{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404489517211914, "min": 1.404489517211914, "max": 1.428743839263916, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72939.3515625, "min": 68960.625, "max": 76301.390625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.05701078582435, "min": 76.03416149068323, "max": 362.463768115942, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49361.0, "min": 48966.0, "max": 50349.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999984.0, "min": 49671.0, "max": 1999984.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999984.0, "min": 49671.0, "max": 1999984.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.478731155395508, "min": 0.04817305505275726, "max": 2.4910199642181396, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1608.696533203125, "min": 6.599708557128906, "max": 1608.696533203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8361249359436504, "min": 1.8165159419070196, "max": 3.961957477346417, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2489.645083427429, "min": 248.86268404126167, "max": 2489.645083427429, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8361249359436504, "min": 1.8165159419070196, "max": 3.961957477346417, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2489.645083427429, "min": 248.86268404126167, "max": 2489.645083427429, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01656443109210765, "min": 0.013109168998077318, "max": 0.02240773722199568, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04969329327632294, "min": 0.026218337996154636, "max": 0.05981408841713953, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06154806584947639, "min": 0.02234748660897215, "max": 0.06623853159447511, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18464419754842917, "min": 0.0446949732179443, "max": 0.19871559478342532, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.39604886801667e-06, "min": 3.39604886801667e-06, "max": 0.00029537835154054993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.018814660405001e-05, "min": 1.018814660405001e-05, "max": 0.00084432856855715, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113198333333333, "min": 0.10113198333333333, "max": 0.19845945000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30339594999999997, "min": 0.20741335, "max": 0.58144285, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.648596833333342e-05, "min": 6.648596833333342e-05, "max": 0.004923126555000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019945790500000028, "min": 0.00019945790500000028, "max": 0.014073998215000001, "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": "1689237144", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689239552" }, "total": 2408.2522293939996, "count": 1, "self": 0.47594293700012713, "children": { "run_training.setup": { "total": 0.047677104999991116, "count": 1, "self": 0.047677104999991116 }, "TrainerController.start_learning": { "total": 2407.7286093519997, "count": 1, "self": 4.213287144931201, "children": { "TrainerController._reset_env": { "total": 4.731180182999992, "count": 1, "self": 4.731180182999992 }, "TrainerController.advance": { "total": 2398.6535600990687, "count": 232836, "self": 4.489371104228667, "children": { "env_step": { "total": 1861.3717850399084, "count": 232836, "self": 1565.3498737767613, "children": { "SubprocessEnvManager._take_step": { "total": 293.2519102920859, "count": 232836, "self": 16.900516539165324, "children": { "TorchPolicy.evaluate": { "total": 276.35139375292056, "count": 223046, "self": 276.35139375292056 } } }, "workers": { "total": 2.7700009710611653, "count": 232836, "self": 0.0, "children": { "worker_root": { "total": 2400.0731018860024, "count": 232836, "is_parallel": true, "self": 1121.4756277689207, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007846369999811031, "count": 1, "is_parallel": true, "self": 0.00023761499994634505, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005470220000347581, "count": 2, "is_parallel": true, "self": 0.0005470220000347581 } } }, "UnityEnvironment.step": { "total": 0.04487223200004564, "count": 1, "is_parallel": true, "self": 0.00037032800003089505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023018199999569333, "count": 1, "is_parallel": true, "self": 0.00023018199999569333 }, "communicator.exchange": { "total": 0.0434711490000268, "count": 1, "is_parallel": true, "self": 0.0434711490000268 }, "steps_from_proto": { "total": 0.0008005729999922551, "count": 1, "is_parallel": true, "self": 0.00020779100003665008, "children": { "_process_rank_one_or_two_observation": { "total": 0.000592781999955605, "count": 2, "is_parallel": true, "self": 0.000592781999955605 } } } } } } }, "UnityEnvironment.step": { "total": 1278.5974741170817, "count": 232835, "is_parallel": true, "self": 40.32446033808378, "children": { "UnityEnvironment._generate_step_input": { "total": 81.18573539605228, "count": 232835, "is_parallel": true, "self": 81.18573539605228 }, "communicator.exchange": { "total": 1059.06113896802, "count": 232835, "is_parallel": true, "self": 1059.06113896802 }, "steps_from_proto": { "total": 98.02613941492564, "count": 232835, "is_parallel": true, "self": 34.10718173495155, "children": { "_process_rank_one_or_two_observation": { "total": 63.918957679974085, "count": 465670, "is_parallel": true, "self": 63.918957679974085 } } } } } } } } } } }, "trainer_advance": { "total": 532.7924039549315, "count": 232836, "self": 6.365860087839678, "children": { "process_trajectory": { "total": 137.17642149508936, "count": 232836, "self": 135.79978903509016, "children": { "RLTrainer._checkpoint": { "total": 1.3766324599992004, "count": 10, "self": 1.3766324599992004 } } }, "_update_policy": { "total": 389.25012237200247, "count": 97, "self": 329.74179453400257, "children": { "TorchPPOOptimizer.update": { "total": 59.5083278379999, "count": 2910, "self": 59.5083278379999 } } } } } } }, "trainer_threads": { "total": 9.78999651124468e-07, "count": 1, "self": 9.78999651124468e-07 }, "TrainerController._save_models": { "total": 0.13058094600000913, "count": 1, "self": 0.0036524940001072537, "children": { "RLTrainer._checkpoint": { "total": 0.12692845199990188, "count": 1, "self": 0.12692845199990188 } } } } } } }