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.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/31339 |
| Date | 20 March 2006 |
| Creators | Ortiz, Luis E., Schapire, Robert E., Kakade, Sham M. |
| Contributors | Learning and Intelligent Systems, Leslie Kaelbling |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 15 p., 301190 bytes, 876790 bytes, application/pdf, application/postscript |
| Relation | Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory |
Page generated in 0.002 seconds