Gist Trace-based Learning: Efficient Convention Emergence from Multilateral Interactions

• Published in: ACM transactions on autonomous and adaptive systems 2022-01, Vol.16 (1), p.1-20, Article 2
• Main Authors: Hu, Shuyue, Leung, Chin-Wing, Leung, Ho-Fung, Liu, Jiamou
• Format: Article
• Language: English
• Subjects: Computing methodologies; Multi-agent systems
• ISSN: 1556-4665; 1556-4703
• DOI: 10.1145/3502199

The concept of conventions has attracted much attention in the multi-agent system research. In this article, we study the emergence of conventions from repeated n-player coordination games. Distributed agents learn their policies independently and are capable of observing their neighbours in a network topology. We distinguish two types of information representation about the observations: gist trace and verbatim trace. We conjecture that learning based on the gist trace, which overlooks the details and focuses only on the general choice of action of a neighbourhood, should achieve efficient convention emergence. To this end, a novel learning method that makes use of the gist trace is proposed. The experimental results confirm that the proposed method establishes conventions much faster than the state-of-the-art learning methods across diverse settings of multi-agent systems. In particular, the use of gist trace derived at a low level of abstraction further improves the efficiency of convention emergence.