A PDDL-based planning architecture to support arcade game playing

Abstract

First, we explain the Iceblox game, which has its origin in the Pengo game. After carefully listing requirements on game playing, the contents of plans, their execution and planning problem generation, we design a set of benchmarks to select good playing candidates among currently available PDDL-based planners. We eventually selected two planners which are able to play the Iceblox video game well and mostly in real time. We describe both the predicates and some of the operators we designed. Then, we give details on our planning architecture and in particular discuss the importance of the generation of PDDL planning problems. We wish to report that no planner was tweaked during the benchmarks. © 2009 Springer-Verlag.