1. Neuron-like elements that can solve difficult learning control problems;Barto;IEEE Trans. on Systems Man, and Cybernetics,1983
2. Induction: processes of inference learning, and discovery;Holland,1986
3. Michael I. Jordan and David E. Rumelhart. Supervised learning with a distal teacher. Technical report, MIT, 1990.
4. Learning to predict by the method of temporal differences;Sutton;Machine Learning,1988
5. Chris Watkins. Learning from delayed rewards. PhD thesis, Cambridge University, 1989.