Efficient Sampling Method for Monte Carlo Tree Search Problem


IEICE TRANSACTIONS on Information and Systems   Vol.E97-D   No.3   pp.392-398
Publication Date: 2014/03/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E97.D.392
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Foundations of Computer Science —New Trends in Theory of Computation and Algorithm—)
Category: Computational Learning Theory, Game
Monte Carlo tree search,  random sampling,  game,  UCT,  

Full Text: PDF(453.5KB)
>>Buy this Article

We consider Monte Carlo tree search problem, a variant of Min-Max tree search problem where the score of each leaf is the expectation of some Bernoulli variables and not explicitly given but can be estimated through (random) playouts. The goal of this problem is, given a game tree and an oracle that returns an outcome of a playout, to find a child node of the root which attains an approximate min-max score. This problem arises in two player games such as computer Go. We propose a simple and efficient algorithm for Monte Carlo tree search problem.