Maximum Entropy Correlated Equilibria

Author(s)
Ortiz, Luis E.; Schapire, Robert E.; Kakade, Sham M.
Thumbnail
DownloadMIT-CSAIL-TR-2006-021.pdf (294.1Kb)
Additional downloads
Other Contributors
Learning and Intelligent Systems
Advisor
Leslie Kaelbling
Metadata
Show full item record
Abstract
We study maximum entropy correlated equilibria in (multi-player)games and provide two gradient-based algorithms that are guaranteedto converge to such equilibria. Although we do not provideconvergence rates for these algorithms, they do have strong connectionsto other algorithms (such as iterative scaling) which are effectiveheuristics for tasks such as statistical estimation.
Date issued
2006-03-20
URI
http://hdl.handle.net/1721.1/31339
Other identifiers
MIT-CSAIL-TR-2006-021
Series/Report no.
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
Keywords
Game Theory, Graphical Games, Graphical Models, Normal-form Games, Optimization
Collections