{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405578851699829, "min": 1.405578851699829, "max": 1.42765474319458, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70224.125, "min": 68089.46875, "max": 76590.6796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.58676207513417, "min": 87.17813051146385, "max": 376.32835820895525, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49520.0, "min": 49021.0, "max": 50428.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999974.0, "min": 49861.0, "max": 1999974.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999974.0, "min": 49861.0, "max": 1999974.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.382909059524536, "min": 0.08405806869268417, "max": 2.4139328002929688, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1332.046142578125, "min": 11.179722785949707, "max": 1332.490966796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6942611291924616, "min": 1.864387382466094, "max": 3.9058287905043914, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2065.091971218586, "min": 247.9635218679905, "max": 2105.9693947434425, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6942611291924616, "min": 1.864387382466094, "max": 3.9058287905043914, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2065.091971218586, "min": 247.9635218679905, "max": 2105.9693947434425, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016605567320948467, "min": 0.011083736743118303, "max": 0.020841702306643128, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0498167019628454, "min": 0.022167473486236607, "max": 0.05762142878168865, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05212080391744773, "min": 0.023603162914514544, "max": 0.06528775487095118, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1563624117523432, "min": 0.04720632582902909, "max": 0.18773240422209103, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.0978489674166666e-06, "min": 3.0978489674166666e-06, "max": 0.000295310476563175, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.29354690225e-06, "min": 9.29354690225e-06, "max": 0.0008440152186615997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10103258333333336, "min": 0.10103258333333336, "max": 0.19843682499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30309775000000005, "min": 0.20724864999999998, "max": 0.5813384000000003, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.152590833333332e-05, "min": 6.152590833333332e-05, "max": 0.004921997567499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018457772499999995, "min": 0.00018457772499999995, "max": 0.014068786160000001, "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": "1717880789", "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=Huggy --no-graphics --force", "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": "1717883179" }, "total": 2389.7834278480004, "count": 1, "self": 0.4760830090008312, "children": { "run_training.setup": { "total": 0.05962850299988531, "count": 1, "self": 0.05962850299988531 }, "TrainerController.start_learning": { "total": 2389.247716336, "count": 1, "self": 4.58225949800908, "children": { "TrainerController._reset_env": { "total": 2.1811601100000644, "count": 1, "self": 2.1811601100000644 }, "TrainerController.advance": { "total": 2382.368540422991, "count": 231725, "self": 4.536303358121586, "children": { "env_step": { "total": 1891.2274800859436, "count": 231725, "self": 1564.0824297349025, "children": { "SubprocessEnvManager._take_step": { "total": 324.39430587810125, "count": 231725, "self": 18.21315752712917, "children": { "TorchPolicy.evaluate": { "total": 306.1811483509721, "count": 222870, "self": 306.1811483509721 } } }, "workers": { "total": 2.750744472939914, "count": 231725, "self": 0.0, "children": { "worker_root": { "total": 2382.287323323077, "count": 231725, "is_parallel": true, "self": 1120.7946144630532, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007594260000587383, "count": 1, "is_parallel": true, "self": 0.00018563699995866045, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005737890001000778, "count": 2, "is_parallel": true, "self": 0.0005737890001000778 } } }, "UnityEnvironment.step": { "total": 0.029915981000158354, "count": 1, "is_parallel": true, "self": 0.00039821700033826346, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001948499998434272, "count": 1, "is_parallel": true, "self": 0.0001948499998434272 }, "communicator.exchange": { "total": 0.02855415399994854, "count": 1, "is_parallel": true, "self": 0.02855415399994854 }, "steps_from_proto": { "total": 0.0007687600000281236, "count": 1, "is_parallel": true, "self": 0.00020259100028852117, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005661689997396024, "count": 2, "is_parallel": true, "self": 0.0005661689997396024 } } } } } } }, "UnityEnvironment.step": { "total": 1261.4927088600239, "count": 231724, "is_parallel": true, "self": 38.7478468568936, "children": { "UnityEnvironment._generate_step_input": { "total": 80.83702966303508, "count": 231724, "is_parallel": true, "self": 80.83702966303508 }, "communicator.exchange": { "total": 1054.0739899361354, "count": 231724, "is_parallel": true, "self": 1054.0739899361354 }, "steps_from_proto": { "total": 87.8338424039598, "count": 231724, "is_parallel": true, "self": 30.986908631077085, "children": { "_process_rank_one_or_two_observation": { "total": 56.84693377288272, "count": 463448, "is_parallel": true, "self": 56.84693377288272 } } } } } } } } } } }, "trainer_advance": { "total": 486.6047569789257, "count": 231725, "self": 6.6584360090234895, "children": { "process_trajectory": { "total": 150.7991070469052, "count": 231725, "self": 149.59344616890485, "children": { "RLTrainer._checkpoint": { "total": 1.2056608780003444, "count": 10, "self": 1.2056608780003444 } } }, "_update_policy": { "total": 329.147213922997, "count": 97, "self": 265.62121607000336, "children": { "TorchPPOOptimizer.update": { "total": 63.52599785299367, "count": 2910, "self": 63.52599785299367 } } } } } } }, "trainer_threads": { "total": 7.799999366397969e-07, "count": 1, "self": 7.799999366397969e-07 }, "TrainerController._save_models": { "total": 0.11575552500016784, "count": 1, "self": 0.0029236260002107883, "children": { "RLTrainer._checkpoint": { "total": 0.11283189899995705, "count": 1, "self": 0.11283189899995705 } } } } } } }