Maximum Entropy Correlated Equilibria

Luis E. Ortiz, Robert E. Schapire, Sham M. Kakade
Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, PMLR 2:347-354, 2007.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v2-ortiz07a, title = {Maximum Entropy Correlated Equilibria}, author = {Ortiz, Luis E. and Schapire, Robert E. and Kakade, Sham M.}, booktitle = {Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics}, pages = {347--354}, year = {2007}, editor = {Meila, Marina and Shen, Xiaotong}, volume = {2}, series = {Proceedings of Machine Learning Research}, address = {San Juan, Puerto Rico}, month = {21--24 Mar}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v2/ortiz07a/ortiz07a.pdf}, url = {https://proceedings.mlr.press/v2/ortiz07a.html}, 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.} }
Endnote
%0 Conference Paper %T Maximum Entropy Correlated Equilibria %A Luis E. Ortiz %A Robert E. Schapire %A Sham M. Kakade %B Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2007 %E Marina Meila %E Xiaotong Shen %F pmlr-v2-ortiz07a %I PMLR %P 347--354 %U https://proceedings.mlr.press/v2/ortiz07a.html %V 2 %X 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.
RIS
TY - CPAPER TI - Maximum Entropy Correlated Equilibria AU - Luis E. Ortiz AU - Robert E. Schapire AU - Sham M. Kakade BT - Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics DA - 2007/03/11 ED - Marina Meila ED - Xiaotong Shen ID - pmlr-v2-ortiz07a PB - PMLR DP - Proceedings of Machine Learning Research VL - 2 SP - 347 EP - 354 L1 - http://proceedings.mlr.press/v2/ortiz07a/ortiz07a.pdf UR - https://proceedings.mlr.press/v2/ortiz07a.html AB - 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. ER -
APA
Ortiz, L.E., Schapire, R.E. & Kakade, S.M.. (2007). Maximum Entropy Correlated Equilibria. Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 2:347-354 Available from https://proceedings.mlr.press/v2/ortiz07a.html.

Related Material