Lecture #12 looked at reinforcement learning.
Notes are available in two formats:
The first part of the lecture was taken from:
R. Sutton and A. Barto, Reinforcement learning, MIT Press.The second part comes from Chapter 21 of the textbook, Section 21.1, 21.2.1, 21.2.2, and 21.3.
A classic paper that surveys much of the basic work in the area is:
L. P. Kaebling, M. L. Littman and A. W Moore, Reinforcement Learning: A survey, Journal of Artificial Intelligence, 4, 237-285, 1996.