Prolog versus specialized logic inference engine in General Game Playing

In this paper, we study the problem of applying an inference engine, i.e. a mechanism able to derive answers from a knowledge base, to General Game Playing (GGP). Our focus is on the General Game Playing Competition framework proposed by the Stanford Logic Group. This particular embodiment of a multi-game playing uses the Game Description Language (GDL) for representing the knowledge base by means of game rules. The GDL is a variant of Datalog and a subset of Prolog, so there is a strong bond with formal logic languages. We present basic principles of our system which is dedicated to GDL. The motivation is to exceed the performance of Prolog engines applied to GDL, which is currently a common approach. Empirical results show that our solution is indeed faster in 6 out of 7 tested games.