Reinforcement Communication Learning in Different Social Network Structures

TL;DR

This paper investigates how different social network structures influence the emergence and properties of communication systems in multi-agent reinforcement learning communities, highlighting the role of network connectivity and agent degree.

Contribution

It demonstrates that social network topology significantly affects communication convergence and convention consistency in decentralized reinforcement learning agents.

Findings

Global connectivity promotes shared, symmetric communication systems.

Higher agent degree correlates with less consistent communicative conventions.

Network structure influences the emergence of linguistic conventions.

Abstract

Social network structure is one of the key determinants of human language evolution. Previous work has shown that the network of social interactions shapes decentralized learning in human groups, leading to the emergence of different kinds of communicative conventions. We examined the effects of social network organization on the properties of communication systems emerging in decentralized, multi-agent reinforcement learning communities. We found that the global connectivity of a social network drives the convergence of populations on shared and symmetric communication systems, preventing the agents from forming many local "dialects". Moreover, the agent's degree is inversely related to the consistency of its use of communicative conventions. These results show the importance of the basic properties of social network structure on reinforcement communication learning and suggest a new interpretation of findings on human convergence on word conventions.