{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0539615154266357, "min": 1.0539615154266357, "max": 2.85628604888916, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10074.818359375, "min": 10074.818359375, "max": 29314.0625, "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": 12.749126434326172, "min": 0.47657960653305054, "max": 12.749126434326172, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2486.07958984375, "min": 92.4564437866211, "max": 2572.57568359375, "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": 0.07431825294421002, "min": 0.06272446246059867, "max": 0.07523657035712591, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29727301177684007, "min": 0.25678981617438335, "max": 0.37543862277898904, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2176876027210086, "min": 0.1199930426778783, "max": 0.3050751444755816, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8707504108840344, "min": 0.4799721707115132, "max": 1.5253757223779079, "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": 25.295454545454547, "min": 3.6818181818181817, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 162.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.6818181818181817, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 162.0, "max": 1395.0, "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": "1731169689", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/pedro/miniconda3/envs/py310/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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1731169987" }, "total": 298.3987144470011, "count": 1, "self": 0.2698685140003363, "children": { "run_training.setup": { "total": 0.019425178001256427, "count": 1, "self": 0.019425178001256427 }, "TrainerController.start_learning": { "total": 298.1094207549995, "count": 1, "self": 0.454404128875467, "children": { "TrainerController._reset_env": { "total": 2.2670119280010113, "count": 1, "self": 2.2670119280010113 }, "TrainerController.advance": { "total": 295.3288176151218, "count": 18205, "self": 0.21564665020014218, "children": { "env_step": { "total": 295.11317096492166, "count": 18205, "self": 222.1806082639614, "children": { "SubprocessEnvManager._take_step": { "total": 72.69021799288203, "count": 18205, "self": 1.1106527189549524, "children": { "TorchPolicy.evaluate": { "total": 71.57956527392707, "count": 18205, "self": 71.57956527392707 } } }, "workers": { "total": 0.24234470807823527, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 297.52814328496606, "count": 18205, "is_parallel": true, "self": 134.89920882601837, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.014905788000760367, "count": 1, "is_parallel": true, "self": 0.01369233500190603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012134529988543363, "count": 10, "is_parallel": true, "self": 0.0012134529988543363 } } }, "UnityEnvironment.step": { "total": 0.02531361199908133, "count": 1, "is_parallel": true, "self": 0.0008361059990420472, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000240866000240203, "count": 1, "is_parallel": true, "self": 0.000240866000240203 }, "communicator.exchange": { "total": 0.021630309000101988, "count": 1, "is_parallel": true, "self": 0.021630309000101988 }, "steps_from_proto": { "total": 0.002606330999697093, "count": 1, "is_parallel": true, "self": 0.0004635240002244245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021428069994726684, "count": 10, "is_parallel": true, "self": 0.0021428069994726684 } } } } } } }, "UnityEnvironment.step": { "total": 162.6289344589477, "count": 18204, "is_parallel": true, "self": 7.786312971784355, "children": { "UnityEnvironment._generate_step_input": { "total": 4.313025966121131, "count": 18204, "is_parallel": true, "self": 4.313025966121131 }, "communicator.exchange": { "total": 126.76215729503019, "count": 18204, "is_parallel": true, "self": 126.76215729503019 }, "steps_from_proto": { "total": 23.76743822601202, "count": 18204, "is_parallel": true, "self": 4.357966000676242, "children": { "_process_rank_one_or_two_observation": { "total": 19.409472225335776, "count": 182040, "is_parallel": true, "self": 19.409472225335776 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001647990011406364, "count": 1, "self": 0.0001647990011406364, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 294.5131238823451, "count": 198631, "is_parallel": true, "self": 2.9772337458380207, "children": { "process_trajectory": { "total": 169.15582157250174, "count": 198631, "is_parallel": true, "self": 168.63418790150172, "children": { "RLTrainer._checkpoint": { "total": 0.5216336710000178, "count": 4, "is_parallel": true, "self": 0.5216336710000178 } } }, "_update_policy": { "total": 122.38006856400534, "count": 90, "is_parallel": true, "self": 30.44846398302616, "children": { "TorchPPOOptimizer.update": { "total": 91.93160458097918, "count": 4587, "is_parallel": true, "self": 91.93160458097918 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05902228400009335, "count": 1, "self": 0.0006440320012188749, "children": { "RLTrainer._checkpoint": { "total": 0.058378251998874475, "count": 1, "self": 0.058378251998874475 } } } } } } }