The University of Southampton
University of Southampton Institutional Repository

Temporal dynamics in emergent communication

Temporal dynamics in emergent communication
Temporal dynamics in emergent communication
Emergent communication is an approach designed to enhance the communicative capabilities of agents in multiagent systems. Unlike traditional multiagent communication fields, emergent communication allows agents to learn both the structure and content of their communication protocol with minimal constraints on character sets or vocabularies. This flexibility enables the development of more efficient, adaptable, and environment-specific languages compared to hand-crafted protocols. In this thesis, we identify a significant gap in the existing literature on emergent communication, specifically the lack of exploration of temporal dynamics of emergent languages. To address this, we investigate three dimensions of temporality in emergent communication. First, we examine the influence of communication duration on agent behaviour in a social deduction game called Werewolf, by allowing agents to communicate for varying lengths of time. Our findings reveal that agents develop unexpected strategies and that our modifications enhance their ability to converge on a common language. Second, we study the emergence of temporal references, or words indicating relative positions in time. We introduce a novel environment where agents must communicate about temporal relationships within a dataset. The results demonstrate that agents can learn to reference different time steps to solve the environment successfully. Third, we explore how agents communicate about local spatio-temporal relationships within a single observation. The results not only show that the agents learn to communicate about such relationships, but also that this language can be human interpretable. The contributions presented in this thesis pave the way for more efficient and adaptable protocols in multiagent communicative settings.
University of Southampton
Lipinski, Olaf
88709b3f-c356-45c7-8520-cb49d7b07960
Lipinski, Olaf
88709b3f-c356-45c7-8520-cb49d7b07960
Norman, Tim
663e522f-807c-4569-9201-dc141c8eb50d
Sobey, Adam
e850606f-aa79-4c99-8682-2cfffda3cd28
Cerutti, Federico
9c2341aa-4699-49b4-9474-64f97b2e4224

Lipinski, Olaf (2025) Temporal dynamics in emergent communication. University of Southampton, Doctoral Thesis, 120pp.

Record type: Thesis (Doctoral)

Abstract

Emergent communication is an approach designed to enhance the communicative capabilities of agents in multiagent systems. Unlike traditional multiagent communication fields, emergent communication allows agents to learn both the structure and content of their communication protocol with minimal constraints on character sets or vocabularies. This flexibility enables the development of more efficient, adaptable, and environment-specific languages compared to hand-crafted protocols. In this thesis, we identify a significant gap in the existing literature on emergent communication, specifically the lack of exploration of temporal dynamics of emergent languages. To address this, we investigate three dimensions of temporality in emergent communication. First, we examine the influence of communication duration on agent behaviour in a social deduction game called Werewolf, by allowing agents to communicate for varying lengths of time. Our findings reveal that agents develop unexpected strategies and that our modifications enhance their ability to converge on a common language. Second, we study the emergence of temporal references, or words indicating relative positions in time. We introduce a novel environment where agents must communicate about temporal relationships within a dataset. The results demonstrate that agents can learn to reference different time steps to solve the environment successfully. Third, we explore how agents communicate about local spatio-temporal relationships within a single observation. The results not only show that the agents learn to communicate about such relationships, but also that this language can be human interpretable. The contributions presented in this thesis pave the way for more efficient and adaptable protocols in multiagent communicative settings.

Text
Olaf Lipinski PhD Thesis - Version of Record
Available under License University of Southampton Thesis Licence.
Download (2MB)
Text
Final-thesis-submission-Examination-Mr-Olaf-Lipinski
Restricted to Repository staff only

More information

Published date: February 2025

Identifiers

Local EPrints ID: 498258
URI: http://eprints.soton.ac.uk/id/eprint/498258
PURE UUID: 33721ad8-f8ff-4413-9c37-b61eb4e950c6
ORCID for Olaf Lipinski: ORCID iD orcid.org/0000-0002-2023-7617
ORCID for Tim Norman: ORCID iD orcid.org/0000-0002-6387-4034
ORCID for Adam Sobey: ORCID iD orcid.org/0000-0001-6880-8338

Catalogue record

Date deposited: 13 Feb 2025 17:31
Last modified: 03 Jul 2025 02:26

Export record

Contributors

Author: Olaf Lipinski ORCID iD
Thesis advisor: Tim Norman ORCID iD
Thesis advisor: Adam Sobey ORCID iD
Thesis advisor: Federico Cerutti

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×