A behavior analysis of sequential and off-table information in the game of Mahjong via deep convolutional neural networks

• Item type: National Convention(1)
• 公開日: 2019-02-28
• タイトル: A behavior analysis of sequential and off-table information in the game of Mahjong via deep convolutional neural networks
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 人工知能と認知科学
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: 東大
• 著者所属: 東大
• 著者所属: 東大
• 著者所属: 東大
• 著者名: 高, 世祺; 奥谷, 文徳; 川原, 圭博; 鶴岡, 慶雅
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Evaluation function is a very important factor for policy decision but always hard to define exactly especially in imperfect information games. Most of the studies on the game of Mahjong utilize concrete game rules and use traditional AI methods with artificially well-designed function blocks. For the benchmark of agreement rate on tile discard, traditional baseline is 62.1%. Our past proposal designed a new model with deep convolutional neural networks and raised this result by 6.7%. However the model is still not perfect. In this paper, we make a comparison of the behavior on learning past-made-action information in different ways, and explore better approaches for including off-table messages such as ranks and scores for model learning.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00349328
• 書誌情報: 第81回全国大会講演論文集; 巻 2019, 号 1, p. 387-388, 発行日 2019-02-28
• 出版者 / 言語: ja
• 出版者: 情報処理学会