Scholarlink

Urban traffic congestion remains a critical challenge, largely due to static signal control systems that fail to adapt to real-time traffic dynamics. We propose a multi-agent traffic signal control framework that integrates Graph Neural Networks (GNNs) with the Soft Actor-Critic (SAC) algorithm under a Centralized Training with Decentralized Execution (CTDE) paradigm. Each intersection is modeled as an agent that learns to optimize signal phases based on local observations enriched with neighborhood context through a graph attention encoder. The reward function balances local intersection efficiency with global throughput and prioritizes public transport. We evaluate our approach in the Bologna-Pasubio scenario using the SUMO simulator. Our method shows its potential for adaptive and coordinated traffic control since it reduces average travel time by 87.3%, waiting time by 98.2%, and the number of halting vehicles by 84.3% compared to a fixed-time baseline.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Intelligent Multi-agent System for Urban Traffic Signal Control Leveraging Reinforcement Learning and Graph Neural Networks

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Hien Hieu Le,
  • Van Hieu Bui,
  • Duc Anh Vu,
  • Minh Quang Ha,
  • Minh Hoang Nguyen,
  • Duc Le

摘要

Urban traffic congestion remains a critical challenge, largely due to static signal control systems that fail to adapt to real-time traffic dynamics. We propose a multi-agent traffic signal control framework that integrates Graph Neural Networks (GNNs) with the Soft Actor-Critic (SAC) algorithm under a Centralized Training with Decentralized Execution (CTDE) paradigm. Each intersection is modeled as an agent that learns to optimize signal phases based on local observations enriched with neighborhood context through a graph attention encoder. The reward function balances local intersection efficiency with global throughput and prioritizes public transport. We evaluate our approach in the Bologna-Pasubio scenario using the SUMO simulator. Our method shows its potential for adaptive and coordinated traffic control since it reduces average travel time by 87.3%, waiting time by 98.2%, and the number of halting vehicles by 84.3% compared to a fixed-time baseline.