|
JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/10925
|
| タイトル: | Playing PuyoPuyo: Two Search Algorithms for Constructing Chain and Tactical Heuristics |
| 著者: | Ikeda, Kokolo
Tomizawa, Daisuke
Viennot, Simon
Tanaka, Yuu |
| キーワード: | PuyoPuyo
Tree search
Potential Maximization
Template matching |
| 発行日: | 2012-09 |
| 出版者: | Institute of Electrical and Electronics Engineers (IEEE) |
| 誌名: | 2012 IEEE Conference on Computational Intelligence and Games (CIG) |
| 開始ページ: | 71 |
| 終了ページ: | 78 |
| DOI: | 10.1109/CIG.2012.6374140 |
| 抄録: | Tetris is one of the most famous tile-matching videogames, and has been used as a test bed for artificial intelligencetechniques such as machine learning. Many games have beenderived from such early tile-matching games, in this paper wediscuss how to develop AI players of “PuyoPuyo”. PuyoPuyois a popular two-player game, and where the main point is toconstruct a “chain” longer than the opponent. We introducetwo tree search algorithms and some tactical heuristics forimproving the performance. We were able to reach an averagechain length of 11, notably higher than that of the commercial AIs. |
| Rights: | This is the author's version of the work. Copyright (C) 2012 IEEE. 2012 IEEE Conference on Computational Intelligence and Games (CIG), 2012, 71-78. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| URI: | http://hdl.handle.net/10119/10925 |
| 資料タイプ: | author |
| 出現コレクション: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| 18704.pdf | | 537Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
