- 期刊
- OpenAccess
Improving Mini-Shogi Engine Using Self-Play and Possibility of White's Advantage
摘要
The artificial intelligence (AI) in Shogi has made rapid progress recently, owing to the recent establishment of a method of learning evaluation via self-play. In this paper, we applied this method to Mini-Shogi to verify the effect. Specifically, we used YaneuraOu Shogi engine to develop the Mini-Shogi program and trained a neural network-based evaluation function. Our program won all competitions in which we participated in 2020. Moreover, the experimental results suggest the second-move (White) advantage in Mini-Shogi.
延伸閱讀
- 饒鏞（2022）。Combining MuZero Algorithm with Consecutive Winning Moves to Improve the Outer-Open Gomoku Program〔碩士論文，國立臺灣師範大學〕。華藝線上圖書館。https://doi.org/10.6345/NTNU202201075
- Huang, W. F. (2013). Learning Effects of English Spelling in Mahjong-Like Game Design Perspectives and Initiative Study [master's thesis, National Chung Cheng University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0033-2110201613565747
- 阮柏鈞（2017）。Uchifuzume in Minishogi〔碩士論文，中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu201700196
- 林猷琛（2020）。Using Other Players' Information Models to Improve Mahjong Program〔碩士論文，國立臺灣師範大學〕。華藝線上圖書館。https://doi.org/10.6345/NTNU202001457
- 方仕翔（2017）。A Mobile Client for Minishogi on Android Devices〔碩士論文，中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu201700486