{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4017069339752197, "min": 1.4017069339752197, "max": 1.4273285865783691, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69847.0546875, "min": 68104.8671875, "max": 78613.3984375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.54787234042553, "min": 77.59591194968553, "max": 407.0325203252033, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49377.0, "min": 48688.0, "max": 50158.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999959.0, "min": 49731.0, "max": 1999959.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999959.0, "min": 49731.0, "max": 1999959.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4776902198791504, "min": 0.03927982971072197, "max": 2.4983255863189697, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1397.417236328125, "min": 4.792139053344727, "max": 1547.6827392578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8639640641127917, "min": 1.9003947699656252, "max": 4.003712545270505, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2179.2757321596146, "min": 231.84816193580627, "max": 2482.0995532274246, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8639640641127917, "min": 1.9003947699656252, "max": 4.003712545270505, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2179.2757321596146, "min": 231.84816193580627, "max": 2482.0995532274246, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01561876108793917, "min": 0.014337204749608645, "max": 0.019795225560665132, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04685628326381751, "min": 0.02867440949921729, "max": 0.0569654899610517, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05268935954405202, "min": 0.0228351566940546, "max": 0.05967930816113949, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15806807863215605, "min": 0.0456703133881092, "max": 0.17364830474058787, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6964987678666544e-06, "min": 3.6964987678666544e-06, "max": 0.00029533837655387497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1089496303599963e-05, "min": 1.1089496303599963e-05, "max": 0.0008441104686298501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123213333333332, "min": 0.10123213333333332, "max": 0.19844612499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036964, "min": 0.20762864999999997, "max": 0.5813701499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.148345333333316e-05, "min": 7.148345333333316e-05, "max": 0.0049224616375, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021445035999999946, "min": 0.00021445035999999946, "max": 0.014070370485, "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": "1703188207", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703190760" }, "total": 2553.367356117, "count": 1, "self": 0.4417279060007786, "children": { "run_training.setup": { "total": 0.052906377999534016, "count": 1, "self": 0.052906377999534016 }, "TrainerController.start_learning": { "total": 2552.8727218329996, "count": 1, "self": 4.803477121069591, "children": { "TrainerController._reset_env": { "total": 3.686765949999426, "count": 1, "self": 3.686765949999426 }, "TrainerController.advance": { "total": 2544.2674603999303, "count": 232802, "self": 5.116286603931258, "children": { "env_step": { "total": 2011.0378621720283, "count": 232802, "self": 1667.9731569080532, "children": { "SubprocessEnvManager._take_step": { "total": 339.88450657103203, "count": 232802, "self": 17.526282504970368, "children": { "TorchPolicy.evaluate": { "total": 322.35822406606167, "count": 222978, "self": 322.35822406606167 } } }, "workers": { "total": 3.1801986929431223, "count": 232802, "self": 0.0, "children": { "worker_root": { "total": 2545.1170373205123, "count": 232802, "is_parallel": true, "self": 1191.0901291147293, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000760451000132889, "count": 1, "is_parallel": true, "self": 0.0002941090006061131, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004663419995267759, "count": 2, "is_parallel": true, "self": 0.0004663419995267759 } } }, "UnityEnvironment.step": { "total": 0.034231996999551484, "count": 1, "is_parallel": true, "self": 0.0010191599985773792, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020999700063839555, "count": 1, "is_parallel": true, "self": 0.00020999700063839555 }, "communicator.exchange": { "total": 0.031429505000232894, "count": 1, "is_parallel": true, "self": 0.031429505000232894 }, "steps_from_proto": { "total": 0.0015733350001028157, "count": 1, "is_parallel": true, "self": 0.0002727700002651545, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013005649998376612, "count": 2, "is_parallel": true, "self": 0.0013005649998376612 } } } } } } }, "UnityEnvironment.step": { "total": 1354.026908205783, "count": 232801, "is_parallel": true, "self": 42.5589883763123, "children": { "UnityEnvironment._generate_step_input": { "total": 85.15095567264052, "count": 232801, "is_parallel": true, "self": 85.15095567264052 }, "communicator.exchange": { "total": 1129.8622376847634, "count": 232801, "is_parallel": true, "self": 1129.8622376847634 }, "steps_from_proto": { "total": 96.4547264720668, "count": 232801, "is_parallel": true, "self": 35.16257578315799, "children": { "_process_rank_one_or_two_observation": { "total": 61.292150688908805, "count": 465602, "is_parallel": true, "self": 61.292150688908805 } } } } } } } } } } }, "trainer_advance": { "total": 528.1133116239707, "count": 232802, "self": 7.505744991902247, "children": { "process_trajectory": { "total": 161.66497954106217, "count": 232802, "self": 160.38986876606396, "children": { "RLTrainer._checkpoint": { "total": 1.2751107749982111, "count": 10, "self": 1.2751107749982111 } } }, "_update_policy": { "total": 358.9425870910063, "count": 97, "self": 291.54346515399357, "children": { "TorchPPOOptimizer.update": { "total": 67.39912193701275, "count": 2910, "self": 67.39912193701275 } } } } } } }, "trainer_threads": { "total": 7.740000000922009e-07, "count": 1, "self": 7.740000000922009e-07 }, "TrainerController._save_models": { "total": 0.11501758800022799, "count": 1, "self": 0.001951719000317098, "children": { "RLTrainer._checkpoint": { "total": 0.11306586899991089, "count": 1, "self": 0.11306586899991089 } } } } } } }