このエントリーをはてなブックマークに追加
ID 14793
Eprint ID
14793
FullText URL
Author
Abstract
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.
Published Date
2008-12
Publication Title
Proceedings : Fourth International Workshop on Computational Intelligence & Applications
Volume
volume2008
Issue
issue1
Publisher
IEEE SMC Hiroshima Chapter
Start Page
48
End Page
53
Content Type
Conference Paper
language
英語
Event Title
Fourth International Workshop on Computational Intelligence & Applications IEEE SMC Hiroshima Chapter : IWCIA 2008
Event Location
東広島市
Event Location Alternative
Higashi-Hiroshima City
File Version
publisher
Refereed
True
Eprints Journal Name
IWCIA