Gestión semafórica basada en aprendizaje por refuerzo: Q-Learning y SARSA
Prospectiva · 30.06.2026 · 24 (2)
DOI: 10.15665/q4jsbg56 ↗Kurz gefasst
Fachartikel in der Zeitschrift Prospectiva, online erschienen am 30.06.2026. Verfasst von Juan Pablo Hoyos und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
The accelerated growth of urban traffic has revealed the limitations of traditional traffic lights with fixed timing, which do not adapt to the variability of traffic patterns. In response, this work proposes the use of reinforcement learning algorithms, specifically Q-Learning and SARSA, to implement more efficient and dynamic traffic light control systems. Simulations are developed in the SUMO (Simulation of Urban Mobility) environment to compare the performance of these models against traditional traffic lights, with the average waiting time per vehicle as the main metric. The results allow us to evaluate the adaptability and superiority of intelligent models in most traffic scenarios, demonstrating their potential as an effective solution for managing vehicle flow in urban environments.
Zitieren
APA
Hoyos, J. P., Cartagena, J. J. V., & Raudales, L. A. D. (2026). Gestión semafórica basada en aprendizaje por refuerzo: Q-Learning y SARSA. Prospectiva, 24(2). https://doi.org/10.15665/q4jsbg56
Vancouver
Hoyos JP, Cartagena JJV, Raudales LAD. Gestión semafórica basada en aprendizaje por refuerzo: Q-Learning y SARSA. Prospectiva. 2026;24(2). doi:10.15665/q4jsbg56
BibTeX
@article{Hoyos2026,
author = {Hoyos, Juan Pablo and Cartagena, Jose Joaquin Vergara and Raudales, Leober Arturo Duran},
title = {Gestión semafórica basada en aprendizaje por refuerzo: Q-Learning y SARSA},
journal = {Prospectiva},
year = {2026},
volume = {24},
number = {2},
doi = {10.15665/q4jsbg56}
}
EUVIMED