Articles Vol. 5, No. 1 (2027)
Achya Arifudin, Budiman Budiman, Titan Parama Yoga, Nur Alamsyah
Universitas Informatika dan Bisnis Indonesia ROR
10.58477/cj.v5i1.532 Published: 2027-02-01
Abstract

Adaptive traffic signal control can respond to changing traffic demand more effectively than fixed-time operation, but deep reinforcement learning performance depends strongly on environment design, state representation, and reward formulation. This study evaluates a tuned Deep Q-Network (DQN) with a quadratic congestion penalty for two-phase traffic signal control. A dataset-driven environment paired two street segments as conflicting approaches and applied chronological training, validation, and test splits. No external microscopic traffic simulator was used; instead, the observed demand sequences drove a custom queue-based Gymnasium environment. Hyperparameters were tuned using the validation set, while final models were evaluated across three random seeds under normal, peak, incident, and imbalanced-demand scenarios. The quadratic DQN was compared with a linear-reward DQN, a fixed 50:50 controller, and a rule-based adaptive controller. Under normal traffic, the quadratic DQN achieved a mean queue of 22.16 vehicles, a 95th-percentile queue of 35.11 vehicles, throughput of 594.24 vehicles, and a service rate of 95.42%. Compared with the linear DQN, it reduced queue imbalance by 5.15% and action changes by 12.82%, although mean queue and throughput did not improve. The rule-based controller produced the best overall performance. These findings indicate that quadratic reward shaping can improve policy balance and stability, but simpler controllers may remain competitive when training data are limited. Fair baselines and multi-seed evaluation remain essential practices.

How to Cite

How to Cite

Arifudin, M. A., Budiman, B., Yoga, T. P., & Alamsyah, N. (2027). Evaluation of a Deep Q-Network with a Quadratic Reward Function for Two-Phase Traffic Signal Control. Computer Journal, 5(1), 61-75. https://doi.org/10.58477/cj.v5i1.532
Achya Arifudin

Universitas Informatika dan Bisnis Indonesia

Department of Informatics, Universitas Informatika dan Bisnis Indonesia, Bandung City, West Java Province, Indonesia.

Budiman Budiman

Universitas Informatika dan Bisnis Indonesia

Department of Informatics, Universitas Informatika dan Bisnis Indonesia, Bandung City, West Java Province, Indonesia.

Titan Parama Yoga

Universitas Informatika dan Bisnis Indonesia

Department of Information Systems, Universitas Informatika dan Bisnis Indonesia, Bandung City, West Java Province, Indonesia.

Nur Alamsyah

Universitas Informatika dan Bisnis Indonesia

Department of Information Systems, Universitas Informatika dan Bisnis Indonesia, Bandung City, West Java Province, Indonesia.

Issue Vol. 5 No. 1 (2027)
SectionArticles
DOI10.58477/cj.v5i1.532
Publication Date2027-02-01
Pages61-75
  • Adeniran, A. O., Adeniran, A. A., Ogieva, M. O., & Ogwuche, G. (2026). Adoption of Intelligent Transport Systems (ITS) in urban transportation planning. Discover Global Society, 4, Article 13. https://doi.org/10.1007/s44282-025-00312-3
  • Bie, Y., Ji, Y., & Ma, D. (2024). Multi-agent deep reinforcement learning collaborative traffic signal control method considering intersection heterogeneity. Transportation Research Part C: Emerging Technologies, 164, 104663. https://doi.org/10.1016/j.trc.2024.104663
  • Bouktif, S., Cheniki, A., Ouni, A., & El-Sayed, H. (2023). Deep reinforcement learning for traffic signal control with consistent state and reward design approach. Knowledge-Based Systems, 267, 110440. https://doi.org/10.1016/j.knosys.2023.110440
  • Brocchini, L., Wang, C., & Pratelli, A. (2026). Intelligent traffic control strategies for road networks: A taxonomy-based perspective on methods, applications, and future directions. Applied Sciences, 16(13), 6341. https://doi.org/10.3390/app16136341
  • Cai, C., & Wei, M. (2024). Adaptive urban traffic signal control based on enhanced deep reinforcement learning. Scientific Reports, 14, 14116. https://doi.org/10.1038/s41598-024-64885-w
  • Chinyanga, F., Sibiya, M., & Sumbwanyambe, M. (2026). Improving urban traffic efficiency through IoT-based intelligent traffic control systems and machine learning. IEEE Open Journal of Intelligent Transportation Systems, 7, 1552–1562. https://doi.org/10.1109/OJITS.2026.3705979
  • Chu, K.-F., Lam, A. Y. S., & Li, V. O. K. (2022). Traffic signal control using end-to-end off-policy deep reinforcement learning. IEEE Transactions on Intelligent Transportation Systems, 23(7), 7184–7195. https://doi.org/10.1109/TITS.2021.3067057
  • Colpo, L. R., & Gomes, H. M. (2026). An adaptative fuzzy logic control with road class classifications based on machine learning approaches. Mechanics Based Design of Structures and Machines, 54(1), Article 2523577. https://doi.org/10.1080/15397734.2025.2523577
  • Fokker, E. S., van der Mei, R. D., & Dugundji, E. R. (2026). From models to mobility systems: A survey of multimodal dynamic traffic assignment. Operations Research Forum, 7, Article 58. https://doi.org/10.1007/s43069-026-00642-1
  • Haddad, T. A., Hedjazi, D., & Aouag, S. (2022). A deep reinforcement learning-based cooperative approach for multi-intersection traffic signal control. Engineering Applications of Artificial Intelligence, 114, 105019. https://doi.org/10.1016/j.engappai.2022.105019
  • Hassan, M., Turjo, T. D., Rambe, A. H., Jusoh, M., Islam, M. K., Hafizur Rahman, M. M., Alam, M. S., & Rahman, M. M. (2026). A comprehensive survey of adaptive traffic signal control: Methods, applications, challenges, and future research. Archives of Computational Methods in Engineering. Advance online publication. https://doi.org/10.1007/s11831-026-10574-y
  • Huang, G., Wang, H., Zhang, L., & Xu, D. (2026). The impact of ride-hailing regulations on traffic congestion: Evidence from China. Transportation Research Part A: Policy and Practice, 203, 104765. https://doi.org/10.1016/j.tra.2025.104765
  • Jin, J., Wu, S., Zhang, P., Zhang, X., Yin, C., & Dong, C. (2026). Hybrid action space approach to traffic signal optimization using deep reinforcement learning. Computers & Operations Research, 189, 107391. https://doi.org/10.1016/j.cor.2026.107391
  • Kang, L., Huang, H., Lu, W., & Liu, L. (2023). A dueling deep Q-network method for low-carbon traffic signal control. Applied Soft Computing, 141, 110304. https://doi.org/10.1016/j.asoc.2023.110304
  • Katzilieris, K., Kampitakis, E., & Vlahogianni, E. I. (2026). A multi-agent reinforcement learning framework for integrated traffic signal control and dynamic bus lane access management. Transportation Research Part C: Emerging Technologies, 182, 105391. https://doi.org/10.1016/j.trc.2025.105391
  • Liu, H., Li, X., Zhang, L., & Cheng, R. (2026). Bridging phase and timing: A joint Q-value learning framework for synergistic traffic signal control at consecutive arterial road intersections. Physica A: Statistical Mechanics and Its Applications, 688, 131421. https://doi.org/10.1016/j.physa.2026.131421
  • Manikandan, R., & Pandian, J. A. (2026). A systematic review of traditional and reinforcement learning-based traffic signal control methods. Archives of Computational Methods in Engineering. Advance online publication. https://doi.org/10.1007/s11831-026-10692-7
  • Mao, F., Li, Z., & Li, L. (2022). A comparison of deep reinforcement learning models for isolated traffic signal control. IEEE Intelligent Transportation Systems Magazine, 15(1), 160–180. https://doi.org/10.1109/MITS.2022.3144797
  • Oguchi, T., Iryo, M., & Toriumi, A. (2026). Traffic engineering. In Pioneering the future for traffic and safety sciences: Transdisciplinary wisdom (pp. 77–101). Springer.
  • Ren, F., Dong, W., Zhao, X., Zhang, F., Kong, Y., & Yang, Q. (2024). Two-layer coordinated reinforcement learning for traffic signal control in traffic network. Expert Systems with Applications, 235, 121111. https://doi.org/10.1016/j.eswa.2023.121111
  • Sabbaghian, M. H., Molan, A. M., Hummer, J. E., & Osafo-Gyamfi, S. (2026). Traffic operation and safety performance of the new roundabout and median U-turn combination design in comparison to four roundabout designs. International Journal of Transportation Science and Technology. Advance online publication. https://doi.org/10.1016/j.ijtst.2025.09.007
  • Tan, X., Zhou, Y., & Jiao, X. (2025). Traffic signal control based on deep reinforcement learning using state fusion and trend reward. Engineering Applications of Artificial Intelligence, 159, 111701. https://doi.org/10.1016/j.engappai.2025.111701
  • ur Rehman, H. M. R., Gul, M. J., Younas, R., Jhandir, M. Z., Alvarez, R. M., Miro, Y., & Ashraf, I. (2026). End-to-end emergency response protocol for tunnel accidents augmentation with reinforcement learning. Scientific Reports, 16, 6226. https://doi.org/10.1038/s41598-026-37191-w
  • Wang, R., Zhang, J., Wang, X., He, H., & Zou, Y. (2026). Multi-modal and multi-agent reinforcement learning framework for urban traffic flow prediction and signal control optimization. Scientific Reports, 16, 7612. https://doi.org/10.1038/s41598-026-37722-5
  • Wang, T., Zhu, Z., Zhang, J., Tian, j., & Zhang, W. (2024). A large-scale traffic signal control algorithm based on multi-layer graph deep reinforcement learning. Transportation Research Part C: Emerging Technologies, 162, 104582. https://doi.org/10.1016/j.trc.2024.104582
  • Wei, W., Zheng, L., & El Esawey, M. (2026). Model-agnostic meta-learning-based real-time traffic conflict prediction with limited sample at heterogeneous signalized intersections. IEEE Transactions on Intelligent Transportation Systems, 27(4), 4811–4823. https://doi.org/10.1109/TITS.2025.3648403
  • Xiao, H., Li, H., Wang, Z., Yang, Z., Qi, S., Zhang, J., Cai, D., & Yin, J. (2026). Intelligent traffic signal control based on reinforcement learning: A survey. Artificial Intelligence Review, 59, Article 128. https://doi.org/10.1007/s10462-026-11530-9
  • Yu, J., Laharotte, P.-A., Han, Y., & Leclercq, L. (2023). Decentralized signal control for multi-modal traffic network: A deep reinforcement learning approach. Transportation Research Part C: Emerging Technologies, 154, 104281. https://doi.org/10.1016/j.trc.2023.104281
  • Zhao, H., Dong, C., Cao, j., & Chen, Q. (2024). A survey on deep reinforcement learning approaches for traffic signal control. Engineering Applications of Artificial Intelligence, 133, 108100. https://doi.org/10.1016/j.eswa.2024.108100
  • Zhao, M., Zou, Y., Wang, J., Li, D., & Yang, Q. (2026). Safe and scalable multi-agent optimization for autonomous electric taxi dispatching via a two-stage reinforcement learning framework. IEEE Transactions on Automation Science and Engineering. Advance online publication. https://doi.org/10.1109/TASE.2026.3651287
License

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Article Statistics
Download data is not yet available.
Similar Articles