Bridge Bidding via Deep Reinforcement Learning and Belief Monte Carlo Search  

作　　者：Zizhang Qiu Shouguang Wang Dan You MengChu Zhou 

机构地区：[1]School of Information and Electronic Engineering,Zhejiang Gongshang University,Hangzhou 310018,China [2]IEEE

出　　处：《IEEE/CAA Journal of Automatica Sinica》2024年第10期2111-2122,共12页自动化学报（英文版）

摘　　要：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 10000 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.

关 键 词：Contract Bridge reinforcement learning SEARCH 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]