pruvost's picture
First Push
8b233bb
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9236583709716797,
"min": 0.9212262034416199,
"max": 2.8749029636383057,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8819.08984375,
"min": 8819.08984375,
"max": 29473.505859375,
"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": 12.803145408630371,
"min": 0.26200616359710693,
"max": 12.803145408630371,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2496.61328125,
"min": 50.82919692993164,
"max": 2586.787841796875,
"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": 0.0688494952582736,
"min": 0.06352331658469185,
"max": 0.07281758098913854,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2753979810330944,
"min": 0.25410264526725096,
"max": 0.3523013787949001,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19645967980956328,
"min": 0.10286688548741021,
"max": 0.2818589973683451,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7858387192382531,
"min": 0.41146754194964086,
"max": 1.4092949868417255,
"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": 25.34090909090909,
"min": 3.022727272727273,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 133.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.022727272727273,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 133.0,
"max": 1379.0,
"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": "1675422939",
"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": "1.21.6",
"end_time_seconds": "1675423515"
},
"total": 575.672496911,
"count": 1,
"self": 0.5479506550000224,
"children": {
"run_training.setup": {
"total": 0.14219091000001072,
"count": 1,
"self": 0.14219091000001072
},
"TrainerController.start_learning": {
"total": 574.9823553460001,
"count": 1,
"self": 0.9075746020050701,
"children": {
"TrainerController._reset_env": {
"total": 8.780618059999995,
"count": 1,
"self": 8.780618059999995
},
"TrainerController.advance": {
"total": 565.155822333995,
"count": 18202,
"self": 0.465171371001702,
"children": {
"env_step": {
"total": 564.6906509629933,
"count": 18202,
"self": 426.8997124729964,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.3678780489912,
"count": 18202,
"self": 2.4179970179892507,
"children": {
"TorchPolicy.evaluate": {
"total": 134.94988103100195,
"count": 18202,
"self": 21.936782286997072,
"children": {
"TorchPolicy.sample_actions": {
"total": 113.01309874400488,
"count": 18202,
"self": 113.01309874400488
}
}
}
}
},
"workers": {
"total": 0.42306044100575946,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 572.9139461899979,
"count": 18202,
"is_parallel": true,
"self": 248.16077748599554,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010932061999994858,
"count": 1,
"is_parallel": true,
"self": 0.006401018000076419,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004531043999918438,
"count": 10,
"is_parallel": true,
"self": 0.004531043999918438
}
}
},
"UnityEnvironment.step": {
"total": 0.044758694000051946,
"count": 1,
"is_parallel": true,
"self": 0.0007095090001030258,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004849499999863838,
"count": 1,
"is_parallel": true,
"self": 0.0004849499999863838
},
"communicator.exchange": {
"total": 0.041102668000007725,
"count": 1,
"is_parallel": true,
"self": 0.041102668000007725
},
"steps_from_proto": {
"total": 0.0024615669999548118,
"count": 1,
"is_parallel": true,
"self": 0.0005905789998905675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018709880000642443,
"count": 10,
"is_parallel": true,
"self": 0.0018709880000642443
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 324.75316870400235,
"count": 18201,
"is_parallel": true,
"self": 12.95497515701038,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.821999834992255,
"count": 18201,
"is_parallel": true,
"self": 7.821999834992255
},
"communicator.exchange": {
"total": 256.85499801700115,
"count": 18201,
"is_parallel": true,
"self": 256.85499801700115
},
"steps_from_proto": {
"total": 47.12119569499856,
"count": 18201,
"is_parallel": true,
"self": 10.41734697097769,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.70384872402087,
"count": 182010,
"is_parallel": true,
"self": 36.70384872402087
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.0294999937250395e-05,
"count": 1,
"self": 5.0294999937250395e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 559.8705018570082,
"count": 583329,
"is_parallel": true,
"self": 15.725912147017198,
"children": {
"process_trajectory": {
"total": 311.1959819139905,
"count": 583329,
"is_parallel": true,
"self": 310.2152252269906,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9807566869999391,
"count": 4,
"is_parallel": true,
"self": 0.9807566869999391
}
}
},
"_update_policy": {
"total": 232.9486077960005,
"count": 90,
"is_parallel": true,
"self": 57.40045470500223,
"children": {
"TorchPPOOptimizer.update": {
"total": 175.54815309099826,
"count": 4587,
"is_parallel": true,
"self": 175.54815309099826
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13829005499997038,
"count": 1,
"self": 0.002134498999907919,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13615555600006246,
"count": 1,
"self": 0.13615555600006246
}
}
}
}
}
}
}