skip navigation

This page looks better in modern browsers. Please upgrade.

Brown Home Brown Home Brown Home Brown CS
Research Project:

Reinforcement Learning in Markov Games

A classic goal of an AI agent is to learn optimize in uncertain environments, often modelled as Markov decision processes. At Brown, we are designing agents that learn to strategize in uncertain environments that are inhabited by other agents, modelled as Markov games. In the single-agent case, dynamic programming (DP) and reinforcement learning (RL) algorithms converge to optimal stationary policies. However, multiagent generalizations of DP and RL techniques need not converge to stationary equilibrium policies. On the contrary, we are investigating the space of nonstationary (e.g., cyclic) equilibrium policies that can arise in the multiagent case.

Project status: Active


Project Home Page: http://www.cs.brown.edu/people/amy/multiagent.html

People

David Gondek
Amy Greenwald
Keith Hall
Michael Littman
Martin Zinkevich
 

Funding

Computational Social Choice Theory, National Science Foundation, $375,000, 3/1/2002 - 2/28/2007

 

Publications

Zinkevich, M., Greenwald, A., and Littman, M. Cyclic Equilibria in Markov Games. In Advances in Neural Information Processing Systems (2006), MIT Press. To Appear. [ postscript | pdf ]

Greenwald, A., and Zinkevich, M. A Direct Proof of the Existence of Correlated Equilibrium Policies in General-Sum Markov Games. Tech. Rep. CS-05-07, Brown University, Department of Computer Science, Jun 2005.

Greenwald, A., and Hall, K. Correlated Q Learning. In Proceedings of the Twentieth International Conference on Machine Learning (Aug 2003), pp. 242-249. [ pdf ]


Page Owner: Webmaster Last Modified: Mon Oct 23 14:57:09 2006