DBScholar

Back to papers

FutureLight: An Efficient Future Traffic Data-Driven Reinforcement Learning Framework for Traffic Signal Controls

Summary: FutureLight is an RL framework for traffic-signal control that exploits future route data via a signal-aware, lane-level macroscopic simulator. Future-aware state/reward/value augmentation plus pruning improves control quality and accelerates training by over 30×. (summarized by gpt-5.6-luna on Aug 17 2026)

Paper ID
h16ccd8aec2a669e1
Venue
VLDB
Year
2026
Pagerank
4.9793485e-05
Overall Rank
10,790 | 27.46%
DOI
10.14778/3819518.3819555

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{xu_vldb26,
        title = {{FutureLight: An Efficient Future Traffic Data-Driven Reinforcement Learning Framework for Traffic Signal Controls}},
        author = {Xu, Zizhuo and Ma, Haolun and Li, Lei and Wang, Zhiyuan and Huang, Yunjie and Zhou, Xiaofang},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {9},
        pages = {2344--2357},
        doi = {10.14778/3819518.3819555},
        url = {https://doi.org/10.14778/3819518.3819555},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 2 of 2 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers