Real-Time Matching and Dispatching for Urban Freight Transportation: A Hierarchical Reinforcement Learning Through Actor-Critic and H3 Spatial Partitioning

Real-time freight matching and dispatching present complex challenges due to the dynamic nature of supply and demand, high-dimensional decision spaces, and the need for rapid response under operational constraints. In this paper, we propose a novel Hierarchical Reinforcement Learning (HRL) framework that jointly optimizes matching and dispatching processes in freight transportation, offering enhanced responsiveness, modularity, and coordination under real-time constraints. To mitigate computational demands without sacrificing matching accuracy, we present two efficient pre-filtering algorithms, PAMA (Pre-filtering Algorithm for Matching Agent) and PADA (Pre-filtering Algorithm for Dispatching Agent), which enhance the H3 hexagonal geospatial partitioning system. A GIS-based simulation of freight flow in Montreal provides realistic validation. Experimental results show that our framework improves successful match rates by 1.73%, reduces vehicle idle time by 5.7%, and maintains low empty mileage. Compared to state-of-the-art baselines including Deep Q-Network and clustering-based methods, our HRL model achieves superior reward efficiency, scalability, and adaptability in dynamic freight environments. These findings underscore the potential of HRL to enhance the operational efficiency of smart freight platforms.