BlackSwan1827's picture
Initial Commit
ca14e0b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0508521795272827,
"min": 1.049127459526062,
"max": 2.8716909885406494,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10068.21484375,
"min": 10068.21484375,
"max": 29503.75390625,
"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": 12.664390563964844,
"min": 0.39936697483062744,
"max": 12.664390563964844,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2469.55615234375,
"min": 77.4771957397461,
"max": 2574.61669921875,
"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": 0.0685081014754342,
"min": 0.05989602166564688,
"max": 0.07636059486791127,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2740324059017368,
"min": 0.23958408666258751,
"max": 0.38180297433955634,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21986043873224773,
"min": 0.10780739299062748,
"max": 0.30989997655737633,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8794417549289909,
"min": 0.43122957196250994,
"max": 1.5494998827868818,
"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": 24.84090909090909,
"min": 3.2045454545454546,
"max": 25.345454545454544,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 141.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.2045454545454546,
"max": 25.345454545454544,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 141.0,
"max": 1394.0,
"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": "1691204133",
"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": "1691204770"
},
"total": 636.9776637710002,
"count": 1,
"self": 1.0404752230001577,
"children": {
"run_training.setup": {
"total": 0.05498243600004571,
"count": 1,
"self": 0.05498243600004571
},
"TrainerController.start_learning": {
"total": 635.882206112,
"count": 1,
"self": 0.943349822002574,
"children": {
"TrainerController._reset_env": {
"total": 2.536361335000038,
"count": 1,
"self": 2.536361335000038
},
"TrainerController.advance": {
"total": 632.1330781239974,
"count": 18224,
"self": 0.44721061502173143,
"children": {
"env_step": {
"total": 631.6858675089757,
"count": 18224,
"self": 511.5000083759346,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.73264507002068,
"count": 18224,
"self": 2.8979187170291425,
"children": {
"TorchPolicy.evaluate": {
"total": 116.83472635299154,
"count": 18224,
"self": 116.83472635299154
}
}
},
"workers": {
"total": 0.4532140630203685,
"count": 18224,
"self": 0.0,
"children": {
"worker_root": {
"total": 633.1294271489917,
"count": 18224,
"is_parallel": true,
"self": 271.22565825799256,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007106654999915918,
"count": 1,
"is_parallel": true,
"self": 0.0043078529997728765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027988020001430414,
"count": 10,
"is_parallel": true,
"self": 0.0027988020001430414
}
}
},
"UnityEnvironment.step": {
"total": 0.08439409400011755,
"count": 1,
"is_parallel": true,
"self": 0.0009457789999487431,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000516821000019263,
"count": 1,
"is_parallel": true,
"self": 0.000516821000019263
},
"communicator.exchange": {
"total": 0.07986157400000593,
"count": 1,
"is_parallel": true,
"self": 0.07986157400000593
},
"steps_from_proto": {
"total": 0.003069920000143611,
"count": 1,
"is_parallel": true,
"self": 0.0005274490004012478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025424709997423633,
"count": 10,
"is_parallel": true,
"self": 0.0025424709997423633
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 361.9037688909991,
"count": 18223,
"is_parallel": true,
"self": 15.567529320990616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.05053849899582,
"count": 18223,
"is_parallel": true,
"self": 8.05053849899582
},
"communicator.exchange": {
"total": 287.26814471200896,
"count": 18223,
"is_parallel": true,
"self": 287.26814471200896
},
"steps_from_proto": {
"total": 51.01755635900372,
"count": 18223,
"is_parallel": true,
"self": 10.256489654017287,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.76106670498643,
"count": 182230,
"is_parallel": true,
"self": 40.76106670498643
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00026436799998919014,
"count": 1,
"self": 0.00026436799998919014,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 626.4327030800305,
"count": 649600,
"is_parallel": true,
"self": 15.842807221077237,
"children": {
"process_trajectory": {
"total": 346.1060240329532,
"count": 649600,
"is_parallel": true,
"self": 343.3816876329529,
"children": {
"RLTrainer._checkpoint": {
"total": 2.724336400000311,
"count": 4,
"is_parallel": true,
"self": 2.724336400000311
}
}
},
"_update_policy": {
"total": 264.48387182600004,
"count": 90,
"is_parallel": true,
"self": 94.9641492799949,
"children": {
"TorchPPOOptimizer.update": {
"total": 169.51972254600514,
"count": 4587,
"is_parallel": true,
"self": 169.51972254600514
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2691524629999549,
"count": 1,
"self": 0.0015944179999678454,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26755804499998703,
"count": 1,
"self": 0.26755804499998703
}
}
}
}
}
}
}