{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3297345638275146, "min": 1.3297345638275146, "max": 1.4177614450454712, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 66005.3671875, "min": 64268.796875, "max": 77864.875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 102.84905660377359, "min": 79.29695024077047, "max": 394.0, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49059.0, "min": 48938.0, "max": 50076.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999996.0, "min": 49840.0, "max": 1999996.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999996.0, "min": 49840.0, "max": 1999996.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3293540477752686, "min": 0.07275520265102386, "max": 2.417428731918335, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1111.1019287109375, "min": 9.167155265808105, "max": 1448.24169921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6424216551850677, "min": 1.9435213681251284, "max": 3.923651122843292, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1737.4351295232773, "min": 244.88369238376617, "max": 2304.2841026186943, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6424216551850677, "min": 1.9435213681251284, "max": 3.923651122843292, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1737.4351295232773, "min": 244.88369238376617, "max": 2304.2841026186943, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015911076146876438, "min": 0.015299388875137085, "max": 0.021104390442487783, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04773322844062931, "min": 0.03059877775027417, "max": 0.06003561312449165, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.03864940146605174, "min": 0.020283563900738957, "max": 0.041428420022130014, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.11594820439815522, "min": 0.04069214222952723, "max": 0.12313401956111192, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 2.4644987678000037e-06, "min": 2.4644987678000037e-06, "max": 0.00019689570155215002, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 7.393496303400011e-06, "min": 7.393496303400011e-06, "max": 0.0005628444185778001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123220000000001, "min": 0.10123220000000001, "max": 0.19844785000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30369660000000004, "min": 0.20760095, "max": 0.5814222000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 5.9164780000000086e-05, "min": 5.9164780000000086e-05, "max": 0.003938069215000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017749434000000026, "min": 0.00017749434000000026, "max": 0.011258745780000001, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1722582491", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1722585364" }, "total": 2872.497301821, "count": 1, "self": 0.4598835740002869, "children": { "run_training.setup": { "total": 0.061099055999989105, "count": 1, "self": 0.061099055999989105 }, "TrainerController.start_learning": { "total": 2871.9763191909997, "count": 1, "self": 4.5071777100247346, "children": { "TrainerController._reset_env": { "total": 2.983093116999953, "count": 1, "self": 2.983093116999953 }, "TrainerController.advance": { "total": 2863.628943956975, "count": 232011, "self": 4.975341766720248, "children": { "env_step": { "total": 2024.4318415601447, "count": 232011, "self": 1641.4660770819519, "children": { "SubprocessEnvManager._take_step": { "total": 379.90256088108424, "count": 232011, "self": 18.38594426701809, "children": { "TorchPolicy.evaluate": { "total": 361.51661661406615, "count": 223026, "self": 361.51661661406615 } } }, "workers": { "total": 3.0632035971084406, "count": 232011, "self": 0.0, "children": { "worker_root": { "total": 2863.1049639430007, "count": 232011, "is_parallel": true, "self": 1545.6603401569469, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009975120000262905, "count": 1, "is_parallel": true, "self": 0.00025001900007737277, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007474929999489177, "count": 2, "is_parallel": true, "self": 0.0007474929999489177 } } }, "UnityEnvironment.step": { "total": 0.05625406199999361, "count": 1, "is_parallel": true, "self": 0.0003981530001055944, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002469599999130878, "count": 1, "is_parallel": true, "self": 0.0002469599999130878 }, "communicator.exchange": { "total": 0.05483315200001471, "count": 1, "is_parallel": true, "self": 0.05483315200001471 }, "steps_from_proto": { "total": 0.000775796999960221, "count": 1, "is_parallel": true, "self": 0.0002309110000169312, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005448859999432898, "count": 2, "is_parallel": true, "self": 0.0005448859999432898 } } } } } } }, "UnityEnvironment.step": { "total": 1317.4446237860539, "count": 232010, "is_parallel": true, "self": 39.37776271299322, "children": { "UnityEnvironment._generate_step_input": { "total": 85.91785372196694, "count": 232010, "is_parallel": true, "self": 85.91785372196694 }, "communicator.exchange": { "total": 1098.1487765530867, "count": 232010, "is_parallel": true, "self": 1098.1487765530867 }, "steps_from_proto": { "total": 94.0002307980069, "count": 232010, "is_parallel": true, "self": 35.278505244057556, "children": { "_process_rank_one_or_two_observation": { "total": 58.72172555394934, "count": 464020, "is_parallel": true, "self": 58.72172555394934 } } } } } } } } } } }, "trainer_advance": { "total": 834.2217606301101, "count": 232011, "self": 6.933422297069228, "children": { "process_trajectory": { "total": 177.36866701403926, "count": 232011, "self": 170.27879381603964, "children": { "RLTrainer._checkpoint": { "total": 7.089873197999623, "count": 10, "self": 7.089873197999623 } } }, "_update_policy": { "total": 649.9196713190016, "count": 97, "self": 435.2712507850016, "children": { "TorchPPOOptimizer.update": { "total": 214.64842053400002, "count": 4850, "self": 214.64842053400002 } } } } } } }, "trainer_threads": { "total": 1.0200001270277426e-06, "count": 1, "self": 1.0200001270277426e-06 }, "TrainerController._save_models": { "total": 0.8571033869998246, "count": 1, "self": 0.014533579999806534, "children": { "RLTrainer._checkpoint": { "total": 0.842569807000018, "count": 1, "self": 0.842569807000018 } } } } } } }