{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.922466516494751, "min": 0.922466516494751, "max": 2.8758199214935303, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8817.857421875, "min": 8817.857421875, "max": 29514.541015625, "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": 12.773842811584473, "min": 0.278909832239151, "max": 12.91517448425293, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2490.8994140625, "min": 54.10850524902344, "max": 2606.57373046875, "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": 0.07100745961789096, "min": 0.06330882687607835, "max": 0.07593281450916786, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2840298384715638, "min": 0.26255662498000426, "max": 0.37966407254583934, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22717198641861186, "min": 0.10980689404281223, "max": 0.30513443193014933, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9086879456744474, "min": 0.4392275761712489, "max": 1.5256721596507465, "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": 25.068181818181817, "min": 2.7954545454545454, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 123.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 2.7954545454545454, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 123.0, "max": 1398.0, "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": "1714816358", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714816938" }, "total": 580.5272210490001, "count": 1, "self": 0.708831036000106, "children": { "run_training.setup": { "total": 0.07017041900007825, "count": 1, "self": 0.07017041900007825 }, "TrainerController.start_learning": { "total": 579.7482195939999, "count": 1, "self": 0.7826241770123943, "children": { "TrainerController._reset_env": { "total": 3.311429870999973, "count": 1, "self": 3.311429870999973 }, "TrainerController.advance": { "total": 575.5530779659878, "count": 18201, "self": 0.4452167099847202, "children": { "env_step": { "total": 575.107861256003, "count": 18201, "self": 442.58891534599275, "children": { "SubprocessEnvManager._take_step": { "total": 132.10696200900918, "count": 18201, "self": 2.282668100007868, "children": { "TorchPolicy.evaluate": { "total": 129.8242939090013, "count": 18201, "self": 129.8242939090013 } } }, "workers": { "total": 0.4119839010011219, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 577.9399954969895, "count": 18201, "is_parallel": true, "self": 270.0967917039753, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006750015000079657, "count": 1, "is_parallel": true, "self": 0.004674019999924894, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020759950001547622, "count": 10, "is_parallel": true, "self": 0.0020759950001547622 } } }, "UnityEnvironment.step": { "total": 0.04811230100006014, "count": 1, "is_parallel": true, "self": 0.0008993260000806913, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004538680000223394, "count": 1, "is_parallel": true, "self": 0.0004538680000223394 }, "communicator.exchange": { "total": 0.0444008939999776, "count": 1, "is_parallel": true, "self": 0.0444008939999776 }, "steps_from_proto": { "total": 0.0023582129999795143, "count": 1, "is_parallel": true, "self": 0.0004591640000626285, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018990489999168858, "count": 10, "is_parallel": true, "self": 0.0018990489999168858 } } } } } } }, "UnityEnvironment.step": { "total": 307.84320379301414, "count": 18200, "is_parallel": true, "self": 14.755774435053127, "children": { "UnityEnvironment._generate_step_input": { "total": 7.540187473994479, "count": 18200, "is_parallel": true, "self": 7.540187473994479 }, "communicator.exchange": { "total": 241.05719578898731, "count": 18200, "is_parallel": true, "self": 241.05719578898731 }, "steps_from_proto": { "total": 44.49004609497922, "count": 18200, "is_parallel": true, "self": 8.826905483986707, "children": { "_process_rank_one_or_two_observation": { "total": 35.663140610992514, "count": 182000, "is_parallel": true, "self": 35.663140610992514 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0006972609999138513, "count": 1, "self": 0.0006972609999138513, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 568.8690151599665, "count": 772899, "is_parallel": true, "self": 17.2663120409494, "children": { "process_trajectory": { "total": 306.48270680301744, "count": 772899, "is_parallel": true, "self": 305.86212456401745, "children": { "RLTrainer._checkpoint": { "total": 0.6205822389999867, "count": 4, "is_parallel": true, "self": 0.6205822389999867 } } }, "_update_policy": { "total": 245.11999631599963, "count": 90, "is_parallel": true, "self": 63.983010682997815, "children": { "TorchPPOOptimizer.update": { "total": 181.1369856330018, "count": 4587, "is_parallel": true, "self": 181.1369856330018 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10039031899987094, "count": 1, "self": 0.001328181999951994, "children": { "RLTrainer._checkpoint": { "total": 0.09906213699991895, "count": 1, "self": 0.09906213699991895 } } } } } } }