Robust Mean-Field Games With Partial Observations: A Complementary Strategy

Document Type

Article

Publication Date

1-1-2024

Abstract

This work addresses a class of robust mean-field games for large-population multiagent systems, where each agent has access only to partial observations and is subject to an unknown bounded disturbance input. Unlike the existing literature in which formulated robust mean-field games are minimax problems, this work formulates a nonworst-case game problem and proposes a complementary control strategy with a decoupled design of mean-field tracking and robustness. A neat state-space realization for an operator Q concerning robustness is provided, incorporating parameters of an th-order H∞ controller. A consensus process example is provided to illustrate the robustness and performance of the proposed complementary mean-field control strategy.

Publication Source (Journal or Book title)

IEEE Transactions on Automatic Control

First Page

8766

Last Page

8773

This document is currently not available here.

Share

COinS