519998680073,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08635481700002856,
"count": 1,
"self": 0.08635481700002856
}
}
}
}
}
}
}