On learning algorithms for Nash equilibria

DOI10.1007/978-3-642-16170-4_11MaRDI QIDQ3162512zbMATH OpenOpenAlexFDO

Authors Constantinos Daskalakis, Rafael Frongillo, George Pierrakos, Gregory Valiant, Christos Papadimitriou

Publication date 19 October 2010

Published in Algorithmic Game Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-642-16170-4_11

Mathematics Subject Classification ID

Noncooperative games (91A10) Evolutionary games (91A22) Rationality and learning in game theory (91A26)

Recommendations

• On the rate of convergence of fictitious play
• On the rate of convergence of fictitious play
• Absolutely expedient algorithms for learning Nash equilibria
• A general class of no-regret learning algorithms and game-theoretic equilibria.
• Learning algorithms for repeated bimatrix Nash games with incomplete information

Cites work

• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• Adaptive game playing using multiplicative weights
• An iterative method of solving a game
• scientific article; zbMATH DE number 5485469 (Why is no real title available?)
• scientific article; zbMATH DE number 5485549 (Why is no real title available?)
• scientific article; zbMATH DE number 3205074 (Why is no real title available?)
• scientific article; zbMATH DE number 3225772 (Why is no real title available?)
• Intrinsic robustness of the price of anarchy
• Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
• Multiplicative updates outperform generic no-regret learning in congestion games (extended abstract)
• The multiplicative weights update method: a meta-algorithm and applications
• The Nonstochastic Multiarmed Bandit Problem

Cited in

(17)

• Learning algorithms for repeated bimatrix Nash games with incomplete information
• Three problems in learning mixed-strategy Nash equilibria
• Absolutely expedient algorithms for learning Nash equilibria
• Convergent multiple-timescales reinforcement learning algorithms in normal form games
• Finding multiple Nash equilibria via machine learning-supported Gröbner bases
• Learning convex partitions and computing game-theoretic equilibria from best response queries
• Learning strict Nash equilibria through reinforcement
• scientific article; zbMATH DE number 1594530 (Why is no real title available?)
• A competitive rate allocation game
• Learning Algorithms for Two-Person Zero-Sum Stochastic Games with Incomplete Information
• On gradient-based learning in continuous games
• GENERAL PROOF OF CONVERGENCE OF THE NASH-Q-LEARNING ALGORITHM
• Fast algorithm for recovering the true solution with fixed weight of a system of linear Boolean equations with noised right-hand side
• Steady State Learning and Nash Equilibrium
• A general class of no-regret learning algorithms and game-theoretic equilibria.
• Specification-Guided Learning of Nash Equilibria with High Social Welfare
• Swim till you sink: computing the limit of a game

This page was built for publication: On learning algorithms for Nash equilibria

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3162512)