Bridge: New challenge for artificial intelligence

The game of bridge is very complex both for humans and for computer bridge programs. While the AI Go AlphaGo recently reached the level of grandmaster go, it is not the case for bridge where robots are still far from the best human players. The main difference between the two games is that bridge is a partially observable game. An expert program on bridge could therefore perform tasks that are different from and complementary to those handled by AlphaGo. The first part of this article is devoted to the presentation of various aspects of the bridge and some thoughts on the numerous challenges inherent to them together with a state of art of the computer bridge community. In the second part, we present our work related to the adaptation to bridge of a recent method using for boosting game AIs by seeking a random seed better than the others on a particular game. The AI bridge Wbridge5 developed by Yves Costel has been boosted with the best seed found on the outcome of these experiments and won the world championship bridge robots in September 2016. © 2017 Lavoisier.