While most reading for the course will involve research papers, there are
two useful texts that will provide relevant background:
- The primary text is
Multiagent Systems: Algorithmic,
Game-Theoretic, and Logical Foundations by Yoav Shoham and Kevin
Leyton-Brown (Cambridge University Press, 2009). It is
freely available online (with suggested limitations on its use).
Chapters 3, 5, 6, 9 and 10 will provide useful background for the
second half of the course. It is referred to as MASAGLF in any assigned readings.
- An useful background reference for certain parts of the
course (especially for those without significant AI background)
is Artificial Intelligence: A Modern Approach, by Stuart Russell
and Peter Norvig (Prentice-Hall, 1995). This is a comprehensive text with
reasonably concise, very readable, well-motivated chapters on several of
the topics we will discuss. I'll refer to sections from AIMA
as background reading on probabilistic inference and decision theory.
Not a necessary reference (since lectures will be self-contained on these
topics), but potentially useful. I'll make available several copies
of the text.
Some further general background readings on various topics.
Probabilistic Reasoning and Bayesian networks
- Judea Pearl. Probabilistic Reasoning in Intelligent
Systems: Networks of Plausible Inference. Morgan-Kaufmann, 1988.
The bible of Bayesian networks.
- Daphne Koller and Nir Friedman. Probabilistic Graphical Models:
Principles and Techniques Systems. MIT Press, 2009.
The most comprehensive, up-to-date treatment
of inference and learning in graphical models.
Decision Theory
- Simon French. Decision Theory. Halsted Press, 1986.
Excellent general decision theory
text. Sufficient technical depth coupled with good explanations
and intuitions.
- L. Savage. The Foundations of Statistics. Wiley, 1954.
Foundations of decision theory
Markov Decision Processes
- C. Boutilier, T. Dean and S Hanks. Decision Theoretic Planning:
Structural Assumptions and Computational Leverage, Journal of
AI Research 11:1--94 (1999)
Survey of MDPs and the use of AI techniques to solve
them. Good intro, somewhat dated by now w.r.t. state of the art).
Available here..
- Martin L. Puterman. Markov Decision Processes:
Discrete Stochastic Dynamic Programming. Wiley, 1994.
General MDPs
- Dimitri P. Bertsekas. Dynamic Programming:
Deterministic and Stochastic Models. Prentice-Hall, 1987.
General MDPs
- T. Dean and M. Wellman. Planning and Control.
Morgan-Kaufmann, 1991.
Planning and decision theoretic planning
- W. Lovejoy. A Survey of Algorithmic Methods for Partially
Observed Markov Decision Processes, Annals of Operations Research
28:47--66 (1991).
Survey of basic
POMDP solution techniques
Reinforcement Learning
Not a topic we'll cover, but something at the intersection of
machine learning and MDPS. May be of interest to some (and we can
discuss in class if there is enough interest).
- R. Sutton and A. Barto. Reinforcement Learning: An Introduction,
MIT Press, 1998.
Great introductory text for reinforcement
learning. Very accessible, easy reading.
Entire
book is online.
- M. Wiering, M. van Otterlo (eds). Reinforcement Learning:
State of the Art, Springer, 2012.
Comprehensive collection of of chapters on both
basics and up-to-date state of the art. Chapters vary considerably in style
and depth/insight.
Entire book is online.
- L. Kaelbling, M Littman, A. Moore. Reinforcement Learning:
A Survey, Journal of Artificial Intelligence Research 4:237--285,
1996.
Nice survey article (great intro to the basics,
somewhat dated by now w.r.t. state of the art).
Available here..
- D. Bertsekas and J. Tsitsiklis. Neuro-dynamic Programming,
Athena, 1996.
Another great text for RL. Less accessible than
Sutton and Barto, but goes into much more technical depth.
- D. Bertsekas and J. Tsitsiklis. Neuro-dynamic Programming,
Game Theory
- Andreu Mas-Colell, Michael Whinston, and Jerry Green. Microeconomic Theory. Oxford, 1995.
Comprehensive treatment of microeconomics, covering
game theory, auctions, mechanism design, social choice and many related topics we
address in this course. A valuable reference for anyone working in the area.
- R. Myerson. Game Theory: Analysis of Conflict. Harvard, 1991.
Decent game theory text
- D. Fudenberg and J. Tirole. Game Theory. MIT, 1991.
Another decent game theory text
- N. Nisan, T. Roughgarden, E. Tardos, V. Vazirani (Eds.).
Algorithmic Game Theory. Cambridge, 2007.
Excellent collection of chapters on
a variety of topics in game theory and mechanism design from a
computational perspective. Full text available online it seems.
A superb resource.
- S. Rosenschein and G. Zlotkin. Rules of Encounter. MIT, 1994.
A monograph on application of game theoretic methods to AI style
problems