Associative Search Network: A Reinforcement Learning Associative Memory

Authors

Andrew G. Barto, University of Massachusetts - Amherst
Richard S. Sutton, University of Massachusetts - Amherst
Peter S. Brouwer, University of Massachusetts - Amherst

Publication Date

1981

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.

Comments

This paper was harvested from CiteSeer

Recommended Citation

Barto, Andrew G.; Sutton, Richard S.; and Brouwer, Peter S., "Associative Search Network: A Reinforcement Learning Associative Memory" (1981). Computer Science Department Faculty Publication Series. 6.
Retrieved from https://scholarworks.umass.edu/cs_faculty_pubs/6