Enhanced multi-task deep reinforcement learning for the integrated inventory-routing problem under VMI mode

Effective inventory replenishment and routing are crucial for minimizing supply chain costs and enhancing operational efficiency. In this paper, we focus on the integrated optimization of inventory replenishment and routing problems in Vendor Managed Inventory (VMI) mode and further propose an enhanced Multi-Task Proximal Policy Optimization (MTPPO) with deep reinforcement learning. The proposed model refines inventory replenishment strategies by learning from inventory status and retailer location data. Routing strategies are optimized by utilizing a Graph Isomorphism Network (GIN) to analyze the network data of retailers and formulate routing strategies based on delivery requirements and retailer network information. By jointly optimizing inventory and routing problems, the total cost is reduced. Further, experimental results demonstrate that the MTPPO outperforms heuristic algorithms, reducing inventory costs by 8.58% and total costs by 6.18%.