The Emergence of Norms via Contextual Agreements in Open Societies

TL;DR

This paper introduces reinforcement learning methods enabling agents in open societies to develop norms through semantic agreements on resource use, even with multiple roles and limited interaction, advancing understanding of social norm emergence.

Contribution

It proposes novel reinforcement learning approaches for agents to form norms via semantic agreements in complex, open social environments with multiple roles and no shared knowledge.

Findings

Agents efficiently converge to norms in various society sizes.

High convergence speed even in complex settings.

Effective social learning processes demonstrated.

Abstract

This paper explores the emergence of norms in agents' societies when agents play multiple -even incompatible- roles in their social contexts simultaneously, and have limited interaction ranges. Specifically, this article proposes two reinforcement learning methods for agents to compute agreements on strategies for using common resources to perform joint tasks. The computation of norms by considering agents' playing multiple roles in their social contexts has not been studied before. To make the problem even more realistic for open societies, we do not assume that agents share knowledge on their common resources. So, they have to compute semantic agreements towards performing their joint actions. %The paper reports on an empirical study of whether and how efficiently societies of agents converge to norms, exploring the proposed social learning processes w.r.t. different society sizes, and the ways agents are connected. The results reported are very encouraging, regarding the speed of the learning process as well as the convergence rate, even in quite complex settings.