{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4076839685440063, "min": 1.4076839685440063, "max": 1.4273782968521118, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70713.59375, "min": 66865.5859375, "max": 76800.265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.17283950617283, "min": 80.8983606557377, "max": 405.9349593495935, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49427.0, "min": 49118.0, "max": 49930.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999969.0, "min": 49489.0, "max": 1999969.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999969.0, "min": 49489.0, "max": 1999969.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4118540287017822, "min": 0.11857007443904877, "max": 2.483100175857544, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1367.521240234375, "min": 14.46554946899414, "max": 1441.6251220703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.634751214972669, "min": 1.918504501463937, "max": 3.8935070421014513, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2060.9039388895035, "min": 234.0575491786003, "max": 2277.919889986515, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.634751214972669, "min": 1.918504501463937, "max": 3.8935070421014513, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2060.9039388895035, "min": 234.0575491786003, "max": 2277.919889986515, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018941896080408093, "min": 0.01316987810326585, "max": 0.019013619855589546, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.056825688241224276, "min": 0.0263397562065317, "max": 0.056825688241224276, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05515140336420801, "min": 0.021185753277192514, "max": 0.058272507538398105, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16545421009262404, "min": 0.04237150655438503, "max": 0.17481752261519432, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3741988752999916e-06, "min": 3.3741988752999916e-06, "max": 0.00029535195154935007, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0122596625899974e-05, "min": 1.0122596625899974e-05, "max": 0.0008439133686955501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011247, "min": 0.1011247, "max": 0.19845064999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033741, "min": 0.20737464999999997, "max": 0.5813044499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.612252999999988e-05, "min": 6.612252999999988e-05, "max": 0.004922687435, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019836758999999961, "min": 0.00019836758999999961, "max": 0.014067092055000001, "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": "1736855364", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736857844" }, "total": 2480.5323384430003, "count": 1, "self": 0.4253321130004224, "children": { "run_training.setup": { "total": 0.06664556199996241, "count": 1, "self": 0.06664556199996241 }, "TrainerController.start_learning": { "total": 2480.040360768, "count": 1, "self": 4.593331992012736, "children": { "TrainerController._reset_env": { "total": 5.087888686000042, "count": 1, "self": 5.087888686000042 }, "TrainerController.advance": { "total": 2470.2406332419873, "count": 232243, "self": 4.650666502956028, "children": { "env_step": { "total": 1961.3293670011299, "count": 232243, "self": 1536.3938157660455, "children": { "SubprocessEnvManager._take_step": { "total": 422.05173679898905, "count": 232243, "self": 16.177682779978, "children": { "TorchPolicy.evaluate": { "total": 405.87405401901106, "count": 222948, "self": 405.87405401901106 } } }, "workers": { "total": 2.883814436095463, "count": 232243, "self": 0.0, "children": { "worker_root": { "total": 2472.5138606450273, "count": 232243, "is_parallel": true, "self": 1222.8821185460401, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010725289999982124, "count": 1, "is_parallel": true, "self": 0.00033253099991270574, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007399980000855066, "count": 2, "is_parallel": true, "self": 0.0007399980000855066 } } }, "UnityEnvironment.step": { "total": 0.03126653200001783, "count": 1, "is_parallel": true, "self": 0.00037997899994479667, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019361200008916057, "count": 1, "is_parallel": true, "self": 0.00019361200008916057 }, "communicator.exchange": { "total": 0.02992375799999536, "count": 1, "is_parallel": true, "self": 0.02992375799999536 }, "steps_from_proto": { "total": 0.0007691829999885158, "count": 1, "is_parallel": true, "self": 0.0002183609999519831, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005508220000365327, "count": 2, "is_parallel": true, "self": 0.0005508220000365327 } } } } } } }, "UnityEnvironment.step": { "total": 1249.6317420989872, "count": 232242, "is_parallel": true, "self": 38.0551456421008, "children": { "UnityEnvironment._generate_step_input": { "total": 82.28491149802244, "count": 232242, "is_parallel": true, "self": 82.28491149802244 }, "communicator.exchange": { "total": 1038.7366809119135, "count": 232242, "is_parallel": true, "self": 1038.7366809119135 }, "steps_from_proto": { "total": 90.55500404695056, "count": 232242, "is_parallel": true, "self": 33.7462670888998, "children": { "_process_rank_one_or_two_observation": { "total": 56.80873695805076, "count": 464484, "is_parallel": true, "self": 56.80873695805076 } } } } } } } } } } }, "trainer_advance": { "total": 504.2605997379013, "count": 232243, "self": 6.734064204868332, "children": { "process_trajectory": { "total": 169.34032421003167, "count": 232243, "self": 167.96836291903207, "children": { "RLTrainer._checkpoint": { "total": 1.371961290999593, "count": 10, "self": 1.371961290999593 } } }, "_update_policy": { "total": 328.1862113230013, "count": 97, "self": 262.4196943229965, "children": { "TorchPPOOptimizer.update": { "total": 65.7665170000048, "count": 2910, "self": 65.7665170000048 } } } } } } }, "trainer_threads": { "total": 1.0809999366756529e-06, "count": 1, "self": 1.0809999366756529e-06 }, "TrainerController._save_models": { "total": 0.11850576699998783, "count": 1, "self": 0.0021171070002310444, "children": { "RLTrainer._checkpoint": { "total": 0.11638865999975678, "count": 1, "self": 0.11638865999975678 } } } } } } }