2010年
Least Absolute Policy Iteration-A Robust Approach to Value Function Approximation.
IEICE Trans. Inf. Syst.
- ,
- ,
- ,
- 巻
- 93-D
- 号
- 9
- 開始ページ
- 2555
- 終了ページ
- 2565
- 記述言語
- 英語
- 掲載種別
- 研究論文(学術雑誌)
- DOI
- 10.1587/transinf.E93.D.2555
- 出版者・発行元
- IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
Least-squares policy iteration is a useful reinforcement learning method in robotics due to its computational efficiency. However, it tends to be sensitive to outliers in observed rewards. In this paper, we propose an alternative method that employs the absolute loss for enhancing robustness and reliability. The proposed method is formulated as a linear programming problem which can be solved efficiently by standard optimization software, so the computational advantage is not sacrificed for gaining robustness and reliability. We demonstrate the usefulness of the proposed approach through a simulated robot-control task.
- リンク情報
-
- DOI
- https://doi.org/10.1587/transinf.E93.D.2555
- DBLP
- https://dblp.uni-trier.de/rec/journals/ieicet/SugiyamaHKM10
- Web of Science
- https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000282245100022&DestApp=WOS_CPL
- URL
- http://search.ieice.org/bin/summary.php?id=e93-d_9_2555
- URL
- https://dblp.uni-trier.de/db/journals/ieicet/ieicet93d.html#SugiyamaHKM10
- ID情報
-
- DOI : 10.1587/transinf.E93.D.2555
- ISSN : 1745-1361
- DBLP ID : journals/ieicet/SugiyamaHKM10
- Web of Science ID : WOS:000282245100022