A Parallel Computer-Go Player, using HDP Method

Donald C. Wunsch, Missouri University of Science and Technology
Xindi Cai

This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1391

There were 7 downloads as of 28 Jun 2016.


The game of Go has simple rules to learn but requires complex strategies to play well, and, the conventional tree search algorithm for computer games is not suited for Go program. Thus, the game of Go is an ideal problem domain for machine learning algorithms. This paper examines the performance of a 19x19 computer Go player, using heuristic dynamic programming (HDP) and parallel alpha-beta search. The neural network based Go player learns good Go evaluation functions and wins about 30% of the games in a test series on 19x19 board