RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control

Mingyuan Li, Jiahao Wang, Guangsheng Yu, Xu Wang, Qianrun Chen, Wei Ni, Lixiang Li, Haipeng Peng
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36192-36214, 2025.

Abstract

Reinforcement Learning (RL) optimizes Traffic Signal Control (TSC) to reduce congestion and emissions, but real-world TSC systems face challenges like adversarial attacks and missing data, leading to incorrect signal decisions and increased congestion. Existing methods, limited to offline data predictions, address only one issue and fail to meet TSC’s dynamic, real-time needs. We propose RobustLight, a novel framework with an enhanced, plug-and-play diffusion model to improve TSC robustness against noise, missing data, and complex patterns by restoring attacked data. RobustLight integrates two algorithms to recover original data states without altering existing TSC platforms. Using a dynamic state infilling algorithm, it trains the diffusion model online. Experiments on real-world datasets show RobustLight improves recovery performance by up to 50.43% compared to baseline scenarios. It effectively counters diverse adversarial attacks and missing data. The relevant datasets and code are available at Github.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-li25cs, title = {{R}obust{L}ight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control}, author = {Li, Mingyuan and Wang, Jiahao and Yu, Guangsheng and Wang, Xu and Chen, Qianrun and Ni, Wei and Li, Lixiang and Peng, Haipeng}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {36192--36214}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/li25cs/li25cs.pdf}, url = {https://proceedings.mlr.press/v267/li25cs.html}, abstract = {Reinforcement Learning (RL) optimizes Traffic Signal Control (TSC) to reduce congestion and emissions, but real-world TSC systems face challenges like adversarial attacks and missing data, leading to incorrect signal decisions and increased congestion. Existing methods, limited to offline data predictions, address only one issue and fail to meet TSC’s dynamic, real-time needs. We propose RobustLight, a novel framework with an enhanced, plug-and-play diffusion model to improve TSC robustness against noise, missing data, and complex patterns by restoring attacked data. RobustLight integrates two algorithms to recover original data states without altering existing TSC platforms. Using a dynamic state infilling algorithm, it trains the diffusion model online. Experiments on real-world datasets show RobustLight improves recovery performance by up to 50.43% compared to baseline scenarios. It effectively counters diverse adversarial attacks and missing data. The relevant datasets and code are available at Github.} }
Endnote
%0 Conference Paper %T RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control %A Mingyuan Li %A Jiahao Wang %A Guangsheng Yu %A Xu Wang %A Qianrun Chen %A Wei Ni %A Lixiang Li %A Haipeng Peng %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-li25cs %I PMLR %P 36192--36214 %U https://proceedings.mlr.press/v267/li25cs.html %V 267 %X Reinforcement Learning (RL) optimizes Traffic Signal Control (TSC) to reduce congestion and emissions, but real-world TSC systems face challenges like adversarial attacks and missing data, leading to incorrect signal decisions and increased congestion. Existing methods, limited to offline data predictions, address only one issue and fail to meet TSC’s dynamic, real-time needs. We propose RobustLight, a novel framework with an enhanced, plug-and-play diffusion model to improve TSC robustness against noise, missing data, and complex patterns by restoring attacked data. RobustLight integrates two algorithms to recover original data states without altering existing TSC platforms. Using a dynamic state infilling algorithm, it trains the diffusion model online. Experiments on real-world datasets show RobustLight improves recovery performance by up to 50.43% compared to baseline scenarios. It effectively counters diverse adversarial attacks and missing data. The relevant datasets and code are available at Github.
APA
Li, M., Wang, J., Yu, G., Wang, X., Chen, Q., Ni, W., Li, L. & Peng, H.. (2025). RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:36192-36214 Available from https://proceedings.mlr.press/v267/li25cs.html.

Related Material