Scholarlink

<p>As the logistics industry expands, the complexity of vehicle routing problems, particularly those with time window constraints, increases with the growing demand for services. The challenge of vehicle routing problems with time windows (VRPTW) lies in efficiently scheduling a fleet of vehicles to service a set of customers within specified time frames. This study introduces a deep reinforcement learning approach based on attention mechanisms to optimize vehicle routing and scheduling, aiming to meet specific time window requirements of customers while effectively reducing travel distances and costs, thereby enhancing the efficiency of logistics delivery. This method models the problem as a Markov decision process, defines actions, states, and rewards, and uses reinforcement learning for training to extract node information features and generate preliminary solutions. The model can focus on key information and optimize strategy selection by introducing an encoding-decoding structure and attention map neural network. Then, the large neighborhood search algorithm is used to iterative optimize the initial solution to obtain the optimal solution. The model is trained and tested on the Solomon data set. The experimental results show that the model is significantly better than other methods.</p>

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

Deep reinforcement learning with graph attention mechanism for vehicle routing problem with time windows

  • 期刊论文

  • 发表日期：

    2025年8月27日

查看全文
  • Fan Zhang,
  • Huiling Hu,
  • Yuqian Zhao

摘要

As the logistics industry expands, the complexity of vehicle routing problems, particularly those with time window constraints, increases with the growing demand for services. The challenge of vehicle routing problems with time windows (VRPTW) lies in efficiently scheduling a fleet of vehicles to service a set of customers within specified time frames. This study introduces a deep reinforcement learning approach based on attention mechanisms to optimize vehicle routing and scheduling, aiming to meet specific time window requirements of customers while effectively reducing travel distances and costs, thereby enhancing the efficiency of logistics delivery. This method models the problem as a Markov decision process, defines actions, states, and rewards, and uses reinforcement learning for training to extract node information features and generate preliminary solutions. The model can focus on key information and optimize strategy selection by introducing an encoding-decoding structure and attention map neural network. Then, the large neighborhood search algorithm is used to iterative optimize the initial solution to obtain the optimal solution. The model is trained and tested on the Solomon data set. The experimental results show that the model is significantly better than other methods.