{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7811824679374695, "min": 0.7709082961082458, "max": 2.8721606731414795, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7424.3583984375, "min": 7424.3583984375, "max": 29319.015625, "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": 11.972668647766113, "min": 0.2813635468482971, "max": 11.972668647766113, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2334.67041015625, "min": 54.58452606201172, "max": 2420.564208984375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06295659255988093, "min": 0.060444064867196556, "max": 0.07650350043025123, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2518263702395237, "min": 0.24177625946878623, "max": 0.35741002059384136, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17162585035696917, "min": 0.1081036708646399, "max": 0.26972815262920713, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6865034014278767, "min": 0.4324146834585596, "max": 1.2929292040712692, "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.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.Environment.CumulativeReward.mean": { "value": 23.727272727272727, "min": 3.159090909090909, "max": 23.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1044.0, "min": 139.0, "max": 1279.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.727272727272727, "min": 3.159090909090909, "max": 23.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1044.0, "min": 139.0, "max": 1279.0, "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": "1742739567", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742740012" }, "total": 444.4390376399999, "count": 1, "self": 0.4359825959998034, "children": { "run_training.setup": { "total": 0.023827851000078226, "count": 1, "self": 0.023827851000078226 }, "TrainerController.start_learning": { "total": 443.97922719300004, "count": 1, "self": 0.34946201698062396, "children": { "TrainerController._reset_env": { "total": 3.0383297299999867, "count": 1, "self": 3.0383297299999867 }, "TrainerController.advance": { "total": 440.4473043080193, "count": 18192, "self": 0.3798192670158187, "children": { "env_step": { "total": 312.15114762900225, "count": 18192, "self": 238.14719357498393, "children": { "SubprocessEnvManager._take_step": { "total": 73.79232831502759, "count": 18192, "self": 1.3050039680194914, "children": { "TorchPolicy.evaluate": { "total": 72.4873243470081, "count": 18192, "self": 72.4873243470081 } } }, "workers": { "total": 0.21162573899073323, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 442.2089642609967, "count": 18192, "is_parallel": true, "self": 232.86567158598405, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00622745999999097, "count": 1, "is_parallel": true, "self": 0.00450486099975933, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017225990002316394, "count": 10, "is_parallel": true, "self": 0.0017225990002316394 } } }, "UnityEnvironment.step": { "total": 0.03707721099999617, "count": 1, "is_parallel": true, "self": 0.0006158880000839417, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004958510000960814, "count": 1, "is_parallel": true, "self": 0.0004958510000960814 }, "communicator.exchange": { "total": 0.03397013499989043, "count": 1, "is_parallel": true, "self": 0.03397013499989043 }, "steps_from_proto": { "total": 0.001995336999925712, "count": 1, "is_parallel": true, "self": 0.00037948799990772386, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016158490000179881, "count": 10, "is_parallel": true, "self": 0.0016158490000179881 } } } } } } }, "UnityEnvironment.step": { "total": 209.34329267501266, "count": 18191, "is_parallel": true, "self": 9.995811815985007, "children": { "UnityEnvironment._generate_step_input": { "total": 5.566330642999219, "count": 18191, "is_parallel": true, "self": 5.566330642999219 }, "communicator.exchange": { "total": 160.63367244102074, "count": 18191, "is_parallel": true, "self": 160.63367244102074 }, "steps_from_proto": { "total": 33.1474777750077, "count": 18191, "is_parallel": true, "self": 6.0218651190027686, "children": { "_process_rank_one_or_two_observation": { "total": 27.125612656004932, "count": 181910, "is_parallel": true, "self": 27.125612656004932 } } } } } } } } } } }, "trainer_advance": { "total": 127.91633741200121, "count": 18192, "self": 0.44787858800191316, "children": { "process_trajectory": { "total": 27.95624848699913, "count": 18192, "self": 27.32192759799932, "children": { "RLTrainer._checkpoint": { "total": 0.6343208889998095, "count": 4, "self": 0.6343208889998095 } } }, "_update_policy": { "total": 99.51221033700017, "count": 90, "self": 41.13690210599998, "children": { "TorchPPOOptimizer.update": { "total": 58.37530823100019, "count": 4587, "self": 58.37530823100019 } } } } } } }, "trainer_threads": { "total": 1.368000084767118e-06, "count": 1, "self": 1.368000084767118e-06 }, "TrainerController._save_models": { "total": 0.14412977000006322, "count": 1, "self": 0.0010588190000362374, "children": { "RLTrainer._checkpoint": { "total": 0.14307095100002698, "count": 1, "self": 0.14307095100002698 } } } } } } }