{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9412683844566345, "min": 0.9412683844566345, "max": 2.868903875350952, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9007.9384765625, "min": 9007.9384765625, "max": 29412.001953125, "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": 12.920598030090332, "min": 0.5027452111244202, "max": 12.920598030090332, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.5166015625, "min": 97.5325698852539, "max": 2604.86767578125, "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.Losses.PolicyLoss.mean": { "value": 0.07330537104281855, "min": 0.06327827169037596, "max": 0.07330537104281855, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2932214841712742, "min": 0.25311308676150385, "max": 0.36003723643108404, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19159745592887722, "min": 0.09708070110725969, "max": 0.26526275242076197, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7663898237155089, "min": 0.38832280442903877, "max": 1.32631376210381, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.130097290000004e-06, "min": 8.130097290000004e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.2520389160000015e-05, "min": 3.2520389160000015e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10271, "min": 0.10271, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41084, "min": 0.41084, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014522900000000006, "min": 0.00014522900000000006, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005809160000000002, "min": 0.0005809160000000002, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.113636363636363, "min": 2.7954545454545454, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 123.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 2.7954545454545454, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 123.0, "max": 1406.0, "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": "1723457852", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723458301" }, "total": 448.73903989099995, "count": 1, "self": 0.7324942400000509, "children": { "run_training.setup": { "total": 0.0610516669999015, "count": 1, "self": 0.0610516669999015 }, "TrainerController.start_learning": { "total": 447.945493984, "count": 1, "self": 0.5581625700076529, "children": { "TrainerController._reset_env": { "total": 2.7789906699999847, "count": 1, "self": 2.7789906699999847 }, "TrainerController.advance": { "total": 444.4669274349924, "count": 18207, "self": 0.26121752602057313, "children": { "env_step": { "total": 444.2057099089718, "count": 18207, "self": 286.8381953039793, "children": { "SubprocessEnvManager._take_step": { "total": 157.09187040098755, "count": 18207, "self": 1.4797179219874579, "children": { "TorchPolicy.evaluate": { "total": 155.6121524790001, "count": 18207, "self": 155.6121524790001 } } }, "workers": { "total": 0.2756442040049478, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 446.7098390810022, "count": 18207, "is_parallel": true, "self": 227.23136646600165, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053915280000182975, "count": 1, "is_parallel": true, "self": 0.0037873050002872333, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016042229997310642, "count": 10, "is_parallel": true, "self": 0.0016042229997310642 } } }, "UnityEnvironment.step": { "total": 0.03766029899998102, "count": 1, "is_parallel": true, "self": 0.0006264639998789789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003738309999334888, "count": 1, "is_parallel": true, "self": 0.0003738309999334888 }, "communicator.exchange": { "total": 0.03406527300012385, "count": 1, "is_parallel": true, "self": 0.03406527300012385 }, "steps_from_proto": { "total": 0.0025947310000447033, "count": 1, "is_parallel": true, "self": 0.0010973319997447106, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014973990002999926, "count": 10, "is_parallel": true, "self": 0.0014973990002999926 } } } } } } }, "UnityEnvironment.step": { "total": 219.47847261500056, "count": 18206, "is_parallel": true, "self": 10.055651971015777, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5208270689709025, "count": 18206, "is_parallel": true, "self": 5.5208270689709025 }, "communicator.exchange": { "total": 169.79333737600064, "count": 18206, "is_parallel": true, "self": 169.79333737600064 }, "steps_from_proto": { "total": 34.10865619901324, "count": 18206, "is_parallel": true, "self": 6.529487703983477, "children": { "_process_rank_one_or_two_observation": { "total": 27.579168495029762, "count": 182060, "is_parallel": true, "self": 27.579168495029762 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016161600001396437, "count": 1, "self": 0.00016161600001396437, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 438.73597889594976, "count": 668829, "is_parallel": true, "self": 14.143739439912451, "children": { "process_trajectory": { "total": 242.79635187003714, "count": 668829, "is_parallel": true, "self": 241.42847312303752, "children": { "RLTrainer._checkpoint": { "total": 1.3678787469996223, "count": 4, "is_parallel": true, "self": 1.3678787469996223 } } }, "_update_policy": { "total": 181.79588758600016, "count": 90, "is_parallel": true, "self": 58.06028061899087, "children": { "TorchPPOOptimizer.update": { "total": 123.73560696700929, "count": 4587, "is_parallel": true, "self": 123.73560696700929 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14125169299995832, "count": 1, "self": 0.0012442720001217822, "children": { "RLTrainer._checkpoint": { "total": 0.14000742099983654, "count": 1, "self": 0.14000742099983654 } } } } } } }