The Fast-Forward Planning System

In trying to attack domain-independent planning as heuristic search, the main difficulty lies in the automatic derivation of the heuristic function. For human algorithm designers, a common approach to deriving a heuristic is to relax the problem at hand into a simpler problem ' that can be solved efficiently. Facing a search state in, one can then use the solution length of the same state in ' to estimate its difficulty. Bonet, Loerincs, and Geffner (1997) proposed a way of applying this idea to domainindependent planning. They relax the highlevel problem description by simply ignoring delete lists.