{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8975753784179688, "min": 0.8975753784179688, "max": 2.8597354888916016, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8530.556640625, "min": 8530.556640625, "max": 29192.1796875, "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": 12.776655197143555, "min": 0.46246621012687683, "max": 12.885666847229004, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2491.44775390625, "min": 89.71844482421875, "max": 2636.5, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07192382876340109, "min": 0.061896672252766495, "max": 0.07233163446068705, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28769531505360435, "min": 0.2539309578389614, "max": 0.34788263919900225, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22757543382399226, "min": 0.12895768764314663, "max": 0.30576228961056356, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.910301735295969, "min": 0.5158307505725865, "max": 1.5288114480528179, "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": 25.136363636363637, "min": 3.5, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 154.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 3.5, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 154.0, "max": 1400.0, "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": "1742418441", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "1742418883" }, "total": 442.240541192, "count": 1, "self": 0.43804675900003076, "children": { "run_training.setup": { "total": 0.023282254000037028, "count": 1, "self": 0.023282254000037028 }, "TrainerController.start_learning": { "total": 441.77921217899996, "count": 1, "self": 0.3571841920040697, "children": { "TrainerController._reset_env": { "total": 3.062101415000029, "count": 1, "self": 3.062101415000029 }, "TrainerController.advance": { "total": 438.26972194099585, "count": 18192, "self": 0.37662847498836527, "children": { "env_step": { "total": 312.29938751100747, "count": 18192, "self": 236.34124002902308, "children": { "SubprocessEnvManager._take_step": { "total": 75.74165262999998, "count": 18192, "self": 1.3496447489977754, "children": { "TorchPolicy.evaluate": { "total": 74.3920078810022, "count": 18192, "self": 74.3920078810022 } } }, "workers": { "total": 0.21649485198440743, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 440.247598570999, "count": 18192, "is_parallel": true, "self": 232.61559110898577, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006181594999929985, "count": 1, "is_parallel": true, "self": 0.004596318000039901, "children": { "_process_rank_one_or_two_observation": { "total": 0.001585276999890084, "count": 10, "is_parallel": true, "self": 0.001585276999890084 } } }, "UnityEnvironment.step": { "total": 0.034448657999973875, "count": 1, "is_parallel": true, "self": 0.0005470569999488362, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040865500000109023, "count": 1, "is_parallel": true, "self": 0.00040865500000109023 }, "communicator.exchange": { "total": 0.03158952199999021, "count": 1, "is_parallel": true, "self": 0.03158952199999021 }, "steps_from_proto": { "total": 0.0019034240000337377, "count": 1, "is_parallel": true, "self": 0.0003773279998995349, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015260960001342028, "count": 10, "is_parallel": true, "self": 0.0015260960001342028 } } } } } } }, "UnityEnvironment.step": { "total": 207.63200746201323, "count": 18191, "is_parallel": true, "self": 9.977580674981368, "children": { "UnityEnvironment._generate_step_input": { "total": 5.616386188005777, "count": 18191, "is_parallel": true, "self": 5.616386188005777 }, "communicator.exchange": { "total": 158.68438843200784, "count": 18191, "is_parallel": true, "self": 158.68438843200784 }, "steps_from_proto": { "total": 33.353652167018254, "count": 18191, "is_parallel": true, "self": 6.013333369951283, "children": { "_process_rank_one_or_two_observation": { "total": 27.34031879706697, "count": 181910, "is_parallel": true, "self": 27.34031879706697 } } } } } } } } } } }, "trainer_advance": { "total": 125.59370595500002, "count": 18192, "self": 0.4356591189958863, "children": { "process_trajectory": { "total": 28.031761015004236, "count": 18192, "self": 27.422790016004114, "children": { "RLTrainer._checkpoint": { "total": 0.6089709990001211, "count": 4, "self": 0.6089709990001211 } } }, "_update_policy": { "total": 97.1262858209999, "count": 90, "self": 38.76279023499933, "children": { "TorchPPOOptimizer.update": { "total": 58.36349558600057, "count": 4587, "self": 58.36349558600057 } } } } } } }, "trainer_threads": { "total": 9.43000031838892e-07, "count": 1, "self": 9.43000031838892e-07 }, "TrainerController._save_models": { "total": 0.09020368799997414, "count": 1, "self": 0.0009285319999889907, "children": { "RLTrainer._checkpoint": { "total": 0.08927515599998515, "count": 1, "self": 0.08927515599998515 } } } } } } }