Research map / Reinforcement learning / Visual and representation RL
Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 pressure-based reward/state (ablation) | FRAP · Manhattan | avg travel time (s): 512.70 -> 472.51 | Helped |
| add pressure-based reward/state (ablation) | GCN · Manhattan | avg travel time (s): 653.45 -> 646.47 | Helped |
| add pressure-based reward/state (ablation) | PressLight · Manhattan | avg travel time (s): 654.04 -> 600.42 | Helped |
| parameter sharing across intersections (ablation) | MPLight · synthetic traffic | episodes to converge | Helped |
| MPLight instead of best baseline | traffic signal control · Synthetic Config 3 | avg travel time (s): 19.20% | Helped |
Closest papers by meaning
- π-Light: Programmatic Interpretable Reinforcement Learning for Resource-Limited Traffic Signal Control (AAAI 2024 · similarity 0.91)
- CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control (ICLR 2026 · similarity 0.89)
- RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control (ICML 2025 · similarity 0.88)
- VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture (NeurIPS 2025 · similarity 0.87)
- DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data (NeurIPS 2024 · similarity 0.87)
- IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning (ICLR 2025 · similarity 0.86)
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.