{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4051772356033325, "min": 1.4051772356033325, "max": 1.4273061752319336, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69470.5546875, "min": 69470.5546875, "max": 76005.9453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 94.20190476190476, "min": 82.435, "max": 386.6046511627907, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49456.0, "min": 48783.0, "max": 50276.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999887.0, "min": 49642.0, "max": 1999887.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999887.0, "min": 49642.0, "max": 1999887.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.388550043106079, "min": 0.01902098022401333, "max": 2.469984769821167, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1253.98876953125, "min": 2.434685468673706, "max": 1441.755859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6827304706119355, "min": 1.639048013894353, "max": 3.9253491645913505, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1933.4334970712662, "min": 209.7981457784772, "max": 2316.7945279479027, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6827304706119355, "min": 1.639048013894353, "max": 3.9253491645913505, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1933.4334970712662, "min": 209.7981457784772, "max": 2316.7945279479027, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0178236319833862, "min": 0.014724919642806828, "max": 0.019780695398609775, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.053470895950158595, "min": 0.029449839285613656, "max": 0.05637154244856599, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052229482059677444, "min": 0.022948492877185346, "max": 0.05878663441787163, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15668844617903233, "min": 0.04589698575437069, "max": 0.16798016813894112, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.399998866699999e-06, "min": 3.399998866699999e-06, "max": 0.00029527560157479996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0199996600099997e-05, "min": 1.0199996600099997e-05, "max": 0.00084388276870575, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113329999999998, "min": 0.10113329999999998, "max": 0.19842520000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30339989999999994, "min": 0.20740379999999997, "max": 0.5812942500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.655167e-05, "min": 6.655167e-05, "max": 0.004921417480000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019965501, "min": 0.00019965501, "max": 0.014066583075000003, "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": "1712997424", "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": "1712999833" }, "total": 2408.567401628, "count": 1, "self": 0.8349859380000453, "children": { "run_training.setup": { "total": 0.053770941999971456, "count": 1, "self": 0.053770941999971456 }, "TrainerController.start_learning": { "total": 2407.678644748, "count": 1, "self": 3.984485574986593, "children": { "TrainerController._reset_env": { "total": 2.8831173119999676, "count": 1, "self": 2.8831173119999676 }, "TrainerController.advance": { "total": 2400.6388201570135, "count": 232365, "self": 4.386312885009829, "children": { "env_step": { "total": 1890.4695821809448, "count": 232365, "self": 1571.624090146022, "children": { "SubprocessEnvManager._take_step": { "total": 316.15528596295036, "count": 232365, "self": 16.879276630911193, "children": { "TorchPolicy.evaluate": { "total": 299.27600933203917, "count": 222966, "self": 299.27600933203917 } } }, "workers": { "total": 2.690206071972625, "count": 232365, "self": 0.0, "children": { "worker_root": { "total": 2400.3237156799923, "count": 232365, "is_parallel": true, "self": 1127.1843809200432, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009865769999919394, "count": 1, "is_parallel": true, "self": 0.00027182500002709276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007147519999648466, "count": 2, "is_parallel": true, "self": 0.0007147519999648466 } } }, "UnityEnvironment.step": { "total": 0.030388716999993903, "count": 1, "is_parallel": true, "self": 0.0004139840000334516, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002520119999758208, "count": 1, "is_parallel": true, "self": 0.0002520119999758208 }, "communicator.exchange": { "total": 0.02894879799998762, "count": 1, "is_parallel": true, "self": 0.02894879799998762 }, "steps_from_proto": { "total": 0.0007739229999970121, "count": 1, "is_parallel": true, "self": 0.00020926199999848905, "children": { "_process_rank_one_or_two_observation": { "total": 0.000564660999998523, "count": 2, "is_parallel": true, "self": 0.000564660999998523 } } } } } } }, "UnityEnvironment.step": { "total": 1273.1393347599492, "count": 232364, "is_parallel": true, "self": 39.46735792204595, "children": { "UnityEnvironment._generate_step_input": { "total": 84.65073569790167, "count": 232364, "is_parallel": true, "self": 84.65073569790167 }, "communicator.exchange": { "total": 1056.475654065034, "count": 232364, "is_parallel": true, "self": 1056.475654065034 }, "steps_from_proto": { "total": 92.54558707496761, "count": 232364, "is_parallel": true, "self": 34.79510471100758, "children": { "_process_rank_one_or_two_observation": { "total": 57.75048236396003, "count": 464728, "is_parallel": true, "self": 57.75048236396003 } } } } } } } } } } }, "trainer_advance": { "total": 505.78292509105876, "count": 232365, "self": 6.255313765022095, "children": { "process_trajectory": { "total": 149.32577701903625, "count": 232365, "self": 147.97124159903586, "children": { "RLTrainer._checkpoint": { "total": 1.3545354200003885, "count": 10, "self": 1.3545354200003885 } } }, "_update_policy": { "total": 350.2018343070004, "count": 97, "self": 286.5755058620018, "children": { "TorchPPOOptimizer.update": { "total": 63.62632844499859, "count": 2910, "self": 63.62632844499859 } } } } } } }, "trainer_threads": { "total": 1.5620003068761434e-06, "count": 1, "self": 1.5620003068761434e-06 }, "TrainerController._save_models": { "total": 0.1722201419997873, "count": 1, "self": 0.0028359289999571047, "children": { "RLTrainer._checkpoint": { "total": 0.1693842129998302, "count": 1, "self": 0.1693842129998302 } } } } } } }