{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4024769067764282, "min": 1.4024769067764282, "max": 1.425945520401001, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71899.3828125, "min": 68176.734375, "max": 76627.2109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.91355599214145, "min": 84.42931034482758, "max": 396.62698412698415, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48820.0, "min": 48820.0, "max": 50071.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999954.0, "min": 49915.0, "max": 1999954.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999954.0, "min": 49915.0, "max": 1999954.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3667564392089844, "min": 0.1752566397190094, "max": 2.441361427307129, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1204.6790771484375, "min": 21.907079696655273, "max": 1399.52099609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6235563414270144, "min": 1.9468855130672456, "max": 3.9478331463512526, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1844.3901777863503, "min": 243.36068913340569, "max": 2212.9940482378006, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6235563414270144, "min": 1.9468855130672456, "max": 3.9478331463512526, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1844.3901777863503, "min": 243.36068913340569, "max": 2212.9940482378006, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016571268813762193, "min": 0.013712214865093605, "max": 0.019670358729894765, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04971380644128658, "min": 0.02742442973018721, "max": 0.05901107618968429, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04597058792908987, "min": 0.02092995084822178, "max": 0.05727502790590128, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1379117637872696, "min": 0.04185990169644356, "max": 0.16889234259724617, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.492548835850002e-06, "min": 3.492548835850002e-06, "max": 0.000295350526549825, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0477646507550006e-05, "min": 1.0477646507550006e-05, "max": 0.0008440623186459, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116414999999997, "min": 0.10116414999999997, "max": 0.19845017500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034924499999999, "min": 0.20750340000000006, "max": 0.5813541000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.809108500000005e-05, "min": 6.809108500000005e-05, "max": 0.004922663732500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020427325500000013, "min": 0.00020427325500000013, "max": 0.01406956959, "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": "1720415118", "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": "1720417702" }, "total": 2583.607034431, "count": 1, "self": 0.7144246860002568, "children": { "run_training.setup": { "total": 0.05695355699998572, "count": 1, "self": 0.05695355699998572 }, "TrainerController.start_learning": { "total": 2582.835656188, "count": 1, "self": 4.508341940987066, "children": { "TrainerController._reset_env": { "total": 2.9539926629999513, "count": 1, "self": 2.9539926629999513 }, "TrainerController.advance": { "total": 2575.1853569360132, "count": 232567, "self": 5.119241560104911, "children": { "env_step": { "total": 2036.5807196539954, "count": 232567, "self": 1682.9500522630071, "children": { "SubprocessEnvManager._take_step": { "total": 350.49233014298466, "count": 232567, "self": 18.00317328311371, "children": { "TorchPolicy.evaluate": { "total": 332.48915685987095, "count": 223116, "self": 332.48915685987095 } } }, "workers": { "total": 3.1383372480036087, "count": 232567, "self": 0.0, "children": { "worker_root": { "total": 2575.3343900050804, "count": 232567, "is_parallel": true, "self": 1221.6893384670439, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009331190000239076, "count": 1, "is_parallel": true, "self": 0.0002528820000406995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006802369999832081, "count": 2, "is_parallel": true, "self": 0.0006802369999832081 } } }, "UnityEnvironment.step": { "total": 0.03477843100000655, "count": 1, "is_parallel": true, "self": 0.0003961229999731586, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021932300001026306, "count": 1, "is_parallel": true, "self": 0.00021932300001026306 }, "communicator.exchange": { "total": 0.03336276300001373, "count": 1, "is_parallel": true, "self": 0.03336276300001373 }, "steps_from_proto": { "total": 0.0008002220000093985, "count": 1, "is_parallel": true, "self": 0.00025913799998988907, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005410840000195094, "count": 2, "is_parallel": true, "self": 0.0005410840000195094 } } } } } } }, "UnityEnvironment.step": { "total": 1353.6450515380366, "count": 232566, "is_parallel": true, "self": 40.79565125402405, "children": { "UnityEnvironment._generate_step_input": { "total": 89.4357469240648, "count": 232566, "is_parallel": true, "self": 89.4357469240648 }, "communicator.exchange": { "total": 1126.1636381099759, "count": 232566, "is_parallel": true, "self": 1126.1636381099759 }, "steps_from_proto": { "total": 97.25001524997191, "count": 232566, "is_parallel": true, "self": 37.358224638173226, "children": { "_process_rank_one_or_two_observation": { "total": 59.89179061179868, "count": 465132, "is_parallel": true, "self": 59.89179061179868 } } } } } } } } } } }, "trainer_advance": { "total": 533.4853957219129, "count": 232567, "self": 7.11576097692523, "children": { "process_trajectory": { "total": 163.89114826998747, "count": 232567, "self": 162.49876101798696, "children": { "RLTrainer._checkpoint": { "total": 1.3923872520005034, "count": 10, "self": 1.3923872520005034 } } }, "_update_policy": { "total": 362.47848647500024, "count": 97, "self": 295.9822700340021, "children": { "TorchPPOOptimizer.update": { "total": 66.49621644099813, "count": 2910, "self": 66.49621644099813 } } } } } } }, "trainer_threads": { "total": 1.6259996300505009e-06, "count": 1, "self": 1.6259996300505009e-06 }, "TrainerController._save_models": { "total": 0.1879630220000763, "count": 1, "self": 0.0031046880003486876, "children": { "RLTrainer._checkpoint": { "total": 0.18485833399972762, "count": 1, "self": 0.18485833399972762 } } } } } } }