Barto, A. G., 
Sutton, R. S. & 
Anderson, C. W. (
1983) Neuronlike elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man, and Cybernetics 13:
835–46. (Reprinted 1988: Neurocomputing: Foundations of research, ed. 
Anderson, J. A. & 
Rosenfeld, E., MIT Press. [AGB]
Google Scholar