CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control

TL;DR

CoSLight introduces a dual-policy approach for traffic signal control, dynamically selecting collaborators beyond neighboring intersections to improve congestion management, validated on synthetic and real datasets.

Contribution

It proposes a novel real-time collaborator selection policy integrated with traffic signal control, addressing limitations of existing neighbor-based methods.

Findings

Significant congestion reduction compared to state-of-the-art methods

Effective real-time collaborator selection based on intersection features

Robust performance on both synthetic and real-world datasets

Abstract

Effective multi-intersection collaboration is pivotal for reinforcement-learning-based traffic signal control to alleviate congestion. Existing work mainly chooses neighboring intersections as collaborators. However, quite an amount of congestion, even some wide-range congestion, is caused by non-neighbors failing to collaborate. To address these issues, we propose to separate the collaborator selection as a second policy to be learned, concurrently being updated with the original signal-controlling policy. Specifically, the selection policy in real-time adaptively selects the best teammates according to phase- and intersection-level features. Empirical results on both synthetic and real-world datasets provide robust validation for the superiority of our approach, offering significant improvements over existing state-of-the-art methods. The code is available at https://github.com/bonaldli/CoSLight.