Fuzzy-Guided Exploration for Multi-Agent Reinforcement Learning in Traffic Signal Control
Mathematics · 02.06.2026 · 14 (11) · 1942
DOI: 10.3390/math14111942 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 02.06.2026. Verfasst von Dejan Ćiprovski und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vlatacom Institute, European Union, Science Fund of the Republic of Serbia.
Abstract (Originalsprache)
Traffic signal control over urban networks requires coordinating the controllers of multiple signalized intersections toward a shared goal of minimizing network-wide congestion. Multi-agent reinforcement learning (MARL) methods have shown considerable promise in this setting. The epsilon–greedy exploration strategy adopted by many of these methods treats every candidate signal phase as equally worth trying, discarding the rich domain knowledge that traffic theory already provides. This paper proposes fuzzy-guided exploration, in which a multi-criteria fuzzy inference system uses local traffic conditions, with phase pressure as its primary input, to assign each candidate phase a priority. These priorities define a sampling distribution used in place of the uniform draw. We evaluate the method across four MARL algorithms covering independent learning (IQL) and the centralized training with decentralized execution paradigm (VDN, QMIX, and QPLEX) on both a synthetic grid and a real-world network. Fuzzy-guided exploration consistently improves upon the baseline in all combinations, with tangible gains on the synthetic grid and substantially larger improvements on the real-world network. These findings demonstrate that exploration is an effective intervention point for domain-knowledge integration in cooperative MARL, and that pressure-based scoring provides a well-suited signal to serve that role in traffic signal control.
Förderung
- Vlatacom Institute
- European Union
- Science Fund of the Republic of Serbia
Zitieren
APA
Ćiprovski, D., Ilić, N., Božilović, B., & Vučetić, M. (2026). Fuzzy-Guided Exploration for Multi-Agent Reinforcement Learning in Traffic Signal Control. Mathematics, 14(11), 1942. https://doi.org/10.3390/math14111942
Vancouver
Ćiprovski D, Ilić N, Božilović B, Vučetić M. Fuzzy-Guided Exploration for Multi-Agent Reinforcement Learning in Traffic Signal Control. Mathematics. 2026;14(11):1942. doi:10.3390/math14111942
BibTeX
@article{iprovski2026,
author = {Ćiprovski, Dejan and Ilić, Nemanja and Božilović, Boško and Vučetić, Miljan},
title = {Fuzzy-Guided Exploration for Multi-Agent Reinforcement Learning in Traffic Signal Control},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {11},
pages = {1942},
doi = {10.3390/math14111942}
}
EUVIMED