CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control

2026-03-25

AI Summary

This work addresses the challenges of partial observability and multi-agent coordination in decentralized traffic signal control by proposing CoordLight, a framework for network-wide traffic optimization. CoordLight enhances local perception at individual intersections through Queue Dynamics State Encoding (QDSE) and improves inter-agent coordination via a Neighborhood-Aware Policy Optimization (NAPO) algorithm. Integrating multi-agent reinforcement learning, attention mechanisms, and advantage function optimization, the framework demonstrates superior performance and adaptability over existing methods across three real-world large-scale road networks, with up to 196 intersections.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Adaptive traffic signal control (ATSC) is crucial in alleviating congestion, maximizing throughput and promoting sustainable mobility in ever-expanding cities. Multi-Agent Reinforcement Learning (MARL) has recently shown significant potential in addressing complex traffic dynamics, but the intricacies of partial observability and coordination in decentralized environments still remain key challenges in formulating scalable and efficient control strategies. To address these challenges, we present CoordLight, a MARL-based framework designed to improve intra-neighborhood traffic by enhancing decision-making at individual junctions (agents), as well as coordination with neighboring agents, thereby scaling up to network-level traffic optimization. Specifically, we introduce the Queue Dynamic State Encoding (QDSE), a novel state representation based on vehicle queuing models, which strengthens the agents' capability to analyze, predict, and respond to local traffic dynamics. We further propose an advanced MARL algorithm, named Neighbor-aware Policy Optimization (NAPO). It integrates an attention mechanism that discerns the state and action dependencies among adjacent agents, aiming to facilitate more coordinated decision-making, and to improve policy learning updates through robust advantage calculation. This enables agents to identify and prioritize crucial interactions with influential neighbors, thus enhancing the targeted coordination and collaboration among agents. Through comprehensive evaluations against state-of-the-art traffic signal control methods over three real-world traffic datasets composed of up to 196 intersections, we empirically show that CoordLight consistently exhibits superior performance across diverse traffic networks with varying traffic flows. The code is available at https://github.com/marmotlab/CoordLight

Problem

• decentralized coordination
• traffic signal control
• partial observability
• multi-agent reinforcement learning
• network-wide optimization

Innovation

• Queue Dynamic State Encoding
• Neighbor-aware Policy Optimization
• Multi-Agent Reinforcement Learning
• Decentralized Coordination
• Traffic Signal Control