摘要
With advances in technologies, data science techniques, and computing equipment, there has been rapidly increasing interest in the applications of reinforcement learning (RL) to address the challenges resulting from the evolving business and organisational operations in logistics and supply chain management (SCM). This paper aims to provide a comprehensive review of the development and applications of RL techniques in the field of logistics and SCM. We first provide an introduction to RL methodologies, followed by a classification of previous research studies by application. The state-of-the-art research is reviewed and the current challenges are discussed. It is found that Q-learning (QL) is the most popular RL approach adopted by these studies and the research on RL for urban logistics is growing in recent years due to the prevalence of E-commerce and last mile delivery. Finally, some potential directions are presented for future research.
学科与关键词
- Reinforcement Learning for the Pickup and Delivery ProblemLiu, Fagui; Lai, Chengqi*; Wang, Lvshengbiao31st International Conference on Artificial Neural Networks (ICANN), Univ W England, Bristol, ENGLAND, 2022-09-06 To 2022-09-09.被引 1
- The third party logistics provider freight management problem: a framework and deep reinforcement learning approachAbbasi-Pooya, Amin; Lash, Michael T.*Annals of Operations Research, 2024, 339(1-2): 965-1024.
- A review on unsupervised learning algorithms and applications in supply chain managementRolf, Benjamin*; Beier, Alexander; Jackson, Ilya; Mueller, Marcel; Reggelin, Tobias; Stuckenschmidt, Heiner; Lang, SebastianInternational Journal of Production Research, 2024.被引 2
