Planning, Search, and Optimization
J. Christopher Beck, Robert Holte, Thorsten Koch, Sylvie Thiebaux, Organizers
Technical Report WS-15-12
Softcover version of the technical report: $30.00 softcover
(For international orders please shipping options before ordering on website.)
Mainstream AI planning and heuristic search have traditionally been concerned with finding paths through a state transition system. The objective is typically to find either a feasible solution or an optimal solution to a fairly restricted objective function (for example, minimize plan length or the sum of the costs of actions in a plan).
While there have been pioneering efforts at using optimization for planning (notably in compilation approaches to mixed integer programming and constraint programming), there has been significant renewed interest in a number of areas, including formulating heuristic generation and selection as an optimization problem; linear programming as a basis for search heuristics in classical planning; hybridization of optimization approaches and planning to solve more expressive problems involving time, resources, and complex systems; adaptation of optimization methods to design planning and search algorithms that continually improve plan quality as time permits.