Can Deep Reinforcement Learning Improve Inventory Management? Performance on Lost Sales, Dual-Sourcing, and Multi-Echelon Problems

• 成果类型: Article
• 署名作者: Gijsbrechts, Joren; Boute, Robert N.; Van Mieghem, Jan A.; Zhang, Dennis J.
• 署名单位: Universidade Catolica Portuguesa; Vlerick Business School; KU Leuven; Northwestern University; Washington University (WUSTL)
• 刊物名称: M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT
• ISSN/ISSBN: 1523-4614
• DOI: 10.1287/msom.2021.1064
• 发表日期: 2022
• 页码: 1349-1368
• 关键词: inventory theory and control; logistics and transportation; Supply chain management; OM-information technology interface

摘要

Problem definition: Is deep reinforcement learning (DRL) effective at solving inventory problems? Academic/practical relevance: Given that DRL has successfully been applied in computer games and robotics, supply chain researchers and companies are interested in its potential in inventory management. We provide a rigorous performance evaluation of DRL in three classic and intractable inventory problems: lost sales, dual sourcing, and multi-echelon inventory management. Methodology: We model each inventory problem as a Markov decision process and apply and tune the Asynchronous Advantage Actor-Critic (A3C) DRL algorithm for a variety of parameter settings. Results: We demonstrate that the A3C algorithm can match the performance of the state-of-the-art heuristics and other approximate dynamic programming methods. Although the initial tuning was computationally demanding and time demanding, only small changes to the tuning parameters were needed for the other studied problems. Managerial implications: Our study provides evidence that DRL can effectively solve stationary inventory problems. This is especially promising when problem-dependent heuristics are lacking. Yet, generating structural policy insight or designing specialized policies that are (ideally provably) near optimal remains desirable.