Bridge Bidding via Deep Reinforcement Learning and Belief Monte Carlo Search

Contract Bridge, a four-player imperfect information game, comprises two phases: bidding and playing. While computer programs excel at playing, bidding presents a challenging aspect due to the need for information exchange with partners and interference with communication of opponents. In this work, we introduce a Bridge bidding agent that combines supervised learning, deep reinforcement learning via self-play, and a test-time search approach. Our experiments demonstrate that our agent outperforms WBridge5, a highly regarded computer Bridge software that has won multiple world championships, by a performance of 0.98 IMPs (international match points) per deal over 10 000 deals, with a much cost-effective approach. The performance significantly surpasses previous state-of-the-art (0.85 IMPs per deal). Note 0.1 IMPs per deal is a significant improvement in Bridge bidding.