{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4102680683135986, "min": 1.4102680683135986, "max": 1.4285235404968262, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69042.4921875, "min": 69042.4921875, "max": 76319.015625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 119.7677261613692, "min": 84.66037735849056, "max": 379.09090909090907, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48985.0, "min": 48746.0, "max": 50280.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49578.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49578.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.420680522918701, "min": 0.168349489569664, "max": 2.4694535732269287, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 990.058349609375, "min": 22.053783416748047, "max": 1390.60205078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.795026195952828, "min": 1.8418137199096096, "max": 3.9521939427700867, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1552.1657141447067, "min": 241.27759730815887, "max": 2196.3618634343147, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.795026195952828, "min": 1.8418137199096096, "max": 3.9521939427700867, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1552.1657141447067, "min": 241.27759730815887, "max": 2196.3618634343147, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017314299914384417, "min": 0.01333284739400066, "max": 0.02107076681374262, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.034628599828768834, "min": 0.02666569478800132, "max": 0.05782001346136288, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04747677743434906, "min": 0.022754012358685332, "max": 0.06121215729249848, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09495355486869812, "min": 0.048030276161928974, "max": 0.18363647187749543, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.44339851889999e-06, "min": 4.44339851889999e-06, "max": 0.00029530635156454994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.88679703779998e-06, "min": 8.88679703779998e-06, "max": 0.0008439736686754498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10148109999999999, "min": 0.10148109999999999, "max": 0.19843544999999999, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20296219999999998, "min": 0.20296219999999998, "max": 0.5813245500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.390688999999982e-05, "min": 8.390688999999982e-05, "max": 0.004921928955, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016781377999999965, "min": 0.00016781377999999965, "max": 0.014068095045000003, "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": "1702225438", "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": "1702227773" }, "total": 2335.6435521249996, "count": 1, "self": 0.4401687219997257, "children": { "run_training.setup": { "total": 0.05985266500010766, "count": 1, "self": 0.05985266500010766 }, "TrainerController.start_learning": { "total": 2335.1435307379998, "count": 1, "self": 4.393484938925667, "children": { "TrainerController._reset_env": { "total": 4.29111078699998, "count": 1, "self": 4.29111078699998 }, "TrainerController.advance": { "total": 2326.3598905590743, "count": 231743, "self": 4.45624814873554, "children": { "env_step": { "total": 1841.8946076052098, "count": 231743, "self": 1524.280200169455, "children": { "SubprocessEnvManager._take_step": { "total": 314.84140911285886, "count": 231743, "self": 16.85061870275331, "children": { "TorchPolicy.evaluate": { "total": 297.99079041010555, "count": 222978, "self": 297.99079041010555 } } }, "workers": { "total": 2.772998322896001, "count": 231743, "self": 0.0, "children": { "worker_root": { "total": 2327.608334458577, "count": 231743, "is_parallel": true, "self": 1092.1103421787334, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008298129996546777, "count": 1, "is_parallel": true, "self": 0.00023023999983706744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005995729998176103, "count": 2, "is_parallel": true, "self": 0.0005995729998176103 } } }, "UnityEnvironment.step": { "total": 0.04371646599975065, "count": 1, "is_parallel": true, "self": 0.0003275829999438429, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020382299999255338, "count": 1, "is_parallel": true, "self": 0.00020382299999255338 }, "communicator.exchange": { "total": 0.04245633399978033, "count": 1, "is_parallel": true, "self": 0.04245633399978033 }, "steps_from_proto": { "total": 0.0007287260000339302, "count": 1, "is_parallel": true, "self": 0.00019956999994974467, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005291560000841855, "count": 2, "is_parallel": true, "self": 0.0005291560000841855 } } } } } } }, "UnityEnvironment.step": { "total": 1235.4979922798434, "count": 231742, "is_parallel": true, "self": 39.05315344049268, "children": { "UnityEnvironment._generate_step_input": { "total": 80.70815983604007, "count": 231742, "is_parallel": true, "self": 80.70815983604007 }, "communicator.exchange": { "total": 1029.2170707051737, "count": 231742, "is_parallel": true, "self": 1029.2170707051737 }, "steps_from_proto": { "total": 86.51960829813697, "count": 231742, "is_parallel": true, "self": 30.087652568040085, "children": { "_process_rank_one_or_two_observation": { "total": 56.43195573009689, "count": 463484, "is_parallel": true, "self": 56.43195573009689 } } } } } } } } } } }, "trainer_advance": { "total": 480.009034805129, "count": 231743, "self": 6.417011959343199, "children": { "process_trajectory": { "total": 146.4539073557853, "count": 231743, "self": 145.3384566407858, "children": { "RLTrainer._checkpoint": { "total": 1.115450714999497, "count": 10, "self": 1.115450714999497 } } }, "_update_policy": { "total": 327.1381154900005, "count": 96, "self": 264.8182947129776, "children": { "TorchPPOOptimizer.update": { "total": 62.31982077702287, "count": 2880, "self": 62.31982077702287 } } } } } } }, "trainer_threads": { "total": 9.380000847158954e-07, "count": 1, "self": 9.380000847158954e-07 }, "TrainerController._save_models": { "total": 0.09904351499972108, "count": 1, "self": 0.0017173429996546474, "children": { "RLTrainer._checkpoint": { "total": 0.09732617200006644, "count": 1, "self": 0.09732617200006644 } } } } } } }