Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons

Open Access. Powered by Scholars. Published by Universities.®

University of Massachusetts Amherst

Computer Science Department Faculty Publication Series

1981

Articles 1 - 1 of 1

Full-Text Articles in Physical Sciences and Mathematics

Associative Search Network: A Reinforcement Learning Associative Memory, Andrew G. Barto, Richard S. Sutton, Peter S. Brouwer Jan 1981

Associative Search Network: A Reinforcement Learning Associative Memory, Andrew G. Barto, Richard S. Sutton, Peter S. Brouwer

Computer Science Department Faculty Publication Series

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.