PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Transpositions and Move Groups in Monte Carlo Tree Search
Benjamin E Childs, James H Brodeur and Levente Kocsis
In: CIG 2008, 15-18 Dec 2008, Perth, Australia.

Abstract

Monte Carlo search, and specifically the UCT (Upper Confidence Bounds applied to Trees) algorithm, has contributed to a significant improvement in the game of Go and has received considerable attention in other applications. This article investigates two enhancements to the UCT algorithm. First, we consider the possible adjustments to UCT when the search tree is treated as a graph (and information amongst transpositions are shared). The second modification introduces move groupings, which may reduce the effective branching factor. Experiments with both enhancements were performed using artificial trees and in the game of Go. From the experimental results we conclude that both exploiting the graph structure and grouping moves may contribute to an increase in the playing strength of game programs using UCT.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:4571
Deposited By:Levente Kocsis
Deposited On:13 March 2009