Two-Stage Reinforcement Learning on Credit Branch Genetic Network Programming for Mobile Robots

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2013/04/01

タイトル(英語): Two-Stage Reinforcement Learning on Credit Branch Genetic Network Programming for Mobile Robots

著者名: Siti Sendari (The State University of Malang/The Graduate School of Information, Production, and Systems, Waseda University), Shingo Mabu (The Graduate School of Information, Production, and Systems, Waseda University), Kotaro Hirasawa (The Graduate Schoo

著者名(英語): Siti Sendari (The State University of Malang/The Graduate School of Information, Production, and Systems, Waseda University), Shingo Mabu (The Graduate School of Information, Production, and Systems, Waseda University), Kotaro Hirasawa (The Graduate School of Information, Production, and Systems, Waseda University)

キーワード: Genetic Network Programming，Reinforcement Learning，Adaptability

要約(英語): This paper proposes Two-Stage Reinforcement Learning on Credit Branch Genetic Network Programming named GNP-TSRL-CB for mobile robots. The proposed method uses 2 kinds of Q-tables for sub node selection and credit branch selection, which has advantages of (1) determining an alternative function by using sub node selection and (2) skipping useless functions by using credit branch selection. It is clarified from simulation results that the adaptability mechanism of the proposed method can improve the performance compared with the conventional methods when the individuals of GNP-TSRL-CB are implemented in the dynamic environments like the sudden changes occur.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.133 No.4 （2013） 特集：新たなサービス社会に貢献する情報・システム技術

本誌掲載ページ: 856-863 p

原稿種別: 論文／英語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/133/4/133_856/_article/-char/ja/