{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8741690516471863, "min": 0.8741690516471863, "max": 2.8361868858337402, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8308.1025390625, "min": 8308.1025390625, "max": 28951.796875, "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": 12.360114097595215, "min": 0.2860587537288666, "max": 12.360114097595215, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2410.22216796875, "min": 55.49539566040039, "max": 2491.25146484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07169580229353469, "min": 0.0622091120458208, "max": 0.07437172473423118, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28678320917413874, "min": 0.26248646546018256, "max": 0.3718586236711559, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1897852512478244, "min": 0.11138795524169051, "max": 0.29212591110491287, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7591410049912976, "min": 0.44555182096676205, "max": 1.4310115555337832, "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": 24.863636363636363, "min": 3.25, "max": 24.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1094.0, "min": 143.0, "max": 1318.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.863636363636363, "min": 3.25, "max": 24.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1094.0, "min": 143.0, "max": 1318.0, "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": "1744454737", "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": "1744455358" }, "total": 621.0146308370001, "count": 1, "self": 0.591582550000112, "children": { "run_training.setup": { "total": 0.04457304400000339, "count": 1, "self": 0.04457304400000339 }, "TrainerController.start_learning": { "total": 620.378475243, "count": 1, "self": 0.6794766550119675, "children": { "TrainerController._reset_env": { "total": 4.226827388999936, "count": 1, "self": 4.226827388999936 }, "TrainerController.advance": { "total": 615.3806459369879, "count": 18192, "self": 0.7368769209879247, "children": { "env_step": { "total": 434.38881438700923, "count": 18192, "self": 368.61449908704617, "children": { "SubprocessEnvManager._take_step": { "total": 65.3753705039777, "count": 18192, "self": 2.537682759985614, "children": { "TorchPolicy.evaluate": { "total": 62.83768774399209, "count": 18192, "self": 62.83768774399209 } } }, "workers": { "total": 0.3989447959853578, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 617.9647822210069, "count": 18192, "is_parallel": true, "self": 300.5111160600087, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009831624999947053, "count": 1, "is_parallel": true, "self": 0.006415798000034556, "children": { "_process_rank_one_or_two_observation": { "total": 0.003415826999912497, "count": 10, "is_parallel": true, "self": 0.003415826999912497 } } }, "UnityEnvironment.step": { "total": 0.046632660000000214, "count": 1, "is_parallel": true, "self": 0.0007660909999458454, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004540779999615552, "count": 1, "is_parallel": true, "self": 0.0004540779999615552 }, "communicator.exchange": { "total": 0.043215169000063725, "count": 1, "is_parallel": true, "self": 0.043215169000063725 }, "steps_from_proto": { "total": 0.0021973220000290894, "count": 1, "is_parallel": true, "self": 0.0004076190002706426, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017897029997584468, "count": 10, "is_parallel": true, "self": 0.0017897029997584468 } } } } } } }, "UnityEnvironment.step": { "total": 317.4536661609982, "count": 18191, "is_parallel": true, "self": 15.4025915260288, "children": { "UnityEnvironment._generate_step_input": { "total": 8.014959721990977, "count": 18191, "is_parallel": true, "self": 8.014959721990977 }, "communicator.exchange": { "total": 248.5550277959868, "count": 18191, "is_parallel": true, "self": 248.5550277959868 }, "steps_from_proto": { "total": 45.4810871169916, "count": 18191, "is_parallel": true, "self": 8.933229769985473, "children": { "_process_rank_one_or_two_observation": { "total": 36.54785734700613, "count": 181910, "is_parallel": true, "self": 36.54785734700613 } } } } } } } } } } }, "trainer_advance": { "total": 180.25495462899073, "count": 18192, "self": 0.8985514809894539, "children": { "process_trajectory": { "total": 36.03133347500159, "count": 18192, "self": 35.38690213300151, "children": { "RLTrainer._checkpoint": { "total": 0.6444313420000753, "count": 4, "self": 0.6444313420000753 } } }, "_update_policy": { "total": 143.3250696729997, "count": 90, "self": 49.74603592000028, "children": { "TorchPPOOptimizer.update": { "total": 93.57903375299941, "count": 4587, "self": 93.57903375299941 } } } } } } }, "trainer_threads": { "total": 1.6830001641210401e-06, "count": 1, "self": 1.6830001641210401e-06 }, "TrainerController._save_models": { "total": 0.09152357900006791, "count": 1, "self": 0.0013055690001237963, "children": { "RLTrainer._checkpoint": { "total": 0.09021800999994412, "count": 1, "self": 0.09021800999994412 } } } } } } }