Maximum entropy correlated equilibria

Luis E. Ortiz, Robert E. Schapire, Sham M. Kakade

Research output: Contribution to journalConference article

7 Scopus citations

Abstract

We study maximum entropy correlated equilibria (Maxent CE) in multi-player games. After motivating and deriving some interesting important properties of Maxent CE, we provide two gradient-based algorithms that are guaranteed to converge to it. The proposed algorithms have strong connections to algorithms for statistical estimation (e.g., iterative scaling), and permit a distributed learning-dynamics interpretation. We also briefly discuss possible connections of this work, and more generally of the Maximum Entropy Principle in statistics, to the work on learning in games and the problem of equilibrium selection.

Original languageEnglish (US)
Pages (from-to)347-354
Number of pages8
JournalJournal of Machine Learning Research
Volume2
StatePublished - Dec 1 2007
Event11th International Conference on Artificial Intelligence and Statistics, AISTATS 2007 - San Juan, Puerto Rico
Duration: Mar 21 2007Mar 24 2007

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Maximum entropy correlated equilibria'. Together they form a unique fingerprint.

  • Cite this