{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4076077938079834, "min": 1.4076077938079834, "max": 1.427653193473816, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70307.1953125, "min": 68807.484375, "max": 77291.453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.50990099009901, "min": 73.81831831831832, "max": 408.9918699186992, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49395.0, "min": 48911.0, "max": 50306.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999964.0, "min": 49844.0, "max": 1999964.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999964.0, "min": 49844.0, "max": 1999964.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4725286960601807, "min": 0.1282426118850708, "max": 2.538952112197876, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1498.3524169921875, "min": 15.645599365234375, "max": 1620.044189453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8177837126522567, "min": 1.8613968941031909, "max": 4.031073911028263, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2313.5769298672676, "min": 227.0904210805893, "max": 2568.747326552868, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8177837126522567, "min": 1.8613968941031909, "max": 4.031073911028263, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2313.5769298672676, "min": 227.0904210805893, "max": 2568.747326552868, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015557459834801396, "min": 0.01445264742008779, "max": 0.020658760090979437, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.046672379504404185, "min": 0.02890529484017558, "max": 0.06026172773902848, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05731332869165473, "min": 0.022116646512101094, "max": 0.06519706211984158, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1719399860749642, "min": 0.04423329302420219, "max": 0.1886163093149662, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6976487674833275e-06, "min": 3.6976487674833275e-06, "max": 0.0002953089015637, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1092946302449983e-05, "min": 1.1092946302449983e-05, "max": 0.00084404146865285, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123251666666666, "min": 0.10123251666666666, "max": 0.1984363, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30369755, "min": 0.20759224999999998, "max": 0.58134715, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.150258166666655e-05, "min": 7.150258166666655e-05, "max": 0.00492197137, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021450774499999966, "min": 0.00021450774499999966, "max": 0.014069222784999997, "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": "1739293963", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739296425" }, "total": 2461.458433859, "count": 1, "self": 0.43980322800007343, "children": { "run_training.setup": { "total": 0.02467910400002893, "count": 1, "self": 0.02467910400002893 }, "TrainerController.start_learning": { "total": 2460.993951527, "count": 1, "self": 4.302573771021798, "children": { "TrainerController._reset_env": { "total": 2.864966658000071, "count": 1, "self": 2.864966658000071 }, "TrainerController.advance": { "total": 2453.7064549119777, "count": 233073, "self": 4.558220931984579, "children": { "env_step": { "total": 1926.0130730789929, "count": 233073, "self": 1512.5200947709563, "children": { "SubprocessEnvManager._take_step": { "total": 410.8561158329676, "count": 233073, "self": 15.596829460031813, "children": { "TorchPolicy.evaluate": { "total": 395.2592863729358, "count": 222926, "self": 395.2592863729358 } } }, "workers": { "total": 2.6368624750690515, "count": 233073, "self": 0.0, "children": { "worker_root": { "total": 2453.445921076954, "count": 233073, "is_parallel": true, "self": 1216.679077341939, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009969249999812746, "count": 1, "is_parallel": true, "self": 0.0002950629999531884, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007018620000280862, "count": 2, "is_parallel": true, "self": 0.0007018620000280862 } } }, "UnityEnvironment.step": { "total": 0.029118036999989272, "count": 1, "is_parallel": true, "self": 0.00027359299997442577, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019245800001499447, "count": 1, "is_parallel": true, "self": 0.00019245800001499447 }, "communicator.exchange": { "total": 0.027808444000015697, "count": 1, "is_parallel": true, "self": 0.027808444000015697 }, "steps_from_proto": { "total": 0.0008435419999841542, "count": 1, "is_parallel": true, "self": 0.00020738400007758173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006361579999065725, "count": 2, "is_parallel": true, "self": 0.0006361579999065725 } } } } } } }, "UnityEnvironment.step": { "total": 1236.766843735015, "count": 233072, "is_parallel": true, "self": 36.68809159991474, "children": { "UnityEnvironment._generate_step_input": { "total": 81.82710341193865, "count": 233072, "is_parallel": true, "self": 81.82710341193865 }, "communicator.exchange": { "total": 1030.7056638561144, "count": 233072, "is_parallel": true, "self": 1030.7056638561144 }, "steps_from_proto": { "total": 87.5459848670472, "count": 233072, "is_parallel": true, "self": 32.71554391404345, "children": { "_process_rank_one_or_two_observation": { "total": 54.830440953003745, "count": 466144, "is_parallel": true, "self": 54.830440953003745 } } } } } } } } } } }, "trainer_advance": { "total": 523.1351609010001, "count": 233073, "self": 6.180299202976926, "children": { "process_trajectory": { "total": 163.3863779180257, "count": 233073, "self": 161.8911879910263, "children": { "RLTrainer._checkpoint": { "total": 1.4951899269993874, "count": 10, "self": 1.4951899269993874 } } }, "_update_policy": { "total": 353.56848377999745, "count": 97, "self": 286.45617735598194, "children": { "TorchPPOOptimizer.update": { "total": 67.11230642401551, "count": 2910, "self": 67.11230642401551 } } } } } } }, "trainer_threads": { "total": 7.700000423938036e-07, "count": 1, "self": 7.700000423938036e-07 }, "TrainerController._save_models": { "total": 0.11995541600026627, "count": 1, "self": 0.0019219930004510388, "children": { "RLTrainer._checkpoint": { "total": 0.11803342299981523, "count": 1, "self": 0.11803342299981523 } } } } } } }