{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.407397747039795, "min": 1.407397747039795, "max": 1.4302948713302612, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70955.3671875, "min": 68650.296875, "max": 75728.8984375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.55818540433926, "min": 95.64285714285714, "max": 397.85714285714283, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49462.0, "min": 48962.0, "max": 50161.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999986.0, "min": 49984.0, "max": 1999986.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999986.0, "min": 49984.0, "max": 1999986.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.335977077484131, "min": 0.07285836338996887, "max": 2.3981521129608154, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1184.34033203125, "min": 9.107295036315918, "max": 1222.674560546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6693211799777705, "min": 1.6755211312770844, "max": 3.8515093579720916, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1860.3458382487297, "min": 209.44014140963554, "max": 1897.9761727452278, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6693211799777705, "min": 1.6755211312770844, "max": 3.8515093579720916, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1860.3458382487297, "min": 209.44014140963554, "max": 1897.9761727452278, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017285438266763875, "min": 0.013470993131583477, "max": 0.019835764101298992, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051856314800291625, "min": 0.026941986263166955, "max": 0.05674874803225975, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053169313859608436, "min": 0.02229792969301343, "max": 0.06285270758801036, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1595079415788253, "min": 0.04459585938602686, "max": 0.18855812276403108, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1927989357666696e-06, "min": 3.1927989357666696e-06, "max": 0.0002952892515702499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.57839680730001e-06, "min": 9.57839680730001e-06, "max": 0.0008438781187073, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10106423333333332, "min": 0.10106423333333332, "max": 0.19842974999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031927, "min": 0.20730295000000004, "max": 0.5812927, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.310524333333341e-05, "min": 6.310524333333341e-05, "max": 0.004921644524999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001893157300000002, "min": 0.0001893157300000002, "max": 0.014066505730000001, "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": "1710678233", "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", "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": "1710682970" }, "total": 4736.609298211, "count": 1, "self": 0.7582033020007657, "children": { "run_training.setup": { "total": 0.09921691599998894, "count": 1, "self": 0.09921691599998894 }, "TrainerController.start_learning": { "total": 4735.751877993, "count": 1, "self": 8.328960557954815, "children": { "TrainerController._reset_env": { "total": 3.5132960760000174, "count": 1, "self": 3.5132960760000174 }, "TrainerController.advance": { "total": 4723.770473951045, "count": 230993, "self": 8.314480971152989, "children": { "env_step": { "total": 3098.361428898874, "count": 230993, "self": 2592.3831735149174, "children": { "SubprocessEnvManager._take_step": { "total": 500.3376112089813, "count": 230993, "self": 33.75135027087782, "children": { "TorchPolicy.evaluate": { "total": 466.58626093810346, "count": 222940, "self": 466.58626093810346 } } }, "workers": { "total": 5.640644174974966, "count": 230993, "self": 0.0, "children": { "worker_root": { "total": 4719.99195955301, "count": 230993, "is_parallel": true, "self": 2654.7438120491674, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011704959999860876, "count": 1, "is_parallel": true, "self": 0.0003484549999370756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008220410000490119, "count": 2, "is_parallel": true, "self": 0.0008220410000490119 } } }, "UnityEnvironment.step": { "total": 0.0350560660000383, "count": 1, "is_parallel": true, "self": 0.00048153000000183965, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002134940000360075, "count": 1, "is_parallel": true, "self": 0.0002134940000360075 }, "communicator.exchange": { "total": 0.033471292999990965, "count": 1, "is_parallel": true, "self": 0.033471292999990965 }, "steps_from_proto": { "total": 0.0008897490000094876, "count": 1, "is_parallel": true, "self": 0.00024306499994963815, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006466840000598495, "count": 2, "is_parallel": true, "self": 0.0006466840000598495 } } } } } } }, "UnityEnvironment.step": { "total": 2065.2481475038426, "count": 230992, "is_parallel": true, "self": 64.06096843088335, "children": { "UnityEnvironment._generate_step_input": { "total": 97.95385488411262, "count": 230992, "is_parallel": true, "self": 97.95385488411262 }, "communicator.exchange": { "total": 1762.0134648348646, "count": 230992, "is_parallel": true, "self": 1762.0134648348646 }, "steps_from_proto": { "total": 141.21985935398197, "count": 230992, "is_parallel": true, "self": 45.69305181215316, "children": { "_process_rank_one_or_two_observation": { "total": 95.52680754182882, "count": 461984, "is_parallel": true, "self": 95.52680754182882 } } } } } } } } } } }, "trainer_advance": { "total": 1617.0945640810176, "count": 230993, "self": 13.764480397001535, "children": { "process_trajectory": { "total": 248.2113524720155, "count": 230993, "self": 246.80791980601452, "children": { "RLTrainer._checkpoint": { "total": 1.403432666000981, "count": 10, "self": 1.403432666000981 } } }, "_update_policy": { "total": 1355.1187312120005, "count": 97, "self": 339.82863187700536, "children": { "TorchPPOOptimizer.update": { "total": 1015.2900993349951, "count": 2910, "self": 1015.2900993349951 } } } } } } }, "trainer_threads": { "total": 1.0560006558080204e-06, "count": 1, "self": 1.0560006558080204e-06 }, "TrainerController._save_models": { "total": 0.13914635199944314, "count": 1, "self": 0.00695762699979241, "children": { "RLTrainer._checkpoint": { "total": 0.13218872499965073, "count": 1, "self": 0.13218872499965073 } } } } } } }