Learning Generalized Nash Equilibria in a Class of Convex Games

DOI10.1109/TAC.2018.2841319MaRDI QIDQ5223651zbMATH OpenOpenAlexWikidataFDO

Authors Tatiana Tatarenko, Maryam Kamgarpour

Publication date 18 July 2019

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1703.04113

Mathematics Subject Classification ID

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

Abstract: We consider multi-agent decision making where each agent optimizes its convex cost function subject to individual and coupling constraints. The constraint sets are compact convex subsets of a Euclidean space. To learn Nash equilibria, we propose a novel distributed payoff-based algorithm, such that each agent uses information only about its cost function values and the constraint function values with their associated dual multiplier. We prove convergence of this algorithm to a Nash equilibrium, under the assumption that the game admits a strictly convex potential function. In the absence of coupling constraints, we prove convergence to Nash equilibria under significantly weaker assumptions, not requiring a potential function. Namely, strict monotonicity of the game mapping is sufficient for convergence. We also derive the convergence rate of the algorithm for strongly monotone game maps.

Cited in

(15)

• Nash equilibrium seeking in N-coalition games via a gradient-free method
• Learning generalized Nash equilibria in multi-agent dynamical systems via extremum seeking control
• A payoff dynamics model for generalized Nash equilibrium seeking in population games
• Learning convex partitions and computing game-theoretic equilibria from best response queries
• Parametrized inexact-ADMM based coordination games: a normalized Nash equilibrium approach
• Measurement-based efficient resource allocation with demand-side adjustments
• Learning strict Nash equilibria through reinforcement
• Nash equilibrium seeking with prescribed performance
• A unified stochastic approximation framework for learning in games
• Specification-Guided Learning of Nash Equilibria with High Social Welfare
• Distributed control of a mobile robot multi-agent system for Nash equilibrium seeking with sampled neighbor information
• A delta dissipativity-based framework for generalized Nash equilibrium seeking in population games
• Convergence rate of payoff-based generalized Nash equilibrium learning
• Distributed stochastic Nash equilibrium seeking under heavy-tailed noises
• NashOpt: a Python library for computing generalized Nash equilibria

This page was built for publication: Learning Generalized Nash Equilibria in a Class of Convex Games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5223651)