Free online version or Barto/Sutton's RL book

[Subbarao Kambhampati <rao@asu.edu>]

For this course, the R&N chapter will be sufficient. But if you are interested in learning more, you might find the following links useful

Barto and Sutton's book on Reinforcement Learning, which gives most of the algorithms we discuss in the class but with more elaborate description, is freely

available in html version at http://webdocs.cs.ualberta.ca/~sutton/book/ebook/the-book.html

(The book by Warren Powell, (see http://www.amazon.com/Approximate-Dynamic-Programming-Dimensionality-Probability/dp/047060445X) is the Operations Research version of the Barto/Sutton book, while the book by Bertsakis (http://www.amazon.com/Neuro-Dynamic-Programming-Optimization-Neural-Computation/dp/1886529108/) 

gives the heavy-duty proofs of convergence of many of these algorithms)

Rao