{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4060478210449219, "min": 1.4060478210449219, "max": 1.4281854629516602, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70424.71875, "min": 68891.03125, "max": 76211.6953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 112.56363636363636, "min": 84.2947189097104, "max": 405.7154471544715, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49528.0, "min": 48960.0, "max": 50104.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999997.0, "min": 49801.0, "max": 1999997.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999997.0, "min": 49801.0, "max": 1999997.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.291245460510254, "min": 0.01175718568265438, "max": 2.4143800735473633, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1008.1480102539062, "min": 1.43437659740448, "max": 1353.09375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.463403274660761, "min": 1.7059705105961347, "max": 3.9759826404884797, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1523.8974408507347, "min": 208.12840229272842, "max": 2219.4844049811363, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.463403274660761, "min": 1.7059705105961347, "max": 3.9759826404884797, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1523.8974408507347, "min": 208.12840229272842, "max": 2219.4844049811363, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016036042499925116, "min": 0.012690193119245425, "max": 0.02001729811438256, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04810812749977535, "min": 0.02538038623849085, "max": 0.06005189434314767, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05188159143759145, "min": 0.02403501911709706, "max": 0.05793571559091409, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15564477431277435, "min": 0.04807003823419412, "max": 0.16353513238330683, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4696988434666615e-06, "min": 3.4696988434666615e-06, "max": 0.00029527852657382496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0409096530399984e-05, "min": 1.0409096530399984e-05, "max": 0.0008439912186695997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115653333333334, "min": 0.10115653333333334, "max": 0.19842617500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034696, "min": 0.20744134999999997, "max": 0.5813304, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.771101333333323e-05, "min": 6.771101333333323e-05, "max": 0.004921466132500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002031330399999997, "min": 0.0002031330399999997, "max": 0.014068386960000002, "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": "1717962085", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717964840" }, "total": 2754.637478036, "count": 1, "self": 0.8188574880005035, "children": { "run_training.setup": { "total": 0.0713459009999724, "count": 1, "self": 0.0713459009999724 }, "TrainerController.start_learning": { "total": 2753.747274647, "count": 1, "self": 5.19675371900621, "children": { "TrainerController._reset_env": { "total": 3.1888503519999176, "count": 1, "self": 3.1888503519999176 }, "TrainerController.advance": { "total": 2745.1816490769943, "count": 231668, "self": 5.474388238944812, "children": { "env_step": { "total": 2185.736898764036, "count": 231668, "self": 1806.018846209071, "children": { "SubprocessEnvManager._take_step": { "total": 376.25540964804827, "count": 231668, "self": 19.481673225967597, "children": { "TorchPolicy.evaluate": { "total": 356.7737364220807, "count": 223050, "self": 356.7737364220807 } } }, "workers": { "total": 3.46264290691704, "count": 231668, "self": 0.0, "children": { "worker_root": { "total": 2745.5802630369044, "count": 231668, "is_parallel": true, "self": 1295.6144522199784, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008592159999807336, "count": 1, "is_parallel": true, "self": 0.00021046799997748167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006487480000032519, "count": 2, "is_parallel": true, "self": 0.0006487480000032519 } } }, "UnityEnvironment.step": { "total": 0.03077822299997024, "count": 1, "is_parallel": true, "self": 0.0004117250000490458, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020808600004329492, "count": 1, "is_parallel": true, "self": 0.00020808600004329492 }, "communicator.exchange": { "total": 0.02933158599989838, "count": 1, "is_parallel": true, "self": 0.02933158599989838 }, "steps_from_proto": { "total": 0.0008268259999795191, "count": 1, "is_parallel": true, "self": 0.00021451399993566156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006123120000438576, "count": 2, "is_parallel": true, "self": 0.0006123120000438576 } } } } } } }, "UnityEnvironment.step": { "total": 1449.965810816926, "count": 231667, "is_parallel": true, "self": 43.597596386041914, "children": { "UnityEnvironment._generate_step_input": { "total": 88.4826283468974, "count": 231667, "is_parallel": true, "self": 88.4826283468974 }, "communicator.exchange": { "total": 1215.681951938012, "count": 231667, "is_parallel": true, "self": 1215.681951938012 }, "steps_from_proto": { "total": 102.20363414597466, "count": 231667, "is_parallel": true, "self": 35.72374025798899, "children": { "_process_rank_one_or_two_observation": { "total": 66.47989388798567, "count": 463334, "is_parallel": true, "self": 66.47989388798567 } } } } } } } } } } }, "trainer_advance": { "total": 553.9703620740132, "count": 231668, "self": 8.10090210604858, "children": { "process_trajectory": { "total": 167.55516974796706, "count": 231668, "self": 166.0735819389663, "children": { "RLTrainer._checkpoint": { "total": 1.4815878090007573, "count": 10, "self": 1.4815878090007573 } } }, "_update_policy": { "total": 378.3142902199976, "count": 97, "self": 307.88978149700347, "children": { "TorchPPOOptimizer.update": { "total": 70.42450872299412, "count": 2910, "self": 70.42450872299412 } } } } } } }, "trainer_threads": { "total": 1.3319995559868403e-06, "count": 1, "self": 1.3319995559868403e-06 }, "TrainerController._save_models": { "total": 0.1800201669998387, "count": 1, "self": 0.002737857999818516, "children": { "RLTrainer._checkpoint": { "total": 0.17728230900002018, "count": 1, "self": 0.17728230900002018 } } } } } } }