ID | 30129 |
FullText URL | |
Author | |
Abstract | In this paper, we propose a new double-layered state space construction method, which consists of Fritzke's Growing Neural Gas algorithm and a class management mechanism of GNG units. The classification algorithm yields a new class by referring to anticipation error, anticipation vectors of an originated class, and anticipation vectors GNG units belonging in the originated class. |
Keywords | Reinforcement Learning
Growing Neural Gas
Incremental State Space Construction
|
Note | Published with permission from the copyright holder. This is the institute's copy, as published in SICE 2004 Annual Conference, 4-6 Aug. 2004, Vol. 3, Pages 2698-2703.
Publisher URL:http://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=1491910 Copyright © 2004 IEEE. All rights reserved. |
Published Date | 2004-8
|
Publication Title |
SICE 2004 Annual Conference
|
Volume | volume3
|
Start Page | 2698
|
End Page | 2703
|
Content Type |
Journal Article
|
language |
English
|
Refereed |
True
|
Submission Path | industrial_engineering/19
|