{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.411855697631836, "min": 1.411855697631836, "max": 1.4308242797851562, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71205.53125, "min": 69423.0234375, "max": 77898.140625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 100.04040404040404, "min": 96.0701754385965, "max": 387.1860465116279, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49520.0, "min": 48833.0, "max": 50187.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999972.0, "min": 49747.0, "max": 1999972.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999972.0, "min": 49747.0, "max": 1999972.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3407883644104004, "min": 0.17893271148204803, "max": 2.4438838958740234, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1158.690185546875, "min": 22.90338706970215, "max": 1217.350341796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.503952991480779, "min": 1.7555299231316894, "max": 3.912839168471988, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1734.4567307829857, "min": 224.70783016085625, "max": 1997.805602312088, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.503952991480779, "min": 1.7555299231316894, "max": 3.912839168471988, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1734.4567307829857, "min": 224.70783016085625, "max": 1997.805602312088, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01358949675405812, "min": 0.01358949675405812, "max": 0.02161555243244872, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.040768490262174356, "min": 0.028967913011426087, "max": 0.05690311727084918, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05531397126615048, "min": 0.02207256533826391, "max": 0.05690772601713737, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16594191379845144, "min": 0.04414513067652782, "max": 0.16594191379845144, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2921989026333312e-06, "min": 3.2921989026333312e-06, "max": 0.0002953408515530499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.876596707899993e-06, "min": 9.876596707899993e-06, "max": 0.00084408736863755, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109736666666669, "min": 0.10109736666666669, "max": 0.19844695, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30329210000000006, "min": 0.20737619999999996, "max": 0.5813624500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.475859666666663e-05, "min": 6.475859666666663e-05, "max": 0.004922502805000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001942757899999999, "min": 0.0001942757899999999, "max": 0.014069986255, "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": "1691063907", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691066293" }, "total": 2386.108553264, "count": 1, "self": 0.7388051699999778, "children": { "run_training.setup": { "total": 0.043802008000000114, "count": 1, "self": 0.043802008000000114 }, "TrainerController.start_learning": { "total": 2385.325946086, "count": 1, "self": 4.124338472933232, "children": { "TrainerController._reset_env": { "total": 5.372092192000025, "count": 1, "self": 5.372092192000025 }, "TrainerController.advance": { "total": 2375.6450111010668, "count": 231605, "self": 4.487847753144251, "children": { "env_step": { "total": 1830.9679707649323, "count": 231605, "self": 1548.3225334949407, "children": { "SubprocessEnvManager._take_step": { "total": 279.78403516208135, "count": 231605, "self": 16.289131446046383, "children": { "TorchPolicy.evaluate": { "total": 263.49490371603497, "count": 223042, "self": 263.49490371603497 } } }, "workers": { "total": 2.861402107910294, "count": 231605, "self": 0.0, "children": { "worker_root": { "total": 2377.775874216015, "count": 231605, "is_parallel": true, "self": 1115.3295144109775, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000843082000017148, "count": 1, "is_parallel": true, "self": 0.0002567540000200097, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005863279999971382, "count": 2, "is_parallel": true, "self": 0.0005863279999971382 } } }, "UnityEnvironment.step": { "total": 0.029306976000043505, "count": 1, "is_parallel": true, "self": 0.00034483500002124856, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021085999998149418, "count": 1, "is_parallel": true, "self": 0.00021085999998149418 }, "communicator.exchange": { "total": 0.028041985000015757, "count": 1, "is_parallel": true, "self": 0.028041985000015757 }, "steps_from_proto": { "total": 0.0007092960000250059, "count": 1, "is_parallel": true, "self": 0.00020282600002019535, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005064700000048106, "count": 2, "is_parallel": true, "self": 0.0005064700000048106 } } } } } } }, "UnityEnvironment.step": { "total": 1262.4463598050374, "count": 231604, "is_parallel": true, "self": 40.03656163694518, "children": { "UnityEnvironment._generate_step_input": { "total": 80.49734916805551, "count": 231604, "is_parallel": true, "self": 80.49734916805551 }, "communicator.exchange": { "total": 1045.064046903054, "count": 231604, "is_parallel": true, "self": 1045.064046903054 }, "steps_from_proto": { "total": 96.84840209698262, "count": 231604, "is_parallel": true, "self": 34.33440164194974, "children": { "_process_rank_one_or_two_observation": { "total": 62.514000455032885, "count": 463208, "is_parallel": true, "self": 62.514000455032885 } } } } } } } } } } }, "trainer_advance": { "total": 540.18919258299, "count": 231605, "self": 6.4177552130252025, "children": { "process_trajectory": { "total": 132.87802964196374, "count": 231605, "self": 131.4359007339648, "children": { "RLTrainer._checkpoint": { "total": 1.4421289079989492, "count": 10, "self": 1.4421289079989492 } } }, "_update_policy": { "total": 400.893407728001, "count": 97, "self": 341.49195470000865, "children": { "TorchPPOOptimizer.update": { "total": 59.401453027992375, "count": 2910, "self": 59.401453027992375 } } } } } } }, "trainer_threads": { "total": 1.2800001059076749e-06, "count": 1, "self": 1.2800001059076749e-06 }, "TrainerController._save_models": { "total": 0.1845030399999814, "count": 1, "self": 0.002609674000268569, "children": { "RLTrainer._checkpoint": { "total": 0.18189336599971284, "count": 1, "self": 0.18189336599971284 } } } } } } }