Dual-Layer Optimization for Supply–Demand Balance in Urban Taxi Systems: Multi-Agent Reinforcement Learning with Dual-Attention Mechanisms

With the rapid growth of urban transportation demand, traditional taxi systems face challenges such as supply–demand imbalances and low dispatch efficiency. These methods, which rely on static data and predefined strategies, struggle to adapt to dynamic traffic environments. To address these issues, this paper proposes a dual-layer Taxi Dispatch and Empty-Vehicle Repositioning (TDEVR) optimization framework based on Multi-Agent Reinforcement Learning (MARL). The framework separates the tasks of taxi matching and repositioning, enabling efficient coordination between the decision-making and execution layers. This design allows for the real-time integration of both global and local supply–demand information, ensuring adaptability to complex urban traffic conditions. A Multi-Agent Dual-Attention Reinforcement Learning (MADARL) algorithm is proposed to enhance decision-making and coordination, combining local and global attention mechanisms to improve local agents’ decision-making while optimizing global resource allocation. Experiments using a real-world New York City taxi dataset show that the TDEVR framework with MADARL leads to an average improvement of 20.63% in the Order Response Rate (ORR), a 15.29 increase in Platform Cumulative Revenue (PCR), and a 22.07 improvement in the Composite Index (CI). These results highlight the significant performance improvements achieved by the proposed framework in dynamic scenarios, demonstrating its ability to efficiently adapt to real-time fluctuations in supply and demand within urban traffic environments.