Teaching Coordination to Selfish Learning Agents in Resource-Constrained Partially Observable Markov Games

• 成果类型: Article
• 署名作者: Tsaousoglou, Georgios
• 署名单位: Technical University of Denmark
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2024.3515651
• 发表日期: 2025
• 页码: 3449-3455
• 关键词: games; resource management; COSTS; cost function; mechanism design; education; dynamic scheduling; trajectory; Smart grids; simulation; Distributed control; game-theoretic control; multiagent reinforcement learning; online mechanism

摘要

Of increasing relevance to engineering systems are problems that include online resource allocation to agents that feature adaptation and learning capabilities. This article considers the case where a coordinator gets to design a resource allocation mechanism (i.e., a bidding-allocation-rewards protocol) to efficiently allocate a resource to selfish agents that try to gain access by learning to communicate strategically. Toward aligning the agents' incentives with the social objective, a critical-value-based mechanism is proposed. Analytic results are presented for a simple, stylized setting, whereas simulation results for a use case with reinforcement learning agents controlling flexible loads in the smart grid demonstrate the mechanism's ability to teach coordinated behavior to the distributed learners.