A Player for Tactical Air Strike Games Using Evolutionary Computation

This paper discusses the use of evolutionary computation for an automated player of a real-time strategic tactics game in which assets are assigned to targets and threats belonging to the opposing team. Strategy games such as this are essentially a series of asset allocation problems to which evolutionary algorithms are particularly adept. This game contains a significant coupling affect between the assets assigned to targets and those assigned to threats. The effort considers targets and threats in a non-spatiotemporal framework to evaluate the proposed approach. In addition, the architecture that supports the implemented evolutionary search algorithm is also discussed