{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8946282267570496, "min": 0.8946282267570496, "max": 2.8607430458068848, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8502.546875, "min": 8502.546875, "max": 29202.46484375, "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": 13.019976615905762, "min": 0.2893347442150116, "max": 13.019976615905762, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2538.8955078125, "min": 56.13093948364258, "max": 2641.8427734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06879914932206328, "min": 0.0648928970582418, "max": 0.07675255690227656, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27519659728825313, "min": 0.2595715882329672, "max": 0.3837627845113828, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19673818459405618, "min": 0.11314278654754162, "max": 0.27493000311010024, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7869527383762247, "min": 0.4525711461901665, "max": 1.3746500155505013, "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": 25.136363636363637, "min": 3.522727272727273, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 155.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 3.522727272727273, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 155.0, "max": 1417.0, "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": "1788602323", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn ./ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788602799" }, "total": 476.26589002800006, "count": 1, "self": 0.7957396849999441, "children": { "run_training.setup": { "total": 0.020613273000094523, "count": 1, "self": 0.020613273000094523 }, "TrainerController.start_learning": { "total": 475.44953707, "count": 1, "self": 0.4476574550157011, "children": { "TrainerController._reset_env": { "total": 1.9762959450000608, "count": 1, "self": 1.9762959450000608 }, "TrainerController.advance": { "total": 472.87863677198413, "count": 18192, "self": 0.4427151249877852, "children": { "env_step": { "total": 351.929916763007, "count": 18192, "self": 275.8825785590109, "children": { "SubprocessEnvManager._take_step": { "total": 75.77824211400446, "count": 18192, "self": 1.418254707000301, "children": { "TorchPolicy.evaluate": { "total": 74.35998740700416, "count": 18192, "self": 74.35998740700416 } } }, "workers": { "total": 0.269096089991649, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 473.36423370198725, "count": 18192, "is_parallel": true, "self": 231.9304716459958, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019725199999811593, "count": 1, "is_parallel": true, "self": 0.0006559199999855991, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013165999999955602, "count": 10, "is_parallel": true, "self": 0.0013165999999955602 } } }, "UnityEnvironment.step": { "total": 0.03709179600002699, "count": 1, "is_parallel": true, "self": 0.0006031230001326549, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004283729999770003, "count": 1, "is_parallel": true, "self": 0.0004283729999770003 }, "communicator.exchange": { "total": 0.033933976999946935, "count": 1, "is_parallel": true, "self": 0.033933976999946935 }, "steps_from_proto": { "total": 0.002126322999970398, "count": 1, "is_parallel": true, "self": 0.0004928719998815723, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016334510000888258, "count": 10, "is_parallel": true, "self": 0.0016334510000888258 } } } } } } }, "UnityEnvironment.step": { "total": 241.43376205599145, "count": 18191, "is_parallel": true, "self": 10.822168093007349, "children": { "UnityEnvironment._generate_step_input": { "total": 5.764083515000948, "count": 18191, "is_parallel": true, "self": 5.764083515000948 }, "communicator.exchange": { "total": 185.42700739099553, "count": 18191, "is_parallel": true, "self": 185.42700739099553 }, "steps_from_proto": { "total": 39.42050305698763, "count": 18191, "is_parallel": true, "self": 7.086027197007979, "children": { "_process_rank_one_or_two_observation": { "total": 32.33447585997965, "count": 181910, "is_parallel": true, "self": 32.33447585997965 } } } } } } } } } } }, "trainer_advance": { "total": 120.50600488398936, "count": 18192, "self": 0.5839262970030177, "children": { "process_trajectory": { "total": 24.581586102986876, "count": 18192, "self": 24.167131306986903, "children": { "RLTrainer._checkpoint": { "total": 0.4144547959999727, "count": 4, "self": 0.4144547959999727 } } }, "_update_policy": { "total": 95.34049248399947, "count": 90, "self": 38.6366640869968, "children": { "TorchPPOOptimizer.update": { "total": 56.70382839700267, "count": 4587, "self": 56.70382839700267 } } } } } } }, "trainer_threads": { "total": 1.3240000953373965e-06, "count": 1, "self": 1.3240000953373965e-06 }, "TrainerController._save_models": { "total": 0.1469455740000285, "count": 1, "self": 0.0013421310000012454, "children": { "RLTrainer._checkpoint": { "total": 0.14560344300002726, "count": 1, "self": 0.14560344300002726 } } } } } } }