A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence

Tse, Guan Tan and Teo, Jason Tze Wi and Rayner Alfred, and Kim, On Chin (2013) A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence. Asia-Pacific Journal of Information Technology and Multimedia, 2 (2). pp. 53-61. ISSN 2289-2192

A coevolutionary multiobjective evolutionary algorithm.pdf

Download (44kB) | Preview


Recently, the growth of Artificial Intelligence (AI) has provided a set of effective techniques for designing computer-based controllers to perform various tasks autonomously in game area, specifically to produce intelligent optimal game controllers for playing video and computer games. This paper explores the use of the competitive fitness strategy: K Random Opponents (KRO) in a multiobjective approach for evolving Artificial Neural Networks (ANNs) that act as controllers for the Ms. Pac-man agent. The Pareto Archived Evolution Strategy (PAES) algorithm is used to generate a Pareto optimal set of ANNs that optimize the conflicting objectives of maximizing game scores and minimizing neural network complexity. Furthermore, an improved version, namely PAESNet_KRO, is proposed, which incorporates in contrast to its predecessor KRO strategy. The results are compared with PAESNet. From the discussions, it is found that PAESNet_KRO provides better solutions than

Item Type: Article
Uncontrolled Keywords: artificial neural networks, coevolutionary algorithms, evolutionary algorithms, game artificial intelligence, K random opponents, Ms. Pac-man, multiobjective evolutionary algorithms, Pareto archived evolution strategy
Subjects: Q Science > Q Science (General)
Divisions: FACULTY > Faculty of Computing and Informatics
Depositing User: Munira
Date Deposited: 03 Feb 2018 13:53
Last Modified: 03 Feb 2018 13:53
URI: http://eprints.ums.edu.my/id/eprint/18627

Actions (login required)

View Item View Item