An Active Learning Method for Solving Competitive Multiagent Decision-Making and Control Problems

• 成果类型: Article
• 署名作者: Fabiani, Filippo; Bemporad, Alberto
• 署名单位: IMT School for Advanced Studies Lucca
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2024.3477005
• 发表日期: 2025
• 页码: 2374-2389
• 关键词: games; observers; cost function; electricity; Complexity theory; Closed box; vectors; Smart grids; Probabilistic logic; Prediction algorithms; Active learning; competitive decision-making; generalized Nash equilibria; multiagent systems

摘要

To identify a stationary action profile for a population of competitive agents, each executing private strategies, we introduce a novel active-learning scheme where a centralized external observer (or entity) can probe the agents' reactions and recursively update simple local parametric estimates of the action-reaction mappings. Under very general working assumptions (not even assuming that a stationary profile exists), sufficient conditions are established to assess the asymptotic properties of the proposed active learning methodology so that, if the parameters characterizing the action-reaction mappings converge, a stationary action profile is achieved. Such conditions hence act also as certificates for the existence of such a profile. Extensive numerical simulations involving typical competitive multiagent control and decision-making problems illustrate the practical effectiveness of the proposed learning-based approach.