Biological Cybernetics

, Volume 40, Issue 3, pp 201–211

Associative search network: A reinforcement learning associative memory

  • Andrew G. Barto
  • Richard S. Sutton
  • Peter S. Brouwer
Article

DOI: 10.1007/BF00453370

Cite this article as:
Barto, A.G., Sutton, R.S. & Brouwer, P.S. Biol. Cybern. (1981) 40: 201. doi:10.1007/BF00453370

Abstract

An associative memory system is presented which does not require a “teacher” to provide the desired associations. For each input key it conducts a search for the output pattern which optimizes an external payoff or reinforcement signal. The associative search network (ASN) combines pattern recognition and function optimization capabilities in a simple and effective way. We define the associative search problem, discuss conditions under which the associative search network is capable of solving it, and present results from computer simulations. The synthesis of sensory-motor control surfaces is discussed as an example of the associative search problem.

Copyright information

© Springer-Verlag 1981

Authors and Affiliations

  • Andrew G. Barto
    • 1
  • Richard S. Sutton
    • 1
  • Peter S. Brouwer
    • 1
  1. 1.Department of Computer and Information ScienceUniversity of MassachusettsAmherstUSA

Personalised recommendations