Solving Decision-Dependent Games by Learning from Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wood, Killian, Zamzam, Ahmed, Dall'Anese, Emiliano
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929319978205184
author Wood, Killian
Zamzam, Ahmed
Dall'Anese, Emiliano
author_facet Wood, Killian
Zamzam, Ahmed
Dall'Anese, Emiliano
contents This paper tackles the problem of solving stochastic optimization problems with a decision-dependent distribution in the setting of stochastic strongly-monotone games and when the distributional dependence is unknown. A two-stage approach is proposed, which initially involves estimating the distributional dependence on decision variables, and subsequently optimizing over the estimated distributional map. The paper presents guarantees for the approximation of the cost of each agent. Furthermore, a stochastic gradient-based algorithm is developed and analyzed for finding the Nash equilibrium in a distributed fashion. Numerical simulations are provided for a novel electric vehicle charging market formulation using real-world data.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17471
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Solving Decision-Dependent Games by Learning from Feedback
Wood, Killian
Zamzam, Ahmed
Dall'Anese, Emiliano
Systems and Control
Optimization and Control
This paper tackles the problem of solving stochastic optimization problems with a decision-dependent distribution in the setting of stochastic strongly-monotone games and when the distributional dependence is unknown. A two-stage approach is proposed, which initially involves estimating the distributional dependence on decision variables, and subsequently optimizing over the estimated distributional map. The paper presents guarantees for the approximation of the cost of each agent. Furthermore, a stochastic gradient-based algorithm is developed and analyzed for finding the Nash equilibrium in a distributed fashion. Numerical simulations are provided for a novel electric vehicle charging market formulation using real-world data.
title Solving Decision-Dependent Games by Learning from Feedback
topic Systems and Control
Optimization and Control
url https://arxiv.org/abs/2312.17471