Brhnglc's picture
First Push
9652c4a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7191032767295837,
"min": 0.6876862049102783,
"max": 2.8823254108428955,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6937.189453125,
"min": 6543.333984375,
"max": 29517.89453125,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.352370262145996,
"min": 0.2215191125869751,
"max": 13.352370262145996,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2737.23583984375,
"min": 42.974708557128906,
"max": 2737.23583984375,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06522736268100333,
"min": 0.06064462204830859,
"max": 0.07372884277377606,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.32613681340501666,
"min": 0.24257848819323435,
"max": 0.3686442138688803,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1917061503611359,
"min": 0.09343470252055092,
"max": 0.2907124479465625,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9585307518056795,
"min": 0.37373881008220367,
"max": 1.3579512396279503,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.017698982400001e-06,
"min": 1.017698982400001e-06,
"max": 9.891760108239999e-05,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.088494912000005e-06,
"min": 5.088494912000005e-06,
"max": 0.0004846880153120001,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.818181818181817,
"min": 2.6363636363636362,
"max": 26.59090909090909,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1420.0,
"min": 116.0,
"max": 1424.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 2.6363636363636362,
"max": 26.59090909090909,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1420.0,
"min": 116.0,
"max": 1424.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674671718",
"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 --force",
"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": "1674672801"
},
"total": 1083.497220623,
"count": 1,
"self": 0.42393299999980627,
"children": {
"run_training.setup": {
"total": 0.10709082700009276,
"count": 1,
"self": 0.10709082700009276
},
"TrainerController.start_learning": {
"total": 1082.966196796,
"count": 1,
"self": 1.3286268789843234,
"children": {
"TrainerController._reset_env": {
"total": 5.837447507999968,
"count": 1,
"self": 5.837447507999968
},
"TrainerController.advance": {
"total": 1075.6697369340159,
"count": 45476,
"self": 0.7484525480201683,
"children": {
"env_step": {
"total": 1074.9212843859957,
"count": 45476,
"self": 712.275496671997,
"children": {
"SubprocessEnvManager._take_step": {
"total": 361.9141020019895,
"count": 45476,
"self": 3.6515561130174774,
"children": {
"TorchPolicy.evaluate": {
"total": 358.262545888972,
"count": 45476,
"self": 82.567193393955,
"children": {
"TorchPolicy.sample_actions": {
"total": 275.695352495017,
"count": 45476,
"self": 275.695352495017
}
}
}
}
},
"workers": {
"total": 0.7316857120092664,
"count": 45476,
"self": 0.0,
"children": {
"worker_root": {
"total": 1079.5731393580172,
"count": 45476,
"is_parallel": true,
"self": 507.8330024149959,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001978409000003012,
"count": 1,
"is_parallel": true,
"self": 0.0007471090000308322,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012312999999721796,
"count": 10,
"is_parallel": true,
"self": 0.0012312999999721796
}
}
},
"UnityEnvironment.step": {
"total": 0.033969266999974934,
"count": 1,
"is_parallel": true,
"self": 0.00035109999998894637,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024125899994942301,
"count": 1,
"is_parallel": true,
"self": 0.00024125899994942301
},
"communicator.exchange": {
"total": 0.0316436570001315,
"count": 1,
"is_parallel": true,
"self": 0.0316436570001315
},
"steps_from_proto": {
"total": 0.0017332509999050671,
"count": 1,
"is_parallel": true,
"self": 0.0004275170001619699,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013057339997430972,
"count": 10,
"is_parallel": true,
"self": 0.0013057339997430972
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 571.7401369430213,
"count": 45475,
"is_parallel": true,
"self": 20.978041913913103,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.736880506057787,
"count": 45475,
"is_parallel": true,
"self": 12.736880506057787
},
"communicator.exchange": {
"total": 459.90514288903955,
"count": 45475,
"is_parallel": true,
"self": 459.90514288903955
},
"steps_from_proto": {
"total": 78.12007163401086,
"count": 45475,
"is_parallel": true,
"self": 17.083209832123885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.03686180188697,
"count": 454750,
"is_parallel": true,
"self": 61.03686180188697
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.5942999804537976e-05,
"count": 1,
"self": 4.5942999804537976e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1068.3978456787634,
"count": 868642,
"is_parallel": true,
"self": 22.98589653075487,
"children": {
"process_trajectory": {
"total": 613.541286257006,
"count": 868642,
"is_parallel": true,
"self": 611.4976304550055,
"children": {
"RLTrainer._checkpoint": {
"total": 2.0436558020005577,
"count": 10,
"is_parallel": true,
"self": 2.0436558020005577
}
}
},
"_update_policy": {
"total": 431.87066289100244,
"count": 227,
"is_parallel": true,
"self": 107.41267403298411,
"children": {
"TorchPPOOptimizer.update": {
"total": 324.4579888580183,
"count": 11574,
"is_parallel": true,
"self": 324.4579888580183
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13033953200010728,
"count": 1,
"self": 0.0011043509998671652,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12923518100024012,
"count": 1,
"self": 0.12923518100024012
}
}
}
}
}
}
}