|
JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/12960
|
| タイトル: | Exemplar-Based Direct Policy Search with Evolutionary Optimization |
| 著者: | IKEDA, Kokolo |
| キーワード: | Direct policy search
exemplar based policy
evolutionary optimization
Acrobot
Q-learning |
| 発行日: | 2005 |
| 出版者: | Institute of Electrical and Electronics Engineers (IEEE) |
| 誌名: | The 2005 IEEE Congress on Evolutionary Computation |
| 巻: | 3 |
| 開始ページ: | 2357 |
| 終了ページ: | 2364 |
| DOI: | 10.1109/CEC.2005.1554988 |
| 抄録: | In this paper, an exemplar-based policy optimization framework for direct policy search is presented. In this exemplar-based approach, the policy to be optimized is composed of a set of exemplars and a case-based action selector. An implementation of this approach using a state-action-based policy representation and an evolutionary algorithm optimizer is shown to provide favorable search performance for two higher-dimensional problems. |
| Rights: | This is the author's version of the work. Copyright (C) 2005 IEEE. The 2005 IEEE Congress on Evolutionary Computation, 3, 2005, 2357-2364. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| URI: | http://hdl.handle.net/10119/12960 |
| 資料タイプ: | author |
| 出現コレクション: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| cec2005.pdf | | 1134Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
