{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 0.8971384763717651, "min": 0.8971384763717651, "max": 1.4116650819778442, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 45589.88671875, "min": 44195.8671875, "max": 76496.71875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 116.66824644549763, "min": 96.28571428571429, "max": 394.1653543307087, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49234.0, "min": 48923.0, "max": 50277.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999937.0, "min": 49706.0, "max": 1999937.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999937.0, "min": 49706.0, "max": 1999937.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.264763593673706, "min": -0.12383951991796494, "max": 2.331685781478882, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 955.730224609375, "min": -15.603779792785645, "max": 1162.5576171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.59562465054164, "min": 1.8094248542236904, "max": 3.8747694769543326, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1517.353602528572, "min": 227.98753163218498, "max": 1941.2595079541206, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.59562465054164, "min": 1.8094248542236904, "max": 3.8747694769543326, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1517.353602528572, "min": 227.98753163218498, "max": 1941.2595079541206, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015981233178010572, "min": 0.015981233178010572, "max": 0.026182452834473225, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04794369953403172, "min": 0.032029860160158324, "max": 0.06862980061753964, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.030333695850438543, "min": 0.020515682734549047, "max": 0.24981450540944933, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09100108755131563, "min": 0.04423477053642273, "max": 0.49962901081889866, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.168709894376669e-05, "min": 3.168709894376669e-05, "max": 0.0029529075015697513, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.506129683130008e-05, "min": 9.506129683130008e-05, "max": 0.0084391530186949, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105623333333334, "min": 0.10105623333333334, "max": 0.19843025, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031687, "min": 0.20732160000000005, "max": 0.5813051, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.270604333333336e-05, "min": 6.270604333333336e-05, "max": 0.004921669475, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018811813000000008, "min": 0.00018811813000000008, "max": 0.01406712449, "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": "1749639908", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749642412" }, "total": 2504.139872877, "count": 1, "self": 0.43942243400033476, "children": { "run_training.setup": { "total": 0.02354239500004951, "count": 1, "self": 0.02354239500004951 }, "TrainerController.start_learning": { "total": 2503.676908048, "count": 1, "self": 4.537776729991492, "children": { "TrainerController._reset_env": { "total": 3.2380062330000783, "count": 1, "self": 3.2380062330000783 }, "TrainerController.advance": { "total": 2495.7943561950083, "count": 230882, "self": 4.940416981011367, "children": { "env_step": { "total": 2016.464806714998, "count": 230882, "self": 1582.402995270891, "children": { "SubprocessEnvManager._take_step": { "total": 431.33872371104303, "count": 230882, "self": 16.17097800102556, "children": { "TorchPolicy.evaluate": { "total": 415.16774571001747, "count": 223018, "self": 415.16774571001747 } } }, "workers": { "total": 2.723087733063835, "count": 230882, "self": 0.0, "children": { "worker_root": { "total": 2496.008702846121, "count": 230882, "is_parallel": true, "self": 1208.6917321351693, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010466420000057042, "count": 1, "is_parallel": true, "self": 0.000396485000010216, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006501569999954881, "count": 2, "is_parallel": true, "self": 0.0006501569999954881 } } }, "UnityEnvironment.step": { "total": 0.03319824200002586, "count": 1, "is_parallel": true, "self": 0.0003234710000015184, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001997529999471226, "count": 1, "is_parallel": true, "self": 0.0001997529999471226 }, "communicator.exchange": { "total": 0.031960059000084584, "count": 1, "is_parallel": true, "self": 0.031960059000084584 }, "steps_from_proto": { "total": 0.000714958999992632, "count": 1, "is_parallel": true, "self": 0.00020963899987691548, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005053200001157165, "count": 2, "is_parallel": true, "self": 0.0005053200001157165 } } } } } } }, "UnityEnvironment.step": { "total": 1287.3169707109519, "count": 230881, "is_parallel": true, "self": 37.57700631197349, "children": { "UnityEnvironment._generate_step_input": { "total": 85.21843932906279, "count": 230881, "is_parallel": true, "self": 85.21843932906279 }, "communicator.exchange": { "total": 1074.9600630639636, "count": 230881, "is_parallel": true, "self": 1074.9600630639636 }, "steps_from_proto": { "total": 89.56146200595185, "count": 230881, "is_parallel": true, "self": 33.618224872903966, "children": { "_process_rank_one_or_two_observation": { "total": 55.94323713304789, "count": 461762, "is_parallel": true, "self": 55.94323713304789 } } } } } } } } } } }, "trainer_advance": { "total": 474.3891324989987, "count": 230882, "self": 7.169493473026364, "children": { "process_trajectory": { "total": 161.3689927199673, "count": 230882, "self": 160.013542025967, "children": { "RLTrainer._checkpoint": { "total": 1.3554506940002966, "count": 10, "self": 1.3554506940002966 } } }, "_update_policy": { "total": 305.85064630600505, "count": 97, "self": 242.36068587499472, "children": { "TorchPPOOptimizer.update": { "total": 63.48996043101033, "count": 2910, "self": 63.48996043101033 } } } } } } }, "trainer_threads": { "total": 9.929999578162096e-07, "count": 1, "self": 9.929999578162096e-07 }, "TrainerController._save_models": { "total": 0.10676789700028166, "count": 1, "self": 0.0017862580002656614, "children": { "RLTrainer._checkpoint": { "total": 0.104981639000016, "count": 1, "self": 0.104981639000016 } } } } } } }