Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Comparison of CMACs and Radial Basis Functions for Local Function Approximators in Reinforcement Learning
 

Summary: Comparison of CMACs and Radial Basis Functions for Local Function
Approximators in Reinforcement Learning
R. Matthew Kretchmar
Department of Computer Science
Colorado State University
Fort Collins, CO 80523
kretchma@cs.colostate.edu
Charles W. Anderson
Department of Computer Science
Colorado State University
Fort Collins, CO 80523
anderson@cs.colostate.edu
Abstract
CMACs and Radial Basis Functions are often used in rein-
forcement learning to learn value function approximations
having local generalization properties. We examine the simi-
larities and differences between CMACs, RBFs and normal-
ized RBFs and compare the performance of Q-learning with
each representation applied to the mountain car problem. We
discuss ongoing research efforts to exploit the flexibility of

  

Source: Anderson, Charles W. - Department of Computer Science, Colorado State University

 

Collections: Computer Technologies and Information Sciences