{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1770081520080566, "min": 1.17113196849823, "max": 2.874617576599121, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11276.9150390625, "min": 11276.9150390625, "max": 29533.8203125, "count": 40 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.492471694946289, "min": 0.20442742109298706, "max": 12.492471694946289, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2436.031982421875, "min": 39.65892028808594, "max": 2494.06298828125, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0688093423760067, "min": 0.0625730189618052, "max": 0.07465685376676036, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2752373695040268, "min": 0.2632212347348732, "max": 0.3655117934241014, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2086627118143381, "min": 0.11588295219539135, "max": 0.278318935384353, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8346508472573524, "min": 0.4635318087815654, "max": 1.3662589239139185, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.15909090909091, "min": 3.3636363636363638, "max": 25.181818181818183, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 148.0, "max": 1385.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.3636363636363638, "max": 25.181818181818183, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 148.0, "max": 1385.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678867814", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678868281" }, "total": 466.68186826500005, "count": 1, "self": 0.38540409200004433, "children": { "run_training.setup": { "total": 0.36070864100020117, "count": 1, "self": 0.36070864100020117 }, "TrainerController.start_learning": { "total": 465.9357555319998, "count": 1, "self": 0.5961147689927202, "children": { "TrainerController._reset_env": { "total": 7.9586853829998745, "count": 1, "self": 7.9586853829998745 }, "TrainerController.advance": { "total": 457.28087443200707, "count": 18205, "self": 0.3036449680196256, "children": { "env_step": { "total": 456.97722946398744, "count": 18205, "self": 370.14708640900676, "children": { "SubprocessEnvManager._take_step": { "total": 86.53418726097925, "count": 18205, "self": 1.5083941079724354, "children": { "TorchPolicy.evaluate": { "total": 85.02579315300682, "count": 18205, "self": 85.02579315300682 } } }, "workers": { "total": 0.29595579400142924, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 464.8036287809896, "count": 18205, "is_parallel": true, "self": 222.33838017098697, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0037718589999258256, "count": 1, "is_parallel": true, "self": 0.0015225689996896108, "children": { "_process_rank_one_or_two_observation": { "total": 0.002249290000236215, "count": 10, "is_parallel": true, "self": 0.002249290000236215 } } }, "UnityEnvironment.step": { "total": 0.03642216599996573, "count": 1, "is_parallel": true, "self": 0.0005659999999352294, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003993600000740116, "count": 1, "is_parallel": true, "self": 0.0003993600000740116 }, "communicator.exchange": { "total": 0.03363127599982363, "count": 1, "is_parallel": true, "self": 0.03363127599982363 }, "steps_from_proto": { "total": 0.0018255300001328578, "count": 1, "is_parallel": true, "self": 0.0003547700002854981, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014707599998473597, "count": 10, "is_parallel": true, "self": 0.0014707599998473597 } } } } } } }, "UnityEnvironment.step": { "total": 242.46524861000262, "count": 18204, "is_parallel": true, "self": 10.070794126992723, "children": { "UnityEnvironment._generate_step_input": { "total": 5.685530683994102, "count": 18204, "is_parallel": true, "self": 5.685530683994102 }, "communicator.exchange": { "total": 195.8731405500073, "count": 18204, "is_parallel": true, "self": 195.8731405500073 }, "steps_from_proto": { "total": 30.8357832490085, "count": 18204, "is_parallel": true, "self": 5.992454814997473, "children": { "_process_rank_one_or_two_observation": { "total": 24.843328434011028, "count": 182040, "is_parallel": true, "self": 24.843328434011028 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010045999988506082, "count": 1, "self": 0.00010045999988506082, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.4914322040613, "count": 407741, "is_parallel": true, "self": 8.883626116113419, "children": { "process_trajectory": { "total": 238.96906921794675, "count": 407741, "is_parallel": true, "self": 237.78962629094713, "children": { "RLTrainer._checkpoint": { "total": 1.1794429269996272, "count": 4, "is_parallel": true, "self": 1.1794429269996272 } } }, "_update_policy": { "total": 206.63873687000114, "count": 90, "is_parallel": true, "self": 63.788813338002456, "children": { "TorchPPOOptimizer.update": { "total": 142.84992353199868, "count": 4587, "is_parallel": true, "self": 142.84992353199868 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09998048800025572, "count": 1, "self": 0.000689530000272498, "children": { "RLTrainer._checkpoint": { "total": 0.09929095799998322, "count": 1, "self": 0.09929095799998322 } } } } } } }