Suggested RL and RL-Related Readings

RL introductory material...

A great book available online: R. Sutton and A. Barto. Reinforcement Learning: An Introduction, MIT Press, Cambridge, 1998.
L.P.Kaelbling, M.L.Littman and A.W.Moore: Reinforcement Learning: A Survey
Amy Greenwald: Lecture Notes on Reinforcement Learning Nice and brief...
T.Mitchell: Chapter 13 of the "Machine Learning" book: "Reinforcement Learning"

Single-agent Reinforcement Learning Papers

Sutton (1988): Learning to Predict by the Methods of Temporal Differences.
Dayan (1992); Machine Learning, vol. 8.: The Convergence of TD(lambda) for General lambda.
Watkins and Dayan (1992); Machine Learning, vol. 8: Q-Learning
McCallum, Andrew (1995); In Proc. of ICML-95 Instance-Based Utile Distinctions for Reinforcement Learning with Hidden State

Multiagent Reinforcement Learning Papers

· Introductory material:

Shoham, Powers and Grenager: Multi-Agent Reinforcement Learning: a critical survey

· Mainly Game-Theoretic Approaches

Junling Hu: Best-response Algorithm for Multiagent Reinforcement Learning
Junling Hu and Yilian Zhang: Online Reinforcement Learning in Multiagent Systems
N.Suematsu and A.Hayashi: A Multiagent Reinforcement Learning Algorithm using Extended Optimal Response
M.Bowling and M.Veloso: Existence of multiagent equilibria with limited agents
A.Jafari and A.Greenwald and D.Gondek and G.Erkal On No-Regret Learning, Fictitious Play, and Nash Equilibrium
K.Hall & A.Greenwald: Correlated q-learning.
M.Littman and P.Stone: Leading Best-Response Strategies in Repeated Games Bullies and Godfathers

· Not-so-much-Game-Theoretic Approaches

Y.Nagayuki and S.Ishii and K.Doya: Multi-Agent Reinforcement Learning: An Approach Based on the Other Agent's Internal Model
Yu-Han Chang and L.P.Kaelbling: Playing is believing: The role of beliefs in multiagent learning

· Game Theory and Economics

Fudenberg and Levine: Consistency and cautious fictitious play, Journal of Economic Dynamics and Control, 19:1065-1089, 1995.
J.Nachbar and W.Zame: Non-computable strategies and discounted repeated games. Economic Theory, 1996.

· "Classic" MARL Readings

M.Littman: Markov Games as a framework for multiagent Reinforcement Learning.
Hu and Wellman: Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm.
Bowling and Veloso: Multiagent learning using a variable learning rate.
M.Littman: Friend-or-Foe Q-learning in general-sum games.
Claus and Boutilier: The dynamics of Reinforcement Learning in cooperative multiagent systems.
Dearden et al.: Model-based (and model-free) Bayesian RL.

Interesting links

Reinforcement Learning Repository at UMass@Amherst
Michael Littman's Learning and Sequential Decision Making course at Rutgers.