Monte-Carlo Simulation for Mahjong

Jr-Chang Chen, Shih-Chieh Tang,I-Chen Wu

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING(2022)

引用 2|浏览2
暂无评分
摘要
Mahjong is a four-player, stochastic, imperfect information game. This paper focuses on the Taiwanese variant of Mahjong, whose complexity is higher than that of Go. We design a strong anytime Monte-Carlo-based Taiwanese Mahjong program. First, we adopt the flat Monte Carlo to calculate the win rates of all afterstates/actions such as discarding each tile. Then, we propose a heuristic method, which we incorporate into flat Monte Carlo to obtain the accurate tile to be discarded. As an anytime algorithm, we can stop simulations and return the current best move at any time. In addition, we prune bad actions to increase accuracy and efficiency. Our program, SIMCAT, won the championship in the Mahjong tournaments in Computer Olympiad 2020 and TAAI 2019/2020.
更多
查看译文
关键词
Monte-Carlo simulation, discard-twice method, imperfect information game, Mahjong, progressive pruning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要