| ID | 30129 |
| フルテキストURL | |
| 著者 | |
| 抄録 | 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. |
| キーワード | Reinforcement Learning
Growing Neural Gas
Incremental State Space Construction
|
| 備考 | 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. |
| 発行日 | 2004-8
|
| 出版物タイトル |
SICE 2004 Annual Conference
|
| 巻 | 3巻
|
| 開始ページ | 2698
|
| 終了ページ | 2703
|
| 資料タイプ |
学術雑誌論文
|
| 言語 |
英語
|
| 査読 |
有り
|
| Submission Path | industrial_engineering/19
|
