We propose an algorithm for computing approximate Nash equilibria of partially observable games using Monte-Carlo tree search based on recent bandit methods. We obtain experimental results for the game of phantom tic-tac-toe, showing that strong strategies can be efficiently computed by our algorithm.
@article{arxiv.1102.1580,
title = {Multiple Tree for Partially Observable Monte-Carlo Tree Search},
author = {David Auger},
journal= {arXiv preprint arXiv:1102.1580},
year = {2011}
}