The FAR-OFF system: a heuristic search case-based planning

Abstract

This paper presents a case-based planning system, called FAR-OFF, as an alternative approach to heuristic search generative planners, like HSP and FF. The FAR-OFF system introduces the use of a new similarity metric, called ADG (Action Distance-Guided), that is more accurate than other similarity metrics, and it also incorporates techniques to decrease the retrieval time, like the Footprint-based Retrieval. Consequently, the FAR-OFF system can solve more AIPS'00 planning competition problems than the heuristic search planners in an acceptable amount of time.