A Coevolutionary Multiobjective Evolutionary Algorithm for Game Artificial Intelligence

Tse Guan Tan, Jason Teo, Kim On Chin, Rayner Alfred
dx.doi.org/10.17576/apjitm-2013-0202-05

Abstract

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

keyword

artificial neural networks, coevolutionary algorithms, evolutionary algorithms, game artificial intelligence, K random opponents, Ms. Pac-man, multiobjective evolutionary algorithms, Pareto archived e

Area

Data Mining and Optimization