Bridge Bidding via Deep Reinforcement Learning and Belief Monte Carlo Search
文献类型：期刊论文
| 作者 | Zizhang Qiu; Shouguang Wang; Dan You; MengChu Zhou |
| 刊名 | IEEE/CAA Journal of Automatica Sinica
 |
| 出版日期 | 2024 |
| 卷号 | 11期号:10页码:2111-2122 |
| 关键词 | Contract Bridge reinforcement learning search |
| ISSN号 | 2329-9266 |
| DOI | 10.1109/JAS.2024.124488 |
| 英文摘要 | 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 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. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/58841]  |
| 专题 | 自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica |
| 推荐引用方式 GB/T 7714 | Zizhang Qiu,Shouguang Wang,Dan You,et al. Bridge Bidding via Deep Reinforcement Learning and Belief Monte Carlo Search[J]. IEEE/CAA Journal of Automatica Sinica,2024,11(10):2111-2122. |
| APA | Zizhang Qiu,Shouguang Wang,Dan You,&MengChu Zhou.(2024).Bridge Bidding via Deep Reinforcement Learning and Belief Monte Carlo Search.IEEE/CAA Journal of Automatica Sinica,11(10),2111-2122. |
| MLA | Zizhang Qiu,et al."Bridge Bidding via Deep Reinforcement Learning and Belief Monte Carlo Search".IEEE/CAA Journal of Automatica Sinica 11.10(2024):2111-2122. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。