Evolving opponents for interesting interactive computer games

Abstract

In this paper we introduce experiments on neuro-evolution mechanisms applied to predator/prey multi-character computer games. Our test-bed is a modified version of the well-known Pac-Man game. By viewing the game from the predators’ (i.e. opponents’) perspective, we attempt off-line to evolve neural-controlled opponents capable of playing effectively against computer-guided fixed strategy players. However, emergent near-optimal behaviors make the game less interesting to play. We therefore discuss the criteria that make a game interesting and, furthermore, we introduce a generic measure of predator/prey computer games’ interest. Given this measure, we present an evolutionary mechanism for opponents that keep learning from a player while playing against it (i.e. on-line) and we demonstrate its efficiency and robustness in increasing and maintaining the game’s interest. Computer game opponents following this on-line learning approach show high adaptability to changing player strategies which provides evidence for the approach’s effectiveness against human players.