{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4060066938400269, "min": 1.4060066938400269, "max": 1.4267702102661133, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71160.8125, "min": 68046.125, "max": 77722.8984375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.63819095477388, "min": 80.67156862745098, "max": 400.384, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49335.0, "min": 49146.0, "max": 50048.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999939.0, "min": 49581.0, "max": 1999939.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999939.0, "min": 49581.0, "max": 1999939.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.409661054611206, "min": 0.07987549155950546, "max": 2.490151882171631, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1438.567626953125, "min": 9.904561042785645, "max": 1490.5687255859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.698728404751974, "min": 1.7073551615880382, "max": 4.084130210025857, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2208.1408576369286, "min": 211.71204003691673, "max": 2415.200038909912, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.698728404751974, "min": 1.7073551615880382, "max": 4.084130210025857, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2208.1408576369286, "min": 211.71204003691673, "max": 2415.200038909912, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018899744108784946, "min": 0.014433104372437812, "max": 0.020592655615473632, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.056699232326354834, "min": 0.028866208744875624, "max": 0.05690737933618948, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05907384562823507, "min": 0.021344922482967377, "max": 0.06315114144235849, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1772215368847052, "min": 0.04268984496593475, "max": 0.1772215368847052, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2761989079666713e-06, "min": 3.2761989079666713e-06, "max": 0.00029529742656752504, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.828596723900013e-06, "min": 9.828596723900013e-06, "max": 0.0008437726687424501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109203333333334, "min": 0.10109203333333334, "max": 0.19843247499999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30327610000000005, "min": 0.20730995, "max": 0.5812575500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.449246333333342e-05, "min": 6.449246333333342e-05, "max": 0.0049217805025000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019347739000000024, "min": 0.00019347739000000024, "max": 0.014064751745, "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": "1701683567", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701686203" }, "total": 2636.4535428690006, "count": 1, "self": 0.4439823690004232, "children": { "run_training.setup": { "total": 0.06220600000006016, "count": 1, "self": 0.06220600000006016 }, "TrainerController.start_learning": { "total": 2635.9473545, "count": 1, "self": 4.95293493807003, "children": { "TrainerController._reset_env": { "total": 3.560804848000089, "count": 1, "self": 3.560804848000089 }, "TrainerController.advance": { "total": 2627.324784209929, "count": 232759, "self": 5.137414061060554, "children": { "env_step": { "total": 2082.6504548749717, "count": 232759, "self": 1724.9613225779108, "children": { "SubprocessEnvManager._take_step": { "total": 354.42028321995576, "count": 232759, "self": 17.90653343986469, "children": { "TorchPolicy.evaluate": { "total": 336.5137497800911, "count": 223024, "self": 336.5137497800911 } } }, "workers": { "total": 3.2688490771051875, "count": 232759, "self": 0.0, "children": { "worker_root": { "total": 2628.022407859079, "count": 232759, "is_parallel": true, "self": 1231.24827591714, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008742749998873478, "count": 1, "is_parallel": true, "self": 0.000247300999944855, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006269739999424928, "count": 2, "is_parallel": true, "self": 0.0006269739999424928 } } }, "UnityEnvironment.step": { "total": 0.030515016999970612, "count": 1, "is_parallel": true, "self": 0.00030255800015766, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022348099992086645, "count": 1, "is_parallel": true, "self": 0.00022348099992086645 }, "communicator.exchange": { "total": 0.02927727699989191, "count": 1, "is_parallel": true, "self": 0.02927727699989191 }, "steps_from_proto": { "total": 0.0007117010000001756, "count": 1, "is_parallel": true, "self": 0.00021153600005163753, "children": { "_process_rank_one_or_two_observation": { "total": 0.000500164999948538, "count": 2, "is_parallel": true, "self": 0.000500164999948538 } } } } } } }, "UnityEnvironment.step": { "total": 1396.774131941939, "count": 232758, "is_parallel": true, "self": 42.254808968036286, "children": { "UnityEnvironment._generate_step_input": { "total": 90.82148543802873, "count": 232758, "is_parallel": true, "self": 90.82148543802873 }, "communicator.exchange": { "total": 1167.0155097887805, "count": 232758, "is_parallel": true, "self": 1167.0155097887805 }, "steps_from_proto": { "total": 96.6823277470935, "count": 232758, "is_parallel": true, "self": 35.79391997593052, "children": { "_process_rank_one_or_two_observation": { "total": 60.888407771162974, "count": 465516, "is_parallel": true, "self": 60.888407771162974 } } } } } } } } } } }, "trainer_advance": { "total": 539.5369152738967, "count": 232759, "self": 7.725300162828262, "children": { "process_trajectory": { "total": 170.39194510606785, "count": 232759, "self": 169.3041466980676, "children": { "RLTrainer._checkpoint": { "total": 1.0877984080002534, "count": 10, "self": 1.0877984080002534 } } }, "_update_policy": { "total": 361.4196700050006, "count": 97, "self": 295.20201803800023, "children": { "TorchPPOOptimizer.update": { "total": 66.21765196700039, "count": 2910, "self": 66.21765196700039 } } } } } } }, "trainer_threads": { "total": 8.880006134859286e-07, "count": 1, "self": 8.880006134859286e-07 }, "TrainerController._save_models": { "total": 0.10882961600054841, "count": 1, "self": 0.0018172120007875492, "children": { "RLTrainer._checkpoint": { "total": 0.10701240399976086, "count": 1, "self": 0.10701240399976086 } } } } } } }