{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.407679796218872, "min": 1.407679796218872, "max": 1.4301629066467285, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71094.8671875, "min": 68419.3671875, "max": 77362.5234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.79437609841828, "min": 86.79437609841828, "max": 389.734375, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49386.0, "min": 48899.0, "max": 50254.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999913.0, "min": 49366.0, "max": 1999913.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999913.0, "min": 49366.0, "max": 1999913.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.357203960418701, "min": 0.167366161942482, "max": 2.4059157371520996, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1341.2490234375, "min": 21.255502700805664, "max": 1341.2490234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6904028551440247, "min": 1.6970080755592332, "max": 3.7989962882720505, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2099.83922457695, "min": 215.5200255960226, "max": 2099.83922457695, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6904028551440247, "min": 1.6970080755592332, "max": 3.7989962882720505, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2099.83922457695, "min": 215.5200255960226, "max": 2099.83922457695, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01629528328692484, "min": 0.013966212215988587, "max": 0.01943247234351778, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048885849860774516, "min": 0.027932424431977174, "max": 0.05727729689582095, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05579776490728061, "min": 0.02173708661769827, "max": 0.059353924542665484, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16739329472184183, "min": 0.04347417323539654, "max": 0.16958089545369148, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2922489026166706e-06, "min": 3.2922489026166706e-06, "max": 0.00029535517654827494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.876746707850012e-06, "min": 9.876746707850012e-06, "max": 0.00084429646856785, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109738333333335, "min": 0.10109738333333335, "max": 0.19845172500000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30329215000000004, "min": 0.20732159999999994, "max": 0.5814321500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.475942833333342e-05, "min": 6.475942833333342e-05, "max": 0.004922741077499998, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019427828500000026, "min": 0.00019427828500000026, "max": 0.014073464285, "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": "1751056479", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751058898" }, "total": 2418.857470901, "count": 1, "self": 0.44167261699976734, "children": { "run_training.setup": { "total": 0.02256287099999099, "count": 1, "self": 0.02256287099999099 }, "TrainerController.start_learning": { "total": 2418.393235413, "count": 1, "self": 3.9972545061673372, "children": { "TrainerController._reset_env": { "total": 3.042409879000047, "count": 1, "self": 3.042409879000047 }, "TrainerController.advance": { "total": 2411.2334817118326, "count": 231760, "self": 4.360121583766158, "children": { "env_step": { "total": 1942.2474736490472, "count": 231760, "self": 1534.037354842032, "children": { "SubprocessEnvManager._take_step": { "total": 405.58903418499744, "count": 231760, "self": 14.765668730032814, "children": { "TorchPolicy.evaluate": { "total": 390.82336545496463, "count": 222963, "self": 390.82336545496463 } } }, "workers": { "total": 2.6210846220176904, "count": 231760, "self": 0.0, "children": { "worker_root": { "total": 2410.7620653849435, "count": 231760, "is_parallel": true, "self": 1156.7484319130106, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008323380000092584, "count": 1, "is_parallel": true, "self": 0.0002334060000066529, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005989320000026055, "count": 2, "is_parallel": true, "self": 0.0005989320000026055 } } }, "UnityEnvironment.step": { "total": 0.029235778999975537, "count": 1, "is_parallel": true, "self": 0.0003229700000133562, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002037299999528841, "count": 1, "is_parallel": true, "self": 0.0002037299999528841 }, "communicator.exchange": { "total": 0.028000861000009536, "count": 1, "is_parallel": true, "self": 0.028000861000009536 }, "steps_from_proto": { "total": 0.0007082179999997607, "count": 1, "is_parallel": true, "self": 0.00018762300004482313, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005205949999549375, "count": 2, "is_parallel": true, "self": 0.0005205949999549375 } } } } } } }, "UnityEnvironment.step": { "total": 1254.013633471933, "count": 231759, "is_parallel": true, "self": 37.26807175794511, "children": { "UnityEnvironment._generate_step_input": { "total": 81.210868054032, "count": 231759, "is_parallel": true, "self": 81.210868054032 }, "communicator.exchange": { "total": 1047.6488254179449, "count": 231759, "is_parallel": true, "self": 1047.6488254179449 }, "steps_from_proto": { "total": 87.88586824201093, "count": 231759, "is_parallel": true, "self": 32.71541010608121, "children": { "_process_rank_one_or_two_observation": { "total": 55.17045813592972, "count": 463518, "is_parallel": true, "self": 55.17045813592972 } } } } } } } } } } }, "trainer_advance": { "total": 464.62588647901913, "count": 231760, "self": 6.395886998999629, "children": { "process_trajectory": { "total": 151.92222341002127, "count": 231760, "self": 150.6457352370203, "children": { "RLTrainer._checkpoint": { "total": 1.2764881730009847, "count": 10, "self": 1.2764881730009847 } } }, "_update_policy": { "total": 306.3077760699982, "count": 97, "self": 243.96280770398914, "children": { "TorchPPOOptimizer.update": { "total": 62.344968366009084, "count": 2910, "self": 62.344968366009084 } } } } } } }, "trainer_threads": { "total": 1.0510002539376728e-06, "count": 1, "self": 1.0510002539376728e-06 }, "TrainerController._save_models": { "total": 0.12008826500004943, "count": 1, "self": 0.0016755290002947731, "children": { "RLTrainer._checkpoint": { "total": 0.11841273599975466, "count": 1, "self": 0.11841273599975466 } } } } } } }