LeoAgis's picture
First commit
b805b62
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9772223830223083,
"min": 0.9772223830223083,
"max": 2.866279125213623,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9330.51953125,
"min": 9330.51953125,
"max": 29353.564453125,
"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": 13.099754333496094,
"min": 0.37240466475486755,
"max": 13.099754333496094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.4521484375,
"min": 72.24650573730469,
"max": 2669.69091796875,
"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": 0.07162296475315302,
"min": 0.06118023193397961,
"max": 0.07659202125739516,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2864918590126121,
"min": 0.26277133598056274,
"max": 0.357259040429056,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21280854217269843,
"min": 0.1314273802609201,
"max": 0.2745995077432371,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8512341686907937,
"min": 0.5257095210436804,
"max": 1.3729975387161855,
"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": 25.181818181818183,
"min": 3.6363636363636362,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 160.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 3.6363636363636362,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 160.0,
"max": 1428.0,
"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": "1677613946",
"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": "1677614424"
},
"total": 478.5461509239999,
"count": 1,
"self": 0.7914420780000455,
"children": {
"run_training.setup": {
"total": 0.1213227729999744,
"count": 1,
"self": 0.1213227729999744
},
"TrainerController.start_learning": {
"total": 477.6333860729999,
"count": 1,
"self": 0.4930447530064157,
"children": {
"TrainerController._reset_env": {
"total": 11.067666995999957,
"count": 1,
"self": 11.067666995999957
},
"TrainerController.advance": {
"total": 465.85693163499343,
"count": 18200,
"self": 0.26637315999278144,
"children": {
"env_step": {
"total": 465.59055847500065,
"count": 18200,
"self": 320.10086837301094,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.22085162299027,
"count": 18200,
"self": 1.6317235919885889,
"children": {
"TorchPolicy.evaluate": {
"total": 143.58912803100168,
"count": 18200,
"self": 31.16880884800787,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.42031918299381,
"count": 18200,
"self": 112.42031918299381
}
}
}
}
},
"workers": {
"total": 0.2688384789994416,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 475.9263175790005,
"count": 18200,
"is_parallel": true,
"self": 231.84802209601128,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005487815999913437,
"count": 1,
"is_parallel": true,
"self": 0.004168705999745725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013191100001677114,
"count": 10,
"is_parallel": true,
"self": 0.0013191100001677114
}
}
},
"UnityEnvironment.step": {
"total": 0.08320442199999434,
"count": 1,
"is_parallel": true,
"self": 0.0006307979999746749,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006291060000194193,
"count": 1,
"is_parallel": true,
"self": 0.0006291060000194193
},
"communicator.exchange": {
"total": 0.07562811200000397,
"count": 1,
"is_parallel": true,
"self": 0.07562811200000397
},
"steps_from_proto": {
"total": 0.006316405999996277,
"count": 1,
"is_parallel": true,
"self": 0.000527632000171252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005788773999825025,
"count": 10,
"is_parallel": true,
"self": 0.005788773999825025
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 244.07829548298923,
"count": 18199,
"is_parallel": true,
"self": 10.022821698997063,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.318313385990905,
"count": 18199,
"is_parallel": true,
"self": 5.318313385990905
},
"communicator.exchange": {
"total": 196.893842790009,
"count": 18199,
"is_parallel": true,
"self": 196.893842790009
},
"steps_from_proto": {
"total": 31.843317607992276,
"count": 18199,
"is_parallel": true,
"self": 6.975351816994134,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.86796579099814,
"count": 181990,
"is_parallel": true,
"self": 24.86796579099814
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001646880000407691,
"count": 1,
"self": 0.0001646880000407691,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.37509718699334,
"count": 408406,
"is_parallel": true,
"self": 10.277498399985575,
"children": {
"process_trajectory": {
"total": 263.809550846007,
"count": 408406,
"is_parallel": true,
"self": 262.9889726290071,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8205782169999338,
"count": 4,
"is_parallel": true,
"self": 0.8205782169999338
}
}
},
"_update_policy": {
"total": 188.28804794100074,
"count": 90,
"is_parallel": true,
"self": 65.92186914699892,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.36617879400183,
"count": 4587,
"is_parallel": true,
"self": 122.36617879400183
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21557800100003988,
"count": 1,
"self": 0.001274477000151819,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21430352399988806,
"count": 1,
"self": 0.21430352399988806
}
}
}
}
}
}
}