Return to search

Maximum Entropy Correlated Equilibria

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.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/31339
Date20 March 2006
CreatorsOrtiz, Luis E., Schapire, Robert E., Kakade, Sham M.
ContributorsLearning and Intelligent Systems, Leslie Kaelbling
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format15 p., 301190 bytes, 876790 bytes, application/pdf, application/postscript
RelationMassachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory

Page generated in 0.002 seconds