{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4061949253082275, "min": 1.4061949253082275, "max": 1.428806185722351, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70439.1171875, "min": 66993.6875, "max": 79390.40625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.19155844155844, "min": 77.55974842767296, "max": 381.7121212121212, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49398.0, "min": 49246.0, "max": 50386.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999985.0, "min": 49846.0, "max": 1999985.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999985.0, "min": 49846.0, "max": 1999985.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4633920192718506, "min": 0.07754732668399811, "max": 2.4793941974639893, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1517.449462890625, "min": 10.158699989318848, "max": 1557.097412109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8544143664759476, "min": 1.658921213550422, "max": 3.9689928037690416, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2374.3192497491837, "min": 217.31867897510529, "max": 2467.7699859142303, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8544143664759476, "min": 1.658921213550422, "max": 3.9689928037690416, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2374.3192497491837, "min": 217.31867897510529, "max": 2467.7699859142303, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016867721045532056, "min": 0.01369451576449339, "max": 0.021641358135578534, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05060316313659617, "min": 0.02927570958175541, "max": 0.05901323286428427, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05751652382314206, "min": 0.020910785812884566, "max": 0.06183057820631397, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17254957146942618, "min": 0.04182157162576913, "max": 0.18549173461894192, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.622298792599997e-06, "min": 3.622298792599997e-06, "max": 0.00029533740155419995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0866896377799991e-05, "min": 1.0866896377799991e-05, "max": 0.0008440689186437, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012074, "min": 0.1012074, "max": 0.1984458, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036222, "min": 0.20754709999999996, "max": 0.5813563000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.024925999999996e-05, "min": 7.024925999999996e-05, "max": 0.004922445420000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002107477799999999, "min": 0.0002107477799999999, "max": 0.014069679370000001, "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": "1740579111", "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": "1740581591" }, "total": 2480.518580837, "count": 1, "self": 0.43680946100039364, "children": { "run_training.setup": { "total": 0.022519378999959372, "count": 1, "self": 0.022519378999959372 }, "TrainerController.start_learning": { "total": 2480.059251997, "count": 1, "self": 4.424173825997059, "children": { "TrainerController._reset_env": { "total": 2.9615190939998683, "count": 1, "self": 2.9615190939998683 }, "TrainerController.advance": { "total": 2472.5639780340034, "count": 232990, "self": 4.661602459082587, "children": { "env_step": { "total": 1971.0664311089404, "count": 232990, "self": 1543.194001414837, "children": { "SubprocessEnvManager._take_step": { "total": 425.13538695610805, "count": 232990, "self": 15.814213280197691, "children": { "TorchPolicy.evaluate": { "total": 409.32117367591036, "count": 222947, "self": 409.32117367591036 } } }, "workers": { "total": 2.7370427379953526, "count": 232990, "self": 0.0, "children": { "worker_root": { "total": 2472.5362409118966, "count": 232990, "is_parallel": true, "self": 1213.601602025951, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010965740000301594, "count": 1, "is_parallel": true, "self": 0.0004190849999758939, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006774890000542655, "count": 2, "is_parallel": true, "self": 0.0006774890000542655 } } }, "UnityEnvironment.step": { "total": 0.029819086000088646, "count": 1, "is_parallel": true, "self": 0.00033816800009844883, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002041440000084549, "count": 1, "is_parallel": true, "self": 0.0002041440000084549 }, "communicator.exchange": { "total": 0.0285257369998817, "count": 1, "is_parallel": true, "self": 0.0285257369998817 }, "steps_from_proto": { "total": 0.000751037000100041, "count": 1, "is_parallel": true, "self": 0.00020069300012437452, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005503439999756665, "count": 2, "is_parallel": true, "self": 0.0005503439999756665 } } } } } } }, "UnityEnvironment.step": { "total": 1258.9346388859456, "count": 232989, "is_parallel": true, "self": 37.89016139906221, "children": { "UnityEnvironment._generate_step_input": { "total": 82.0430613989422, "count": 232989, "is_parallel": true, "self": 82.0430613989422 }, "communicator.exchange": { "total": 1050.3664119119733, "count": 232989, "is_parallel": true, "self": 1050.3664119119733 }, "steps_from_proto": { "total": 88.63500417596788, "count": 232989, "is_parallel": true, "self": 32.96227067701989, "children": { "_process_rank_one_or_two_observation": { "total": 55.67273349894799, "count": 465978, "is_parallel": true, "self": 55.67273349894799 } } } } } } } } } } }, "trainer_advance": { "total": 496.83594446598045, "count": 232990, "self": 6.616657763969215, "children": { "process_trajectory": { "total": 167.5478679360101, "count": 232990, "self": 166.13498324201032, "children": { "RLTrainer._checkpoint": { "total": 1.4128846939997857, "count": 10, "self": 1.4128846939997857 } } }, "_update_policy": { "total": 322.6714187660011, "count": 97, "self": 247.11360122899555, "children": { "TorchPPOOptimizer.update": { "total": 75.55781753700558, "count": 2910, "self": 75.55781753700558 } } } } } } }, "trainer_threads": { "total": 8.779998097452335e-07, "count": 1, "self": 8.779998097452335e-07 }, "TrainerController._save_models": { "total": 0.10958016499989753, "count": 1, "self": 0.002114013999744202, "children": { "RLTrainer._checkpoint": { "total": 0.10746615100015333, "count": 1, "self": 0.10746615100015333 } } } } } } }