.png){kind=icon}
返回
Learning Multi-Intersection Traffic Signal Control via Coevolutionary Multi-Agent Reinforcement Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TITS.2024.3410023.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Effective management of multi-intersection traffic signal control (MTSC) is vital for intelligent transportation systems. Multi-agent reinforcement learning (MARL) has shown promise in achieving MTSC. However, existing MARL-based MTSC algorithms have primarily focused on capturing the spatial relationship between multi-intersection traffic signals but have overlooking the importance of the temporally stable traffic pattern. This pattern refers to the fixed positions and relatively stable traffic flow between intersections over short periods in real-world MTSC scenarios, which indicates that the learned spatial relationships between traffic signals should co-evolve over time. To this end, we propose a novel algorithm called Coevolutionary Multi-Agent Reinforcement Learning (CoevoMARL). CoevoMARL employs a graph neural network to capture the complex spatial interaction network among traffic signals. Furthermore, we propose a relationship-driven progressive LSTM (RDP-LSTM) that dynamically evolves the learned spatial interaction network over time by leveraging insights from the temporally stable traffic pattern. To accelerate convergence, we also propose the mutual information reward optimization (MIRO) technique, which strengthens the correlation between policy learning and high-performance samples by using a mutual information-based intrinsic reward. Experimental results on both synthetic and realistic datasets demonstrate the superiority of CoevoMARL over existing MTSC algorithms, providing valuable insights into incorporating the temporally stable traffic pattern.
Keyword:
Traffic light control
multi-agent reinforcement learning
graph neural network
期刊
IF:
8.4
论文数:
9.7K
被引数:
6.3W
机构
引用论文
Defect-related photoluminescence properties of as-synthesized and annealed NiO nanostructures via hydrothermal method通过水热法合成和退火的NiO纳米结构的缺陷相关的光致发光特性
.png){kind=icon}
PREAI
分享收藏STMARL: A Spatio-Temporal Multi-Agent Reinforcement Learning Approach for Cooperative Traffic Light ControlSTMARL: 一种用于交通信号灯协同控制的时空多智能体强化学习方法
OAAI
OAAI分享收藏Sustainability at stake during COVID-19: Exploring the role of accounting in addressing environmental crises新型冠状病毒肺炎期间的可持续性: 探索会计在应对环境危机中的作用
PREAI
分享收藏Feudal Latent Space Exploration for Coordinated Multi-Agent Reinforcement Learning协同多智能体强化学习的封建潜在空间探索
PREAI
分享收藏
查看更多内容