Evolving behaviour trees for the commercial game defcon,” in Applications of Evolutionary Computation

www.doc.ic.ac.uk/ccg Abstract. Behaviour trees provide the possibility of improving on ex-isting Artificial Intelligence techniques in games by being simple to im-plement, scalable, able to handle the complexity of games, and modular to improve reusability. This ultimately improves the development pro-cess for designing automated game players. We cover here the use of behaviour trees to design and develop an AI-controlled player for the commercial real-time strategy game DEFCON. In particular, we evolved behaviour trees to develop a competitive player which was able to out-perform the game’s original AI-bot more than 50 % of the time. We aim to highlight the potential for evolving behaviour trees as a practical ap-proach to developing AI-bots in games.