Carnegie Mellon University
file.pdf (923.5 kB)

Knowledge based planning in games

Download (923.5 kB)
journal contribution
posted on 2007-09-01, 00:00 authored by Prasad Tadepalli
Abstract: "This paper explores the issue of planning in two-person games using approximately learned knowledge which is in the form of macros. A planning technique called Knowledge Enabled Planning, which consists of generating new plans by instantiating and composing the macros and testing them against the opponent's counter-plans, is introduced using a program called LEBL that learns and plans in two-person games. Some empirical results of testing LEBL in king and pawn endings in chess are presented along with a complexity analysis of the planning algorithm."




Usage metrics