ROMA-iQSS: An Objective Alignment Approach via State-Based Value Learning and ROund-Robin Multi-Agent Scheduling

arXiv:2404.03984v1 Announce Type: cross
Abstract: Effective multi-agent collaboration is imperative for solving complex, distributed problems. In this context, two key challenges must be addressed: first, autonomously identifying optimal objectives for collective outcomes; second, aligning these objectives among agents. Traditional frameworks, often reliant on centralized learning, struggle with scalability and efficiency in large multi-agent systems. To overcome these issues, we introduce a decentralized state-based value learning algorithm that enables agents to independently discover optimal states. Furthermore, we introduce a novel mechanism …

abstract agent agents alignment arxiv challenges collaboration collective context cs.lg cs.ma cs.sy distributed eess.sy frameworks key multi-agent scheduling state struggle type value via