Learning algorithms for repeated bimatrix Nash games with incomplete information

DOI10.1007/BF00939817MaRDI QIDQ1108947zbMATH OpenFDO

Authors George P. Papavassilopoulos

Publication date 1989

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/BF00939817

zbMATH Keywords

bimatrix gamesgames with incomplete informationlearning algorithmsNash gamerecursive scheme for updating

Mathematics Subject Classification ID

2-person games (91A05) Multistage and repeated games (91A20)

Review text

The purpose of this paper is to study a particular recursive scheme for updating the actions of two players involved in a Nash game, who do not know the parameters of the game, so that the resulting costs and strategies converge to (or approach a neighborhood of) those that could be calculated in the known parameter case. We study this problem in the context of a matrix Nash game, where the elements of the matrices are unknown to both players. The essence of the contribution of this paper is two-fold. On the one hand, it shows that learning algorithms which are known to work for zero-sum games or team problems can also perform well for Nash games. On the other hand, it shows that, if two players act without even knowing that they are involved in a game, but merely thinking that they try to maximize their output using the learning algorithm proposed, they end up being in Nash equilibrium.

Recommendations

• Absolutely expedient algorithms for learning Nash equilibria
• Fictitious play with incomplete learning
• A note on bimatrix games with an unknown payoff matrix
• Averaged predictions and the learning of equilibrium play
• On learning algorithms for Nash equilibria

Cites work

• Dynamic noncooperative game theory
• scientific article; zbMATH DE number 3131266 (Why is no real title available?)
• scientific article; zbMATH DE number 3738921 (Why is no real title available?)
• Iterative Techniques for the Nash Solution in Quadratic Games with Unknown Parameters
• The use of learning algorithms in telephone traffic routing - a methodology

Cited in

(8)

• Absolutely expedient algorithms for learning Nash equilibria
• Aspiration-based reinforcement learning in repeated interaction games: An overview
• On learning algorithms for Nash equilibria
• Learning Algorithms for Two-Person Zero-Sum Stochastic Games with Incomplete Information
• A note on bimatrix games with an unknown payoff matrix
• Learning in network contexts: experimental results from simulations
• An Adaptive Learning Game Model for Interacting Electric Power Markets
• An interconnection game between mobile network operators: hidden information forecasting using expert advice fusion

This page was built for publication: Learning algorithms for repeated bimatrix Nash games with incomplete information

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1108947)