{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4053529500961304, "min": 1.4053529500961304, "max": 1.424031138420105, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70142.5703125, "min": 68705.078125, "max": 76578.328125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 111.53897550111358, "min": 79.49436392914654, "max": 367.2335766423358, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50081.0, "min": 48937.0, "max": 50311.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999814.0, "min": 49722.0, "max": 1999814.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999814.0, "min": 49722.0, "max": 1999814.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.28550386428833, "min": 0.0055274683982133865, "max": 2.4906303882598877, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1026.1912841796875, "min": 0.7517356872558594, "max": 1511.8126220703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.339474959601804, "min": 1.9003580822883284, "max": 3.943976200789213, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1499.4242568612099, "min": 258.44869919121265, "max": 2371.274690926075, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.339474959601804, "min": 1.9003580822883284, "max": 3.943976200789213, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1499.4242568612099, "min": 258.44869919121265, "max": 2371.274690926075, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01878485146444291, "min": 0.014054035369190386, "max": 0.01992341648438014, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.056354554393328725, "min": 0.028108070738380772, "max": 0.056354554393328725, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04224829528894689, "min": 0.022202274141212307, "max": 0.05938824725647768, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.12674488586684068, "min": 0.044404548282424613, "max": 0.1769504292557637, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6610987796666813e-06, "min": 3.6610987796666813e-06, "max": 0.0002953233765588749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0983296339000044e-05, "min": 1.0983296339000044e-05, "max": 0.00084375226874925, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122033333333336, "min": 0.10122033333333336, "max": 0.198441125, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30366100000000007, "min": 0.20758829999999998, "max": 0.58125075, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.089463333333359e-05, "min": 7.089463333333359e-05, "max": 0.0049222121375000006, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021268390000000076, "min": 0.00021268390000000076, "max": 0.014064412424999999, "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": "1720079386", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720081756" }, "total": 2369.3723615730005, "count": 1, "self": 0.43655826000031084, "children": { "run_training.setup": { "total": 0.05496719600000688, "count": 1, "self": 0.05496719600000688 }, "TrainerController.start_learning": { "total": 2368.8808361170004, "count": 1, "self": 4.2655632270443675, "children": { "TrainerController._reset_env": { "total": 3.033848429999807, "count": 1, "self": 3.033848429999807 }, "TrainerController.advance": { "total": 2361.4671075719566, "count": 232582, "self": 4.704372830014563, "children": { "env_step": { "total": 1872.0850678009515, "count": 232582, "self": 1544.77206958592, "children": { "SubprocessEnvManager._take_step": { "total": 324.55786256796387, "count": 232582, "self": 16.659907184988242, "children": { "TorchPolicy.evaluate": { "total": 307.8979553829756, "count": 223096, "self": 307.8979553829756 } } }, "workers": { "total": 2.7551356470676183, "count": 232582, "self": 0.0, "children": { "worker_root": { "total": 2361.985879603041, "count": 232582, "is_parallel": true, "self": 1117.4624190800741, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008824099998037127, "count": 1, "is_parallel": true, "self": 0.00021107799989295017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006713319999107625, "count": 2, "is_parallel": true, "self": 0.0006713319999107625 } } }, "UnityEnvironment.step": { "total": 0.028848301999914838, "count": 1, "is_parallel": true, "self": 0.0003987759998835827, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021645500009981333, "count": 1, "is_parallel": true, "self": 0.00021645500009981333 }, "communicator.exchange": { "total": 0.027435596000032092, "count": 1, "is_parallel": true, "self": 0.027435596000032092 }, "steps_from_proto": { "total": 0.0007974749998993502, "count": 1, "is_parallel": true, "self": 0.00020721000009871204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005902649998006382, "count": 2, "is_parallel": true, "self": 0.0005902649998006382 } } } } } } }, "UnityEnvironment.step": { "total": 1244.523460522967, "count": 232581, "is_parallel": true, "self": 38.723895131040535, "children": { "UnityEnvironment._generate_step_input": { "total": 80.15313715394313, "count": 232581, "is_parallel": true, "self": 80.15313715394313 }, "communicator.exchange": { "total": 1037.6235671989937, "count": 232581, "is_parallel": true, "self": 1037.6235671989937 }, "steps_from_proto": { "total": 88.02286103898973, "count": 232581, "is_parallel": true, "self": 31.04476729608905, "children": { "_process_rank_one_or_two_observation": { "total": 56.97809374290068, "count": 465162, "is_parallel": true, "self": 56.97809374290068 } } } } } } } } } } }, "trainer_advance": { "total": 484.6776669409908, "count": 232582, "self": 6.27971475093409, "children": { "process_trajectory": { "total": 153.37070655705907, "count": 232582, "self": 152.01025161306052, "children": { "RLTrainer._checkpoint": { "total": 1.3604549439985476, "count": 10, "self": 1.3604549439985476 } } }, "_update_policy": { "total": 325.0272456329976, "count": 97, "self": 262.004885011002, "children": { "TorchPPOOptimizer.update": { "total": 63.02236062199563, "count": 2910, "self": 63.02236062199563 } } } } } } }, "trainer_threads": { "total": 9.209998097503558e-07, "count": 1, "self": 9.209998097503558e-07 }, "TrainerController._save_models": { "total": 0.11431596700003865, "count": 1, "self": 0.0018835050000234332, "children": { "RLTrainer._checkpoint": { "total": 0.11243246200001522, "count": 1, "self": 0.11243246200001522 } } } } } } }