EUVIMEDEUVIMED entdecken
Crossref

Boosting the Training of Deep Reinforcement Learning Traffic Control by Using the World Model

Pengbo Wang, Yisheng Lv, Jingwei Ge, Li Li

IEEE Intelligent Transportation Systems Magazine · 2025-05 · 17 (3) · 58-66

DOI: 10.1109/mits.2024.3440069 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Intelligent Transportation Systems Magazine, 2025-05. Verfasst von Pengbo Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep reinforcement learning (DRL) traffic control attracts increasing interest since it is widely viewed as a powerful tool for alleviating congestion that significantly impacts people’s daily lives. However, traditional DRL models require a substantial amount of interactive data that are difficult to collect in both field and simulation tests. To overcome these challenges, this article adopts a world model for better training of DRL models for traffic control. The proposed world model can quickly learn traffic dynamics and the influence of traffic control based on limited field and simulation data. The DRL control model can then be established based on the training data generated by the world model instead. Experimental results demonstrate that DRL traffic control using world models can achieve a noticeably better signal control strategy, providing a promising solution to optimize urban traffic.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, P., Lv, Y., Ge, J., & Li, L. (2025). Boosting the Training of Deep Reinforcement Learning Traffic Control by Using the World Model. IEEE Intelligent Transportation Systems Magazine, 17(3), 58-66. https://doi.org/10.1109/mits.2024.3440069

Vancouver

Wang P, Lv Y, Ge J, Li L. Boosting the Training of Deep Reinforcement Learning Traffic Control by Using the World Model. IEEE Intelligent Transportation Systems Magazine. 2025;17(3):58-66. doi:10.1109/mits.2024.3440069

BibTeX
@article{Wang2025,
  author = {Wang, Pengbo and Lv, Yisheng and Ge, Jingwei and Li, Li},
  title = {Boosting the Training of Deep Reinforcement Learning Traffic Control by Using the World Model},
  journal = {IEEE Intelligent Transportation Systems Magazine},
  year = {2025},
  volume = {17},
  number = {3},
  pages = {58--66},
  doi = {10.1109/mits.2024.3440069}
}
Kostenlos starten →