{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9657704830169678, "min": 0.9540870189666748, "max": 2.8596322536468506, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9178.6826171875, "min": 9178.6826171875, "max": 29191.125, "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": 12.45753002166748, "min": 0.4143187999725342, "max": 12.467453002929688, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2429.21826171875, "min": 80.37784576416016, "max": 2543.3603515625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06839954518192612, "min": 0.06476389558220569, "max": 0.07331977294599318, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2735981807277045, "min": 0.25905558232882275, "max": 0.3665988647299659, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23048978130899223, "min": 0.11588015878463492, "max": 0.30925284289554056, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9219591252359689, "min": 0.4635206351385397, "max": 1.3518392268349144, "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": 24.545454545454547, "min": 3.1136363636363638, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1080.0, "min": 137.0, "max": 1335.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.545454545454547, "min": 3.1136363636363638, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1080.0, "min": 137.0, "max": 1335.0, "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": "1776175274", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1776175759" }, "total": 484.82392686000014, "count": 1, "self": 0.43549908300019524, "children": { "run_training.setup": { "total": 0.02720938999993905, "count": 1, "self": 0.02720938999993905 }, "TrainerController.start_learning": { "total": 484.361218387, "count": 1, "self": 0.43960987200000545, "children": { "TrainerController._reset_env": { "total": 3.4708598900000425, "count": 1, "self": 3.4708598900000425 }, "TrainerController.advance": { "total": 480.3711740809997, "count": 18192, "self": 0.45027603002017713, "children": { "env_step": { "total": 353.99402979798174, "count": 18192, "self": 275.7394358279805, "children": { "SubprocessEnvManager._take_step": { "total": 77.98621717897595, "count": 18192, "self": 1.4203816859680956, "children": { "TorchPolicy.evaluate": { "total": 76.56583549300785, "count": 18192, "self": 76.56583549300785 } } }, "workers": { "total": 0.26837679102527545, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 482.31680897603144, "count": 18192, "is_parallel": true, "self": 241.05248639602098, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005088980999971682, "count": 1, "is_parallel": true, "self": 0.003523224999980812, "children": { "_process_rank_one_or_two_observation": { "total": 0.00156575599999087, "count": 10, "is_parallel": true, "self": 0.00156575599999087 } } }, "UnityEnvironment.step": { "total": 0.0800782240000899, "count": 1, "is_parallel": true, "self": 0.0006152180001208762, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004042390000904561, "count": 1, "is_parallel": true, "self": 0.0004042390000904561 }, "communicator.exchange": { "total": 0.07583290799993847, "count": 1, "is_parallel": true, "self": 0.07583290799993847 }, "steps_from_proto": { "total": 0.003225858999940101, "count": 1, "is_parallel": true, "self": 0.00036495599988484173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028609030000552593, "count": 10, "is_parallel": true, "self": 0.0028609030000552593 } } } } } } }, "UnityEnvironment.step": { "total": 241.26432258001046, "count": 18191, "is_parallel": true, "self": 11.03380422800933, "children": { "UnityEnvironment._generate_step_input": { "total": 5.821304378019249, "count": 18191, "is_parallel": true, "self": 5.821304378019249 }, "communicator.exchange": { "total": 184.71529434100262, "count": 18191, "is_parallel": true, "self": 184.71529434100262 }, "steps_from_proto": { "total": 39.69391963297926, "count": 18191, "is_parallel": true, "self": 7.15312965002704, "children": { "_process_rank_one_or_two_observation": { "total": 32.54078998295222, "count": 181910, "is_parallel": true, "self": 32.54078998295222 } } } } } } } } } } }, "trainer_advance": { "total": 125.92686825299779, "count": 18192, "self": 0.6067906300083905, "children": { "process_trajectory": { "total": 27.939263589989196, "count": 18192, "self": 27.489802795989362, "children": { "RLTrainer._checkpoint": { "total": 0.4494607939998332, "count": 4, "self": 0.4494607939998332 } } }, "_update_policy": { "total": 97.3808140330002, "count": 90, "self": 39.479544816998214, "children": { "TorchPPOOptimizer.update": { "total": 57.90126921600199, "count": 4587, "self": 57.90126921600199 } } } } } } }, "trainer_threads": { "total": 9.610000688553555e-07, "count": 1, "self": 9.610000688553555e-07 }, "TrainerController._save_models": { "total": 0.07957358300018313, "count": 1, "self": 0.0007393600003524625, "children": { "RLTrainer._checkpoint": { "total": 0.07883422299983067, "count": 1, "self": 0.07883422299983067 } } } } } } }