Applying Monte Carlo Tree Search to Tien Gow Game

• Main Authors: CHUNG,KUAN-LIN, 鐘冠麟
• Other Authors: Tsai,Ming-Jyh
• Format: Others
• Language: zh-TW
• Published: 2016
• Online Access: http://ndltd.ncl.edu.tw/handle/57655110821688357520

碩士 === 輔仁大學 === 資訊管理學系碩士班 === 104 === Computer game is one of the research areas of artificial intelligence(AI) development, the type of games is according to whether players know the other player’s information can be broadly divided into perfect information and imperfect information. Most of board games are perfect information, such as chess is an example. When we play chess, the status of the entire board is part of the public, both sides are able to know each other’s information. This study of Tien Gow is part of imperfect information, because it does not know about the other player's cards before play cards, we must judge according to our hands of cards and the next situation. In this study, we use Monte Carlo Tree Search(MCTS) as the core, and implement in the applications(APP) for strategy of AI of Tien Gow game, and recommend the decks to players.