Research map / Reinforcement learning / Visual and representation RL
Scalable Traffic Signal Control with Shared Policy Framework
Haolun MA, Yanchen ZHU, Zizhuo Xu, Weijie Shi, Jiajie Xu, Lei Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the policy-aware LSTM traffic pattern encoder (ablation) | SLight · NY1 | ATT and TP | Improved |
| add the CVAE shared control principle learning (ablation) | SLight · NY1 | ATT and TP | Improved |
| use both LSTM and CVAE rather than neither (ablation) | SLight · NY1 | ATT, AWT, TP | Improved |
| set number of principles K to 4 rather than smaller or larger (ablation) | SLight · NY1 | ATT, AWT, TP | Improved |
| set LSTM history window tau to 10 (ablation) | SLight · NY1 | ATT, TP | Improved |
| replace GPLight grouping with SLight policy-aware assignment | GPLight · NY1 | ATT: 929.43 -> 870.41 | Improved |
| replace GPLight grouping with SLight on the larger NY2 network versus CoSlight | CoSlight · NY2 (2,510 intersections) | ATT: 1053.90 -> 856.94 | Improved |
Closest papers by meaning
- π-Light: Programmatic Interpretable Reinforcement Learning for Resource-Limited Traffic Signal Control (AAAI 2024 · similarity 0.88)
- DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data (NeurIPS 2024 · similarity 0.86)
- CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control (ICLR 2026 · similarity 0.86)
- RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control (ICML 2025 · similarity 0.86)
- Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning (AAAI 2024 · similarity 0.85)
- VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
