Does your PPO agent fail to learn?
Автор: RL Hugh
Загружено: 2022-08-06
Просмотров: 24144
One hyper-parameter could improve the stability of learning, and help your agent to explore!
We investigate how to improve the reliability of training when using stable baselines 3 library, with ViZDoom, using the PyTorch deep neural network library, and the Python 3 language.
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке: