Exploring Communication in Multi-Agent Reinforcement Learning Under Agent Malfunction

Rafael Pina, Varuna De Silva

2025

Abstract

Multi-Agent Reinforcement Learning (MARL) has grown into one of the most popular methods to tackle complex problems within multi-agent systems. Cooperative multi-agent systems denote scenarios where a team of agents must work together to achieve a certain common objective. Among several challenges studied in MARL, one problem is that agents might unexpectedly start acting abnormally, i.e., they can malfunction. Naturally, this malfunctioning agent will affect the behaviour of the team as a whole. In this paper, we investigate this problem and use the concepts of communication within the MARL literature to analyse how agents are affected when a malfunction happens within the team. We leverage popular MARL methods and build on them a communication module to allow the agents to broadcast messages to each other. Our results show that, while communication can boost learning in normal conditions, it can become redundant when malfunctions occur. We look into the team performances when malfunctions happen and we analyse in detail the patterns in the messages that the agents generate to communicate with each other. We observe that these can be strongly affected by malfunctions and we highlight the need to build appropriate architectures that can still leverage the power of communication in MARL when unexpected malfunctions happen.

Paper Citation

in Harvard Style

Pina R. and De Silva V. (2025). Exploring Communication in Multi-Agent Reinforcement Learning Under Agent Malfunction. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 445-452. DOI: 10.5220/0013383400003905

in Bibtex Style

@conference{icpram25,
author={Rafael Pina and Varuna De Silva},
title={Exploring Communication in Multi-Agent Reinforcement Learning Under Agent Malfunction},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={445-452},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013383400003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Exploring Communication in Multi-Agent Reinforcement Learning Under Agent Malfunction
SN - 978-989-758-730-6
AU - Pina R.
AU - De Silva V.
PY - 2025
SP - 445
EP - 452
DO - 10.5220/0013383400003905
PB - SciTePress