{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4048309326171875, "min": 1.4048309326171875, "max": 1.4258478879928589, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70133.375, "min": 68860.328125, "max": 76528.65625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 78.27662957074722, "min": 68.69456066945607, "max": 409.05737704918033, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49236.0, "min": 48867.0, "max": 49928.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999975.0, "min": 49323.0, "max": 1999975.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999975.0, "min": 49323.0, "max": 1999975.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5256824493408203, "min": 0.008007164113223553, "max": 2.5310115814208984, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1591.179931640625, "min": 0.9688668847084045, "max": 1809.4432373046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8940340602208696, "min": 1.8436348933326312, "max": 4.05309206674433, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2453.241457939148, "min": 223.07982209324837, "max": 2860.02295678854, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8940340602208696, "min": 1.8436348933326312, "max": 4.05309206674433, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2453.241457939148, "min": 223.07982209324837, "max": 2860.02295678854, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017368618730688467, "min": 0.014688087769900448, "max": 0.019957005893229508, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0521058561920654, "min": 0.029376175539800896, "max": 0.0578421307024352, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05548823492394553, "min": 0.022880580027898154, "max": 0.06301256989439329, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16646470477183659, "min": 0.04576116005579631, "max": 0.18473280829687916, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.948148683983324e-06, "min": 3.948148683983324e-06, "max": 0.00029534910155030005, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1844446051949971e-05, "min": 1.1844446051949971e-05, "max": 0.0008442103685965498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10131601666666666, "min": 0.10131601666666666, "max": 0.19844969999999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30394804999999997, "min": 0.2077803, "max": 0.58140345, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.566923166666655e-05, "min": 7.566923166666655e-05, "max": 0.0049226400300000014, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022700769499999965, "min": 0.00022700769499999965, "max": 0.014072032155, "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": "1701362560", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701365095" }, "total": 2535.189600102, "count": 1, "self": 0.4558079200000975, "children": { "run_training.setup": { "total": 0.05901152399997045, "count": 1, "self": 0.05901152399997045 }, "TrainerController.start_learning": { "total": 2534.6747806579997, "count": 1, "self": 4.7497471080155265, "children": { "TrainerController._reset_env": { "total": 3.457937394000055, "count": 1, "self": 3.457937394000055 }, "TrainerController.advance": { "total": 2526.362560383984, "count": 233736, "self": 5.019733928044843, "children": { "env_step": { "total": 1989.7841366679577, "count": 233736, "self": 1652.8317759779165, "children": { "SubprocessEnvManager._take_step": { "total": 333.9054966100309, "count": 233736, "self": 16.938856820104547, "children": { "TorchPolicy.evaluate": { "total": 316.9666397899264, "count": 222975, "self": 316.9666397899264 } } }, "workers": { "total": 3.0468640800102094, "count": 233736, "self": 0.0, "children": { "worker_root": { "total": 2527.0071580771173, "count": 233736, "is_parallel": true, "self": 1191.1717577910151, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008319309999933466, "count": 1, "is_parallel": true, "self": 0.00021453099998325342, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006174000000100932, "count": 2, "is_parallel": true, "self": 0.0006174000000100932 } } }, "UnityEnvironment.step": { "total": 0.028427516000192554, "count": 1, "is_parallel": true, "self": 0.0002983960005167319, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019007199989573564, "count": 1, "is_parallel": true, "self": 0.00019007199989573564 }, "communicator.exchange": { "total": 0.027253441999846473, "count": 1, "is_parallel": true, "self": 0.027253441999846473 }, "steps_from_proto": { "total": 0.0006856059999336139, "count": 1, "is_parallel": true, "self": 0.00019652599985420238, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004890800000794115, "count": 2, "is_parallel": true, "self": 0.0004890800000794115 } } } } } } }, "UnityEnvironment.step": { "total": 1335.8354002861022, "count": 233735, "is_parallel": true, "self": 40.55168044023276, "children": { "UnityEnvironment._generate_step_input": { "total": 83.44330990181902, "count": 233735, "is_parallel": true, "self": 83.44330990181902 }, "communicator.exchange": { "total": 1122.4004830490017, "count": 233735, "is_parallel": true, "self": 1122.4004830490017 }, "steps_from_proto": { "total": 89.43992689504876, "count": 233735, "is_parallel": true, "self": 31.093568522958776, "children": { "_process_rank_one_or_two_observation": { "total": 58.34635837208998, "count": 467470, "is_parallel": true, "self": 58.34635837208998 } } } } } } } } } } }, "trainer_advance": { "total": 531.5586897879816, "count": 233736, "self": 7.2733700581213725, "children": { "process_trajectory": { "total": 170.49787455286082, "count": 233736, "self": 169.32666096486037, "children": { "RLTrainer._checkpoint": { "total": 1.1712135880004553, "count": 10, "self": 1.1712135880004553 } } }, "_update_policy": { "total": 353.7874451769994, "count": 97, "self": 288.72736354500785, "children": { "TorchPPOOptimizer.update": { "total": 65.06008163199158, "count": 2910, "self": 65.06008163199158 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.10453482599996278, "count": 1, "self": 0.0016676810000717524, "children": { "RLTrainer._checkpoint": { "total": 0.10286714499989102, "count": 1, "self": 0.10286714499989102 } } } } } } }