{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9969818592071533, "min": 0.9944885969161987, "max": 2.8410720825195312, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9475.3154296875, "min": 9475.3154296875, "max": 29001.6640625, "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": 12.873562812805176, "min": 0.3396061360836029, "max": 12.873562812805176, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2510.3447265625, "min": 65.88359069824219, "max": 2623.283203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06596311114163636, "min": 0.06055350327326724, "max": 0.07261654614971941, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26385244456654544, "min": 0.24221401309306895, "max": 0.3622360002475177, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19733894178095987, "min": 0.11873721123179967, "max": 0.2910494911320069, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7893557671238395, "min": 0.4749488449271987, "max": 1.4552474556600346, "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": 25.386363636363637, "min": 3.659090909090909, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 161.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.659090909090909, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 161.0, "max": 1394.0, "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": "1739993023", "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 --force", "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": "1739993457" }, "total": 434.72595316, "count": 1, "self": 0.47511295100002826, "children": { "run_training.setup": { "total": 0.022711001000061515, "count": 1, "self": 0.022711001000061515 }, "TrainerController.start_learning": { "total": 434.2281292079999, "count": 1, "self": 0.32466805902686247, "children": { "TrainerController._reset_env": { "total": 2.994219793000184, "count": 1, "self": 2.994219793000184 }, "TrainerController.advance": { "total": 430.82098374397265, "count": 18192, "self": 0.35699660300019787, "children": { "env_step": { "total": 302.20205413897907, "count": 18192, "self": 230.6994935689911, "children": { "SubprocessEnvManager._take_step": { "total": 71.30530633699755, "count": 18192, "self": 1.2876128430098106, "children": { "TorchPolicy.evaluate": { "total": 70.01769349398774, "count": 18192, "self": 70.01769349398774 } } }, "workers": { "total": 0.19725423299041722, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 432.76675170600447, "count": 18192, "is_parallel": true, "self": 229.5371421920281, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00580692999983512, "count": 1, "is_parallel": true, "self": 0.0041752390002329776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016316909996021423, "count": 10, "is_parallel": true, "self": 0.0016316909996021423 } } }, "UnityEnvironment.step": { "total": 0.035936592999860295, "count": 1, "is_parallel": true, "self": 0.0005597679996753868, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042186200016658404, "count": 1, "is_parallel": true, "self": 0.00042186200016658404 }, "communicator.exchange": { "total": 0.033130495000023075, "count": 1, "is_parallel": true, "self": 0.033130495000023075 }, "steps_from_proto": { "total": 0.0018244679999952496, "count": 1, "is_parallel": true, "self": 0.00036191800040796807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014625499995872815, "count": 10, "is_parallel": true, "self": 0.0014625499995872815 } } } } } } }, "UnityEnvironment.step": { "total": 203.22960951397636, "count": 18191, "is_parallel": true, "self": 9.79512094995789, "children": { "UnityEnvironment._generate_step_input": { "total": 5.422068586007072, "count": 18191, "is_parallel": true, "self": 5.422068586007072 }, "communicator.exchange": { "total": 156.2790282950034, "count": 18191, "is_parallel": true, "self": 156.2790282950034 }, "steps_from_proto": { "total": 31.733391683007994, "count": 18191, "is_parallel": true, "self": 5.641745687016964, "children": { "_process_rank_one_or_two_observation": { "total": 26.09164599599103, "count": 181910, "is_parallel": true, "self": 26.09164599599103 } } } } } } } } } } }, "trainer_advance": { "total": 128.26193300199338, "count": 18192, "self": 0.4011951749855598, "children": { "process_trajectory": { "total": 27.34751962200835, "count": 18192, "self": 26.71669347700822, "children": { "RLTrainer._checkpoint": { "total": 0.6308261450001282, "count": 4, "self": 0.6308261450001282 } } }, "_update_policy": { "total": 100.51321820499948, "count": 90, "self": 42.00443779800685, "children": { "TorchPPOOptimizer.update": { "total": 58.50878040699263, "count": 4587, "self": 58.50878040699263 } } } } } } }, "trainer_threads": { "total": 9.390000741404947e-07, "count": 1, "self": 9.390000741404947e-07 }, "TrainerController._save_models": { "total": 0.08825667300015994, "count": 1, "self": 0.0008838830001423048, "children": { "RLTrainer._checkpoint": { "total": 0.08737279000001763, "count": 1, "self": 0.08737279000001763 } } } } } } }