Artificial intelligence driven supply chain network optimization: An empirical analysis based on reinforcement learning

In the context of globalization, complex supply chain networks have put forward higher requirements for the logistics and inventory management of enterprises. This paper proposes a supply chain optimization algorithm based on reinforcement learning, combining dynamic programming and deep neural networks to achieve real-time optimization of supply chain links. Based on the data of a multinational manufacturing company, mathematical modeling and simulation experiments are used to verify the advantages of the algorithm in reducing transportation costs and improving inventory turnover. This study demonstrates the potential of artificial intelligence technology in optimizing international supply chain networks and provides theoretical support and technical tools for enterprises to achieve efficient management.