Improving Multi-agent Coordination by Learning to Estimate Contention

2021/05/09 by Danassis, Panayiotis, Wiedemair, Florian, Faltings, Boi
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Multiagent Systems (cs.MA)

paper · doi:10.48550/arxiv.2105.04027

Abstract

We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems. We circumvent the traditional pitfalls of multi-agent learning (e.g., the moving target problem, the curse of dimensionality, or the need for mutually consistent actions) by relying on the ALMA heuristic as a coordination mechanism for each stage game. ALMA-Learning is decentralized, observes only own action/reward pairs, requires no inter-agent communication, and achieves near-optimal (<5% loss) and fair coordination in a variety of synthetic scenarios and a real-world meeting scheduling problem. The lightweight nature and fast learning constitute ALMA-Learning ideal for on-device deployment.

Related

• Temporal Fair Division in Multi-Agent Systems: From Precise Alternation Metrics to Scalable Coordination Proxies
• General Principles of Learning-Based Multi-Agent Systems
• ALMA: Hierarchical Learning for Composite Multi-Agent Tasks
• A Game-Theoretic Model and Best-Response Learning Method for Ad Hoc\n Coordination in Multiagent Systems
• MANSA: Learning Fast and Slow in Multi-Agent Systems