Introduction to Reinforcement LearningRichard S. Sutton, Andrew G. Barto|MIT Press eBooks|1998Cited by 6.9k
Toward a modern theory of adaptive networks: Expectation and prediction.Richard S. Sutton, Andrew G. Barto|Psychological Review|1981Cited by 1.5k
Reinforcement learning is direct adaptive optimal controlRichard S. Sutton, R. J. Williams, Andrew G. Barto|IEEE Control Systems|1992Cited by 524
Time-Derivative Models of Pavlovian ReinforcementRichard S. Sutton, Andrew G. Barto|Unknown|1990Cited by 501
Learning and Sequential Decision MakingAndrew G. Barto, Chris Watkins, Richard S. Sutton|Unknown|1989Cited by 353