Bounded Policy Iteration for Decentralized POMDPs
Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, August 2, 2005.
Download PPT, PDF.
Dynamic Programming for Partially Observable Stochastic
Games.
Nineteenth National Conference on Artificial Intelligence,
San Jose, California, July 27, 2004.
Download PPT, PDF.
Generalized Dynamic Programming for Decentralized POMDPs.
Sixth European Workshop on Reinforcement Learning,
Nancy, France, September 5, 2003.
Download PPT, PDF.
Some Complexity Results for Markov Decision Processes.
Deptartment of Computer Science Theory Seminar, University of
Massachusetts,
April 24, 2001.
Download PPT, PS, PDF.