Hybrid Fuzzy–Reinforcement-Learning Control of Agent-Based Contagion Dynamics on Graphs: Drift Conditions, Topology Dependence and Benchmark Evidence
Information · 16.11.2026 · 17 (11) · 1157
DOI: 10.3390/info17111157 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 16.11.2026. Verfasst von Abdelfattah Oulaika und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Agent-based models are widely used to study complex adaptive dynamics in heterogeneous populations, largely because they capture how autonomous agents behave without central coordination. The same decentralization makes stability hard to establish analytically. We take one controlled two-state contagion model on a graph, steered by a single broadcast scalar, and study six controllers on it: a fuzzy inference system, a tabular reinforcement learner, and four ways of combining them. The analysis is a stochastic drift argument on a Perron-weighted Lyapunov function that asks of each controller only a lower bound on its effort above an activation level, not a Lyapunov function of its own. The spectral radius of the interaction operator sets a critical effort, and a controller whose floor exceeds it keeps the population regulated. Each hybrid inherits a floor from the two it combines, which separates the four: safety blending and the hierarchical override keep a floor whatever the learner does, convex fusion and switching do not. Asynchronous updates follow from the same argument; delays and interruptions do not, and are left to simulation. Its application settings are readings of one model rather than independent validations. The trained learner cuts the fuzzy controller’s cost by 61%, yet eight tuned classical and model-based baselines all cost less than any of the six. The hybrids contain the learner’s failure outside its training range, but that failure is produced by the training protocol: a wider range of initial states removes it. A controller call costs the same up to 106 agents, and three further models mark the scope: control is essential in a cascade, marginal under segregation, and counterproductive where it acts non-monotonically.
Zitieren
APA
Oulaika, A., Barrouch, M., Bouhanch, Z., Ahourag, A., Barhdadi, M., Moutaouakil, K. E., & Palade, V. (2026). Hybrid Fuzzy–Reinforcement-Learning Control of Agent-Based Contagion Dynamics on Graphs: Drift Conditions, Topology Dependence and Benchmark Evidence. Information, 17(11), 1157. https://doi.org/10.3390/info17111157
Vancouver
Oulaika A, Barrouch M, Bouhanch Z, Ahourag A, Barhdadi M, Moutaouakil KE, et al. Hybrid Fuzzy–Reinforcement-Learning Control of Agent-Based Contagion Dynamics on Graphs: Drift Conditions, Topology Dependence and Benchmark Evidence. Information. 2026;17(11):1157. doi:10.3390/info17111157
BibTeX
@article{Oulaika2026,
author = {Oulaika, Abdelfattah and Barrouch, Mohammed and Bouhanch, Zakaria and Ahourag, Abdellah and Barhdadi, Mohamed and Moutaouakil, Karim El and Palade, Vasile},
title = {Hybrid Fuzzy–Reinforcement-Learning Control of Agent-Based Contagion Dynamics on Graphs: Drift Conditions, Topology Dependence and Benchmark Evidence},
journal = {Information},
year = {2026},
volume = {17},
number = {11},
pages = {1157},
doi = {10.3390/info17111157}
}
EUVIMED