Evolutionary Algorithms for Reinforcement Learning

Journal of Artificial Intelligence Research - Tập 11 - Trang 241-276
David E. Moriarty1, Anna Charlotte Schultz2, John J. Grefenstette3
1University of Southern California/Information Sciences Institute, Marina del Rey, CA#TAB#
2Navy Center for Applied Research in Artificial Intelligence, Naval Research Laboratory, Washington DC
3Institute for Biosciences, Bioinformatics and Biotechnology, George Mason University, Manassas, VA#TAB#

Tóm tắt

There are two distinct approaches to solving reinforcement learning problems, namely, searching in value function space and searching in policy space. Temporal difference methods and evolutionary algorithms are well-known examples of these approaches. Kaelbling, Littman and Moore recently provided an informative survey of temporal difference methods. This article focuses on the application of evolutionary algorithms to the reinforcement learning problem, emphasizing alternative policy representations, credit assignment methods, and problem-specific genetic operators. Strengths and weaknesses of the evolutionary approach to reinforcement learning are presented, along with a survey of representative applications.

Từ khóa


Tài liệu tham khảo

Thông tin
Thông tin xuất bản

Journal of Artificial Intelligence Research

Tập 11

241-276

Thông tin tác giả