A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved state-of-the-art performance in many challenging strategy games. Because these games have complicated rules, an action sampled from the full discrete action distribution predicted by the learned policy is likely to be invali...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Shengyi Huang, Santiago Ontañón
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	LibraryPress@UF 2022-05-01
Цуврал:	Proceedings of the International Florida Artificial Intelligence Research Society Conference
Нөхцлүүд:	reinforcement learning deep learning deep reinforcement learning real-time strategy games implementation details invalid action masking
Онлайн хандалт:	https://journals.flvc.org/FLAIRS/article/view/130584
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!