このエントリーをはてなブックマークに追加
ID 28463
file
A1211.pdf 226 KB
creator
Tsubota, Hajime
Handa, Hisashi
NDC
Technology. Engineering
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.
journal title
5th International Workshop on Computational Intelligence & Applications Proceedings : IWCIA 2009
start page
143
end page
146
date of issued
2009-11
publisher
IEEE SMC Hiroshima Chapter
issn
1883-3977
language
eng
nii type
Conference Paper
HU type
Conference Papers
DCMI type
text
format
application/pdf
text version
publisher
rights
(c) Copyright by IEEE SMC Hiroshima Chapter.
relation url
department
Graduate School of Engineering