Optimising Plans using Genetic Programming
Carl Henrik Westerberg, John R. Levine · Strathprints: The University of Strathclyde institutional repository (University of Strathclyde) · 2001
Finding the shortest plan for a given planning problem is extremely hard. We present a domain independent approach for plan optimisation based on Genetic Programming. The algorithm is seeded with correct plans created by hand-encoded heuristic policy sets. The plans are very unlikely to be optimal but are created quickly. The sub-optimal plans are then evolved using a generational algorithm towards the optimal plan. We present initial results from Blocks World and the Briefcase Domain and found that GP method almost always improved sub-optimal plans, often drastically.