Learning Independently from Causality in Multi-Agent Environments

Rafael Pina, Varuna De Silva, Corentin Artaud

2023

Abstract

Multi-Agent Reinforcement Learning (MARL) comprises an area of growing interest in the field of machine learning. Despite notable advances, there are still problems that require investigation. The lazy agent pathology is a famous problem in MARL that denotes the event when some of the agents in a MARL team do not contribute to the common goal, letting the teammates do all the work. In this work, we aim to investigate this problem from a causality-based perspective. We intend to create the bridge between the fields of MARL and causality and argue about the usefulness of this link. We study a fully decentralised MARL setup where agents need to learn cooperation strategies and show that there is a causal relation between individual observations and the team reward. The experiments carried show how this relation can be used to improve independent agents in MARL, resulting not only on better performances as a team but also on the rise of more intelligent behaviours on individual agents.

Paper Citation

in Harvard Style

Pina R., De Silva V. and Artaud C. (2023). Learning Independently from Causality in Multi-Agent Environments. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 481-487. DOI: 10.5220/0011747900003411

in Bibtex Style

@conference{icpram23,
author={Rafael Pina and Varuna De Silva and Corentin Artaud},
title={Learning Independently from Causality in Multi-Agent Environments},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={481-487},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011747900003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Learning Independently from Causality in Multi-Agent Environments
SN - 978-989-758-626-2
AU - Pina R.
AU - De Silva V.
AU - Artaud C.
PY - 2023
SP - 481
EP - 487
DO - 10.5220/0011747900003411