Details of Program: MoGo


Written by: Wang, Yizao & Gelly, Sylvain; also Munos, Rémi & Coquelin, Pierre-Arnaud & Teytaud, Olivier & Hoock, Jean-Baptiste & Chaslot, Guillaume & Rimmel, Arpad


The first Go-playing program to use Monte Carlo methods with UCT (Upper Confidence bounds applied to Trees).

MoGo is a UCT/MC program playing go. It uses patterns in the simulations and improvements in the UCT tree search. The initial development was made during the Yizao Wang's internship at INRIA and Ecole Polytechnique with Sylvain Gelly, Rémi Munos and Olivier Teytaud.

Its web site:

May be downloaded from: