A Pac-Man bot based on grammatical evolution

In this article, we propose the development of a bot for playing the video game Ms. Pac-Man vs. Ghosts using a grammatical evolution based evolutionary algorithm. This technique evolves programs that are evaluated by executing them in the game. The program encodes the strategy that the bot plays and is obtained through the derivation of grammar rules in a particular order, which is defined by the algorithm. We experimented with two different grammars: The first one includes high-level actions and the second one involves medium-level actions. Both grammars include state providers. To make the evolutionary process more efficient, we perform a series of optimizations on the evolutionary algorithm, including parallelization of the fitness evaluation and multi-objective optimization. Experimental results using the two grammars and two different ghost controllers are presented. We report better results with our bots than the baseline controllers and other controllers based on grammatical evolution.