{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4000873565673828, "min": 1.4000873565673828, "max": 1.4272903203964233, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70512.6015625, "min": 68431.46875, "max": 78452.5, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.32451499118166, "min": 83.50417362270451, "max": 403.9596774193548, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48946.0, "min": 48853.0, "max": 50255.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999929.0, "min": 49821.0, "max": 1999929.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999929.0, "min": 49821.0, "max": 1999929.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4038240909576416, "min": 0.15023121237754822, "max": 2.464804172515869, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1362.96826171875, "min": 18.478439331054688, "max": 1431.8812255859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7209291462334795, "min": 1.8459960905517019, "max": 3.9360525790525944, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2109.766825914383, "min": 227.05751913785934, "max": 2275.6392656564713, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7209291462334795, "min": 1.8459960905517019, "max": 3.9360525790525944, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2109.766825914383, "min": 227.05751913785934, "max": 2275.6392656564713, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01836405183405279, "min": 0.013874929760640952, "max": 0.020781561850001, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.055092155502158374, "min": 0.027749859521281905, "max": 0.062344685550003, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.050463980312148736, "min": 0.022099984561403593, "max": 0.06192957895497481, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1513919409364462, "min": 0.04419996912280719, "max": 0.1825288739055395, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2770989076666635e-06, "min": 3.2770989076666635e-06, "max": 0.0002953722015426, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.831296722999991e-06, "min": 9.831296722999991e-06, "max": 0.0008441500686166498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109233333333334, "min": 0.10109233333333334, "max": 0.19845740000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.303277, "min": 0.20735330000000007, "max": 0.5813833500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.45074333333333e-05, "min": 6.45074333333333e-05, "max": 0.0049230242600000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001935222999999999, "min": 0.0001935222999999999, "max": 0.014071029165000002, "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": "1715072280", "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": "1715074710" }, "total": 2429.7160481009996, "count": 1, "self": 0.4380873549998796, "children": { "run_training.setup": { "total": 0.07592097999997804, "count": 1, "self": 0.07592097999997804 }, "TrainerController.start_learning": { "total": 2429.202039766, "count": 1, "self": 4.158785252990583, "children": { "TrainerController._reset_env": { "total": 3.132884511000043, "count": 1, "self": 3.132884511000043 }, "TrainerController.advance": { "total": 2421.7768705920093, "count": 231924, "self": 4.4771360121235375, "children": { "env_step": { "total": 1923.4283676530295, "count": 231924, "self": 1599.2910269472459, "children": { "SubprocessEnvManager._take_step": { "total": 321.2287182058408, "count": 231924, "self": 16.498659838810795, "children": { "TorchPolicy.evaluate": { "total": 304.73005836703, "count": 223000, "self": 304.73005836703 } } }, "workers": { "total": 2.908622499942794, "count": 231924, "self": 0.0, "children": { "worker_root": { "total": 2422.0338757880313, "count": 231924, "is_parallel": true, "self": 1124.8649841171468, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008838769999783835, "count": 1, "is_parallel": true, "self": 0.00023437499999090505, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006495019999874785, "count": 2, "is_parallel": true, "self": 0.0006495019999874785 } } }, "UnityEnvironment.step": { "total": 0.02853839900001276, "count": 1, "is_parallel": true, "self": 0.00036678399987977173, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022199600005023967, "count": 1, "is_parallel": true, "self": 0.00022199600005023967 }, "communicator.exchange": { "total": 0.027220484000054057, "count": 1, "is_parallel": true, "self": 0.027220484000054057 }, "steps_from_proto": { "total": 0.0007291350000286911, "count": 1, "is_parallel": true, "self": 0.00018496300003789656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005441719999907946, "count": 2, "is_parallel": true, "self": 0.0005441719999907946 } } } } } } }, "UnityEnvironment.step": { "total": 1297.1688916708845, "count": 231923, "is_parallel": true, "self": 39.64369928562246, "children": { "UnityEnvironment._generate_step_input": { "total": 84.08783328206675, "count": 231923, "is_parallel": true, "self": 84.08783328206675 }, "communicator.exchange": { "total": 1081.0972555811463, "count": 231923, "is_parallel": true, "self": 1081.0972555811463 }, "steps_from_proto": { "total": 92.34010352204916, "count": 231923, "is_parallel": true, "self": 32.9379749248144, "children": { "_process_rank_one_or_two_observation": { "total": 59.402128597234764, "count": 463846, "is_parallel": true, "self": 59.402128597234764 } } } } } } } } } } }, "trainer_advance": { "total": 493.87136692685624, "count": 231924, "self": 6.247529104817659, "children": { "process_trajectory": { "total": 148.95564314803755, "count": 231924, "self": 147.57798028203865, "children": { "RLTrainer._checkpoint": { "total": 1.3776628659989, "count": 10, "self": 1.3776628659989 } } }, "_update_policy": { "total": 338.66819467400103, "count": 97, "self": 274.6129243950086, "children": { "TorchPPOOptimizer.update": { "total": 64.05527027899245, "count": 2910, "self": 64.05527027899245 } } } } } } }, "trainer_threads": { "total": 9.219997991749551e-07, "count": 1, "self": 9.219997991749551e-07 }, "TrainerController._save_models": { "total": 0.13349848799998654, "count": 1, "self": 0.00527463699972941, "children": { "RLTrainer._checkpoint": { "total": 0.12822385100025713, "count": 1, "self": 0.12822385100025713 } } } } } } }