{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7914475202560425, "min": 0.789305567741394, "max": 2.8638765811920166, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7521.9169921875, "min": 7521.9169921875, "max": 29234.453125, "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": 13.01562786102295, "min": 0.41803812980651855, "max": 13.01562786102295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2538.04736328125, "min": 81.09939575195312, "max": 2651.05908203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06237235215574437, "min": 0.06237235215574437, "max": 0.07380081636538129, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24948940862297747, "min": 0.24948940862297747, "max": 0.36787189731623193, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19386878602352797, "min": 0.12733213015028513, "max": 0.3037031879612043, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7754751440941119, "min": 0.5093285206011405, "max": 1.5185159398060217, "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": 25.613636363636363, "min": 3.8181818181818183, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 168.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 3.8181818181818183, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 168.0, "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": "1781876314", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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": "1781876771" }, "total": 457.2681425779999, "count": 1, "self": 0.4372701889999462, "children": { "run_training.setup": { "total": 0.026012605999994776, "count": 1, "self": 0.026012605999994776 }, "TrainerController.start_learning": { "total": 456.804859783, "count": 1, "self": 0.37537960699341966, "children": { "TrainerController._reset_env": { "total": 2.9025115510000887, "count": 1, "self": 2.9025115510000887 }, "TrainerController.advance": { "total": 453.4470649150064, "count": 18192, "self": 0.3798405759760044, "children": { "env_step": { "total": 332.8555725930121, "count": 18192, "self": 260.4498901920131, "children": { "SubprocessEnvManager._take_step": { "total": 72.17938966399765, "count": 18192, "self": 1.291828702998373, "children": { "TorchPolicy.evaluate": { "total": 70.88756096099928, "count": 18192, "self": 70.88756096099928 } } }, "workers": { "total": 0.22629273700135855, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 454.9935068139848, "count": 18192, "is_parallel": true, "self": 225.99026171396667, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004780377999850316, "count": 1, "is_parallel": true, "self": 0.003207560999726411, "children": { "_process_rank_one_or_two_observation": { "total": 0.001572817000123905, "count": 10, "is_parallel": true, "self": 0.001572817000123905 } } }, "UnityEnvironment.step": { "total": 0.03754928599983032, "count": 1, "is_parallel": true, "self": 0.0006760560002021521, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048532299979342497, "count": 1, "is_parallel": true, "self": 0.00048532299979342497 }, "communicator.exchange": { "total": 0.0344602870000017, "count": 1, "is_parallel": true, "self": 0.0344602870000017 }, "steps_from_proto": { "total": 0.0019276199998330412, "count": 1, "is_parallel": true, "self": 0.0003897519998190546, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015378680000139866, "count": 10, "is_parallel": true, "self": 0.0015378680000139866 } } } } } } }, "UnityEnvironment.step": { "total": 229.00324510001815, "count": 18191, "is_parallel": true, "self": 10.536250654038213, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5685214969907975, "count": 18191, "is_parallel": true, "self": 5.5685214969907975 }, "communicator.exchange": { "total": 175.4150682250072, "count": 18191, "is_parallel": true, "self": 175.4150682250072 }, "steps_from_proto": { "total": 37.48340472398195, "count": 18191, "is_parallel": true, "self": 6.681047464968287, "children": { "_process_rank_one_or_two_observation": { "total": 30.80235725901366, "count": 181910, "is_parallel": true, "self": 30.80235725901366 } } } } } } } } } } }, "trainer_advance": { "total": 120.21165174601833, "count": 18192, "self": 0.44923340204172746, "children": { "process_trajectory": { "total": 24.40718053997557, "count": 18192, "self": 24.007918751975467, "children": { "RLTrainer._checkpoint": { "total": 0.3992617880001035, "count": 4, "self": 0.3992617880001035 } } }, "_update_policy": { "total": 95.35523780400104, "count": 90, "self": 38.96538753300297, "children": { "TorchPPOOptimizer.update": { "total": 56.38985027099807, "count": 4587, "self": 56.38985027099807 } } } } } } }, "trainer_threads": { "total": 8.790000265435083e-07, "count": 1, "self": 8.790000265435083e-07 }, "TrainerController._save_models": { "total": 0.07990283100002671, "count": 1, "self": 0.0007410480000089592, "children": { "RLTrainer._checkpoint": { "total": 0.07916178300001775, "count": 1, "self": 0.07916178300001775 } } } } } } }