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

• 成果类型: Article
• 署名作者: Xu, Jiapeng; Chen, Xiang; Tan, Ying; Gu, Guoxiang
• 署名单位: University of Windsor; University of Melbourne; Louisiana State University System; Louisiana State University
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2024.3419002
• 发表日期: 2024
• 页码: 8766-8773
• 关键词: games; Robustness; cost function; Vehicle dynamics; vectors; uncertainty; Noise measurement; Complementary control; decentralized control; H-infinity control; mean-field games (MFGs)

摘要

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 nth-order H-infinity controller. A consensus process example is provided to illustrate the robustness and performance of the proposed complementary mean-field control strategy.