Adaptive learning for stochastic generalized Nash equilibrium problems

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. Three stochastic gradient strategies are developed by relying on a penalty-based approach where the constraine...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 4840 - 4844
Main Authors Chung-Kai Yu, van der Schaar, Mikaela, Sayed, Ali H.
Format Conference Proceeding Journal Article
LanguageEnglish
Published IEEE 01.03.2016
Subjects
Adaptive learning
Closed-form solutions
Conferences
Cost function
diffusion learning
Economic analysis
Electronics
Formulations
generalized Nash equilibrium
Learning
Nash equilibrium
Network topology
penalized approximation
Random variables
Statistical distributions
Stochasticity
Strategy
Online AccessGet full text
ISSN2379-190X
DOI10.1109/ICASSP.2016.7472597

Cover

More Information
Summary: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. Three stochastic gradient strategies are developed by relying on a penalty-based approach where the constrained GNEP formulation is replaced by a penalized unconstrained formulation. It is shown that this penalty solution is able to approach the Nash equilibrium in a stable manner within O(p), for small step-size values p. The operation of the algorithms is illustrated by considering the Cournot competition problem.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:2379-190X
DOI:10.1109/ICASSP.2016.7472597