Distributed Learning for Stochastic Generalized Nash Equilibrium Problems

DOI10.1109/TSP.2017.2695451MaRDI QIDQ4621770zbMATH OpenFDO

Authors Chung-Kai Yu, Mihaela van der Schaar, Ali H. Sayed

Publication date 8 February 2019

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1608.00039

Mathematics Subject Classification ID

Rationality and learning in game theory (91A26) Applications of game theory (91A80) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: This work examines a stochastic formulation of the generalized Nash equilibrium problem (GNEP) where agents are subject to randomness in the environment of unknown statistical distribution. We focus on fully-distributed online learning by agents and employ penalized individual cost functions to deal with coupled constraints. Three stochastic gradient strategies are developed with constant step-sizes. We allow the agents to use heterogeneous step-sizes and show that the penalty solution is able to approach the Nash equilibrium in a stable manner within $O(m{u}_{e}xtmax)$, for small step-size value $m{u}_{e}xtmax$ and sufficiently large penalty parameters. The operation of the algorithm is illustrated by considering the network Cournot competition problem.

Cited in

(15)

• An operator splitting approach for distributed generalized Nash equilibria computation
• Variance-based subgradient extragradient method for stochastic variational inequality problems
• Privacy impact on generalized Nash equilibrium in peer-to-peer electricity market
• Fast generalized Nash equilibrium seeking under partial-decision information
• Learning generalized Nash equilibria in multi-agent dynamical systems via extremum seeking control
• Stochastic generalized Nash equilibrium seeking under partial-decision information
• Parametrized inexact-ADMM based coordination games: a normalized Nash equilibrium approach
• Continuous-time fully distributed generalized Nash equilibrium seeking for multi-integrator agents
• Game-Theoretic Learning and Distributed Optimization in Memoryless Multi-Agent Systems
• Distributed variable sample-size gradient-response and best-response schemes for stochastic Nash equilibrium problems
• Distributed Learning in Non-Convex Environments— Part II: Polynomial Escape From Saddle-Points
• Asynchronous schemes for stochastic and misspecified potential games and nonconvex optimization
• Achieving Pareto Optimality Through Distributed Learning
• On the linear convergence of distributed Nash equilibrium seeking for multi-cluster games under partial-decision information
• Distributed stochastic Nash equilibrium seeking under heavy-tailed noises

This page was built for publication: Distributed Learning for Stochastic Generalized Nash Equilibrium Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4621770)