CS886 - Textbook

There is no required textbook.  However complementary readings (optional) will be recommended in several references (see course schedule)

• [SiBuf] Olivier Sigaud and Olivier Buffer (2010) Markov Decision Processes in Artificial Intelligence
• [Po] Warren B. Powell (2011, 2nd edition) Approximate Dynamic Programming: Solving the Curses of Dimensionality
• [SutBar] Richard Sutton and Andy Barto (1998) Reinforcement Learning: An Introduction
• [Sze] Csaba Szepesvari (2010) Algorithms for Reinforcement Learning (this link should be free from UW)
• [MauKo] Mausam and Andrey Kolobov (2012) Planning with Markov Decision Processes: An AI Perspective (this link should be free from UW)
• [Pu] Martin L. Puterman (2009, 2nd edition) Markov Decision Processes: Discrete Stochastic Dynamic Programming 
• [Ber] Dimitri Bertsekas (2012, 4th edition) Dynamic Programming and Optimal Control