Rapid and Reliable Adaptation of Video Game AI

S. Bakkes, P. Spronck, J. van den Herik
2009 IEEE Transactions on Computational Intelligence and AI in Games  
Current approaches to adaptive game AI typically require numerous trials to learn effective behaviour (i.e., game adaptation is not rapid). In addition, game developers are concerned that applying adaptive game AI may result in uncontrollable and unpredictable behaviour (i.e., game adaptation is not reliable). These characteristics hamper the incorporation of adaptive game AI in commercially available video games. In this article, we discuss an alternative to these current approaches. Our
more » ... ative approach to adaptive game AI has as its goal adapting rapidly and reliably to game circumstances. Our approach can be classified in the area of case-based adaptive game AI. In the approach, domain knowledge required to adapt to game circumstances is gathered automatically by the game AI, and is exploited immediately (i.e., without trials and without resourceintensive learning) to evoke effective behaviour in a controlled manner in online play. We performed experiments that test casebased adaptive game AI on three different maps in a commercial RTS game. From our results we may conclude that case-based adaptive game AI provides a strong basis for effectively adapting game AI in video games. Index Terms-Game AI, adaptive behaviour, rapid adaptation, reliable adaptation, RTS games. Sander Bakkes, Pieter Spronck, and Jaap van den Herik are with the Tilburg centre for Creative Computing (TiCC),
doi:10.1109/tciaig.2009.2029084 fatcat:gp42kgnrgbcfpapqgfu6cxdqey