[en] Monte-Carlo Tree Search is a new method which has been applied successfully to many games. However, it has never been tested on two-player perfect-information games with a chance factor. Backgam- mon is the reference game of this category. Today’s best Backgammon programs are based on reinforcement learning and are stronger than the best human players. These programs have played millions of offline games to learn to evaluate a position. Our approach consists rather in playing online simulated games to learn how to play correctly in the current position.