このエントリーをはてなブックマークに追加
ID 25619
本文ファイル
著者
Handa, Hisashi
NDC
技術・工学
抄録(英)
We previously proposed evolutionary fuzzy systems of playing Ms.PacMan for the competitions. As a consequence of the evolution, reflective action rules such that PacMan tries to eat pills effectively until ghosts come close to PacMan are acquired. Such rules works well. However, sometimes it is too reflective so that PacMan go toward ghosts by herself in longer corridors. In this paper, a critical situation learning module is combined with the evolved fuzzy systems, i.e., reflective action module. The critical situation learning module is composed of Q-learning with CMAC. Location information of surrounding ghosts and the existence of power-pills are given to PacMan as state. This module punishes if PacMan is caught by ghosts. Therefore, this module learning which pairs of (state, action) cause her death. By using learnt Q-value, PacMan tries to survive much longer. Experimental results on Ms.PacMan elucidate the proposed method is promising since it can capture critical situations well. However, as a consequence of the large amount of memory required by CMAC, real time responses tend to be lost.
掲載誌名
Fourth International Workshop on Computational Intelligence & Applications Proceedings : IWCIA 2008
開始ページ
48
終了ページ
53
出版年月日
2008-12
出版者
IEEE SMC Hiroshima Chapter
ISSN
1883-3977
言語
英語
NII資源タイプ
会議発表論文
広大資料タイプ
会議発表論文
DCMIタイプ
text
フォーマット
application/pdf
著者版フラグ
publisher
権利情報
(c) Copyright by IEEE SMC Hiroshima Chapter.
部局名
工学研究科