Evolving FPS Game Players by Using Continuous EDA-RL

5th International Workshop on Computational Intelligence & Applications Proceedings : IWCIA 2009 Page 143-146 published_at 2009-11

アクセス数 : 728 件

ダウンロード数 : 99 件

今月のアクセス数 : 0 件

今月のダウンロード数 : 1 件

この文献の参照には次のURLをご利用ください : https://ir.lib.hiroshima-u.ac.jp/00028463

File	A1211.pdf 226 KB 種類 : fulltext
Title ( eng )	Evolving FPS Game Players by Using Continuous EDA-RL
Creator	Tsubota Hajime Handa Hisashi
Source Title	5th International Workshop on Computational Intelligence & Applications Proceedings : IWCIA 2009
Start Page	143
End Page	146
Abstract	This paper extends EDA-RL, Estimation of Distribution Algorithms for Reinforcement Learning Problems, to continuous domain. The extended EDA-RL is used to constitiute FPS game players. In order to cope with continuous input-output relations, Gaussian Network is employed as in EBNA. Simulation results on Unreal Tournament 2004, one of major FPS games, confirm the effectiveness of the proposed method.
NDC	Technology. Engineering [ 500 ]
Language	eng
Resource Type	conference paper
Publisher	IEEE SMC Hiroshima Chapter
Date of Issued	2009-11
Rights	(c) Copyright by IEEE SMC Hiroshima Chapter.
Publish Type	Version of Record
Access Rights	open access
Source Identifier	[ISSN] 1883-3977 [URI] http://www.hil.hiroshima-u.ac.jp/iwcia/2009/