{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.796113133430481, "min": 0.796113133430481, "max": 2.8412976264953613, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7566.25927734375, "min": 7566.25927734375, "max": 29003.966796875, "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": 12.96572494506836, "min": 0.33394625782966614, "max": 12.96572494506836, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2528.31640625, "min": 64.78557586669922, "max": 2607.556640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06922673174253136, "min": 0.05715138930010617, "max": 0.07831529907005674, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2769069269701254, "min": 0.2286055572004247, "max": 0.3915764953502837, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1874755069467367, "min": 0.11071218986534423, "max": 0.280581985545509, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7499020277869468, "min": 0.4428487594613769, "max": 1.3476836582024894, "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": 25.795454545454547, "min": 3.0681818181818183, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1135.0, "min": 135.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.795454545454547, "min": 3.0681818181818183, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1135.0, "min": 135.0, "max": 1391.0, "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": "1738601348", "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": "1738601818" }, "total": 469.59840970899995, "count": 1, "self": 0.48559357899989664, "children": { "run_training.setup": { "total": 0.03130645500004903, "count": 1, "self": 0.03130645500004903 }, "TrainerController.start_learning": { "total": 469.081509675, "count": 1, "self": 0.35732875398821307, "children": { "TrainerController._reset_env": { "total": 3.8648029309999856, "count": 1, "self": 3.8648029309999856 }, "TrainerController.advance": { "total": 464.7389799450116, "count": 18192, "self": 0.3780916409798465, "children": { "env_step": { "total": 327.06932824402645, "count": 18192, "self": 249.32739912004547, "children": { "SubprocessEnvManager._take_step": { "total": 77.52132894298438, "count": 18192, "self": 1.3670435639950256, "children": { "TorchPolicy.evaluate": { "total": 76.15428537898936, "count": 18192, "self": 76.15428537898936 } } }, "workers": { "total": 0.22060018099659828, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 467.32711796900253, "count": 18192, "is_parallel": true, "self": 249.01029880599356, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006394043000000238, "count": 1, "is_parallel": true, "self": 0.004288884000288817, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021051589997114206, "count": 10, "is_parallel": true, "self": 0.0021051589997114206 } } }, "UnityEnvironment.step": { "total": 0.06815293199997541, "count": 1, "is_parallel": true, "self": 0.0006693299999369628, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039522500003386085, "count": 1, "is_parallel": true, "self": 0.00039522500003386085 }, "communicator.exchange": { "total": 0.06494421499996861, "count": 1, "is_parallel": true, "self": 0.06494421499996861 }, "steps_from_proto": { "total": 0.0021441620000359762, "count": 1, "is_parallel": true, "self": 0.0004228360000979592, "children": { "_process_rank_one_or_two_observation": { "total": 0.001721325999938017, "count": 10, "is_parallel": true, "self": 0.001721325999938017 } } } } } } }, "UnityEnvironment.step": { "total": 218.31681916300897, "count": 18191, "is_parallel": true, "self": 10.421363375972419, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5330503820129024, "count": 18191, "is_parallel": true, "self": 5.5330503820129024 }, "communicator.exchange": { "total": 169.2576227940051, "count": 18191, "is_parallel": true, "self": 169.2576227940051 }, "steps_from_proto": { "total": 33.10478261101855, "count": 18191, "is_parallel": true, "self": 5.859113782002055, "children": { "_process_rank_one_or_two_observation": { "total": 27.245668829016495, "count": 181910, "is_parallel": true, "self": 27.245668829016495 } } } } } } } } } } }, "trainer_advance": { "total": 137.29156006000528, "count": 18192, "self": 0.47304985200833016, "children": { "process_trajectory": { "total": 29.434466358997724, "count": 18192, "self": 28.792724770997665, "children": { "RLTrainer._checkpoint": { "total": 0.641741588000059, "count": 4, "self": 0.641741588000059 } } }, "_update_policy": { "total": 107.38404384899923, "count": 90, "self": 43.96853186000783, "children": { "TorchPPOOptimizer.update": { "total": 63.4155119889914, "count": 4587, "self": 63.4155119889914 } } } } } } }, "trainer_threads": { "total": 1.362000148219522e-06, "count": 1, "self": 1.362000148219522e-06 }, "TrainerController._save_models": { "total": 0.12039668300008088, "count": 1, "self": 0.0008979130000170699, "children": { "RLTrainer._checkpoint": { "total": 0.11949877000006381, "count": 1, "self": 0.11949877000006381 } } } } } } }