Back to search

Chalmers University of Technology

Multi-agent Communication via Reinforcement Learning in Social Networks

Abstract

dc:description.abstract

This thesis investigates the use of multi-agent reinforcement learning (MARL) to explore emergent communications of artificial agents in social networks. The main goal is understanding how agents develop shared communication protocols to perform collaborative tasks in complex environments. Using the World Color Survey (WCS) dataset, we implement a speaker-listener model in which an agent learns to name colors, providing a framework for observing the formation of communication strategies. In contrast to existing work, we utilize a shared neural network for both speaker’s and listener’s functions, which promotes equivalence in language use between agents and supports consistent communication. Extending the model to multiple agents, we studied how social network structure affects emergency communication, finding that denser networks produce more consistent language while sparser networks allow for greater diversity. The introduction of new agents and different levels of interaction between communities also affects language evolution, with newly generated languages found to be more similar to more populous collectives. However, the scale of our research could be improved. In future work, investigating larger populations of agents would be beneficial for better understanding scalability and refining our findings. Additionally, we could explore other communication modes, such as one to-many or many-to-one interactions, to gain a more comprehensive understanding of emergent communication in artificial systems.

Degree

thesis:*
Level thesis:degree_level
H
Department dc:contributor.department
Chalmers tekniska högskola / Institutionen för data och informationsteknik
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Liang, Zhitao
  • Wang, Wanqiu
Advisors dc:contributor.supervisor
  • David Thomas, Jonathan
  • Carlsson, Emil
Committee member dc:contributor.committeemember
  • Dubhashi, Devdatt

Subjects

dc:subject × 7

Rights

Language dc:language.iso
eng

Identifiers

dc:identifier.*
Dc Identifier Coursecode
DATX05

Chain of custody

source
Harvested from
Chalmers University of Technology
Base URL
odr.chalmers.se/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Liang, Zhitao; Wang, Wanqiu. Multi-agent Communication via Reinforcement Learning in Social Networks. H thesis, 2024. https://hdl.handle.net/20.500.12380/308564