{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4033305644989014, "min": 1.4033305644989014, "max": 1.4256432056427002, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70138.4609375, "min": 68593.2109375, "max": 77047.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 69.16690042075736, "min": 66.84260515603799, "max": 384.4732824427481, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49316.0, "min": 49202.0, "max": 50366.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999971.0, "min": 49876.0, "max": 1999971.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999971.0, "min": 49876.0, "max": 1999971.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.562026023864746, "min": 0.1503358781337738, "max": 2.562026023864746, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1826.724609375, "min": 19.543664932250977, "max": 1856.431640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 4.046768776079715, "min": 1.6953626435536604, "max": 4.103382847004367, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2885.346137344837, "min": 220.39714366197586, "max": 2914.473617732525, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 4.046768776079715, "min": 1.6953626435536604, "max": 4.103382847004367, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2885.346137344837, "min": 220.39714366197586, "max": 2914.473617732525, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01726175903507586, "min": 0.013860432695946657, "max": 0.021535843820957884, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05178527710522758, "min": 0.027720865391893314, "max": 0.06460753146287365, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06172559190955427, "min": 0.020991371789326273, "max": 0.06433962589750687, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1851767757286628, "min": 0.041982743578652545, "max": 0.19005440672238666, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.141498619533339e-06, "min": 4.141498619533339e-06, "max": 0.000295318426560525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2424495858600016e-05, "min": 1.2424495858600016e-05, "max": 0.0008443558685480501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10138046666666665, "min": 0.10138046666666665, "max": 0.1984394750000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30414139999999995, "min": 0.20789549999999996, "max": 0.5814519500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.888528666666676e-05, "min": 7.888528666666676e-05, "max": 0.0049221298024999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002366558600000003, "min": 0.0002366558600000003, "max": 0.014074452305000004, "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": "1708798741", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708801257" }, "total": 2516.192513302, "count": 1, "self": 0.44019916299976103, "children": { "run_training.setup": { "total": 0.07096028900002693, "count": 1, "self": 0.07096028900002693 }, "TrainerController.start_learning": { "total": 2515.68135385, "count": 1, "self": 4.735209219012631, "children": { "TrainerController._reset_env": { "total": 3.553181562000077, "count": 1, "self": 3.553181562000077 }, "TrainerController.advance": { "total": 2507.271921742987, "count": 233508, "self": 5.00655254010735, "children": { "env_step": { "total": 2020.393030355, "count": 233508, "self": 1678.3636376241402, "children": { "SubprocessEnvManager._take_step": { "total": 338.8945842688473, "count": 233508, "self": 17.376906563855073, "children": { "TorchPolicy.evaluate": { "total": 321.51767770499225, "count": 222894, "self": 321.51767770499225 } } }, "workers": { "total": 3.1348084620124155, "count": 233508, "self": 0.0, "children": { "worker_root": { "total": 2507.7132145409473, "count": 233508, "is_parallel": true, "self": 1143.7872820349617, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001123051999911695, "count": 1, "is_parallel": true, "self": 0.00035629299998163333, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007667589999300617, "count": 2, "is_parallel": true, "self": 0.0007667589999300617 } } }, "UnityEnvironment.step": { "total": 0.03013640199992551, "count": 1, "is_parallel": true, "self": 0.0003757389998781946, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026356399996529944, "count": 1, "is_parallel": true, "self": 0.00026356399996529944 }, "communicator.exchange": { "total": 0.02871988800006875, "count": 1, "is_parallel": true, "self": 0.02871988800006875 }, "steps_from_proto": { "total": 0.000777211000013267, "count": 1, "is_parallel": true, "self": 0.00021319000006769784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005640209999455692, "count": 2, "is_parallel": true, "self": 0.0005640209999455692 } } } } } } }, "UnityEnvironment.step": { "total": 1363.9259325059857, "count": 233507, "is_parallel": true, "self": 43.11084687091147, "children": { "UnityEnvironment._generate_step_input": { "total": 90.38090554091184, "count": 233507, "is_parallel": true, "self": 90.38090554091184 }, "communicator.exchange": { "total": 1133.6490552290347, "count": 233507, "is_parallel": true, "self": 1133.6490552290347 }, "steps_from_proto": { "total": 96.7851248651275, "count": 233507, "is_parallel": true, "self": 35.92114455319722, "children": { "_process_rank_one_or_two_observation": { "total": 60.86398031193028, "count": 467014, "is_parallel": true, "self": 60.86398031193028 } } } } } } } } } } }, "trainer_advance": { "total": 481.8723388478795, "count": 233508, "self": 7.074287624968065, "children": { "process_trajectory": { "total": 165.4044655019119, "count": 233508, "self": 164.14647294591134, "children": { "RLTrainer._checkpoint": { "total": 1.257992556000545, "count": 10, "self": 1.257992556000545 } } }, "_update_policy": { "total": 309.39358572099957, "count": 97, "self": 247.8379670789983, "children": { "TorchPPOOptimizer.update": { "total": 61.555618642001264, "count": 2910, "self": 61.555618642001264 } } } } } } }, "trainer_threads": { "total": 1.0030003068095539e-06, "count": 1, "self": 1.0030003068095539e-06 }, "TrainerController._save_models": { "total": 0.12104032299976097, "count": 1, "self": 0.002149330999600352, "children": { "RLTrainer._checkpoint": { "total": 0.11889099200016062, "count": 1, "self": 0.11889099200016062 } } } } } } }