Credit-Assigned-CMAC-based Reinforcement Learning with application to the Acrobot Swing Up Control Problem

Acrobot Swing Up 제어를 위한 Credit-Assigned-CMAC 기반의 강화학습

  • 신연용 (한양대학교 전자전기제어계측공학과) ;
  • 장시영 (한양대학교 전자전기제어계측공학과) ;
  • 서승환 (한양대학교 전자전기제어계측공학과) ;
  • 서일홍 (한양대학교 전자전기제어계측공학과)
  • Published : 2003.11.21


For real world applications of reinforcement learning techniques, function approximation or generalization will be required to avoid curse of dimensionality. For this, an improved function approximation-based reinforcement learning method is proposed to speed up convergence by using CA-CMAC(Credit-Assigned Cerebellar Model Articulation Controller). To show that our proposed CACRL(CA-CMAC-based Reinforcement Learning) performs better than the CRL(CMAC-based Reinforcement Learning), computer simulation results are illustrated, where a swing-up control problem of an acrobot is considered.