Proceedings of the Korean Institute of Intelligent Systems Conference (한국지능시스템학회:학술대회논문집)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지

Robot Control via RPO-based Reinforcement Learning Algorithm

RPO 기반 강화학습 알고리즘을 이용한 로봇 제어

  • Kim Jongho (Dept. of Control & Instrumentation Engineering, Korea University) ;
  • Kang Daesung (Dept. of Control & Instrumentation Engineering, Korea University) ;
  • Park Jooyoung (Dept. of Control & Instrumentation Engineering, Korea University)
  • 김종호 (고려대학교 제어계측공학과) ;
  • 강대성 (고려대학교 제어계측공학과) ;
  • 박주영 (고려대학교 제어계측공학과)
  • Published : 2005.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

The RPO algorithm is a recently developed tool in the area of reinforcement Loaming, And it has been shown In be very successful in several application problems. In this paper, we consider a robot-control problem utilizing a modified RPO algorithm in which its critic network is adapted via RLS(Recursive Least Square) algorithm. We also developed a MATLAB-based animation program, by which the effectiveness of the training algorithms were observed.

Keywords