Reinforcement Learning for Optimizing Can-Order Policy with the Rolling Horizon Method

被引:2
作者
Noh, Jiseong [1 ]
机构
[1] Hanyang Univ, Ctr Creat Convergence Educ, ERICA Campus, Ansan 15588, South Korea
关键词
can-order policy; mixed-integer linear programming; reinforcement learning; rolling horizon method; inventory management; INVENTORY MANAGEMENT; OPTIMIZATION;
D O I
10.3390/systems11070350
中图分类号
C [社会科学总论];
学科分类号
03 ; 0303 ;
摘要
This study presents a novel approach to a mixed-integer linear programming (MILP) model for periodic inventory management that combines reinforcement learning algorithms. The rolling horizon method (RHM) is a multi-period optimization approach that is applied to handle new information in updated markets. The RHM faces a limitation in easily determining a prediction horizon; to overcome this, a dynamic RHM is developed in which RL algorithms optimize the prediction horizon of the RHM. The state vector consisted of the order-up-to-level, real demand, total cost, holding cost, and backorder cost, whereas the action included the prediction horizon and forecasting demand for the next time step. The performance of the proposed model was validated through two experiments conducted in cases with stable and uncertain demand patterns. The results showed the effectiveness of the proposed approach in inventory management, particularly when the proximal policy optimization (PPO) algorithm was used for training compared with other reinforcement learning algorithms. This study signifies important advancements in both the theoretical and practical aspects of multi-item inventory management.
引用
收藏
页数:15
相关论文
共 17 条
[1]   Optimization of vendor-managed inventory systems in a rolling horizon framework [J].
Al-Ameri, Tareq A. ;
Shah, Nilay ;
Papageorgiou, Lazaros G. .
COMPUTERS & INDUSTRIAL ENGINEERING, 2008, 54 (04) :1019-1047
[2]  
AmazonWebServices, 2021, Predicting The Future of Demand: How Amazon Is Reinventing Forecasting with Machine Learning
[3]   Deep reinforcement learning for inventory control: A roadmap [J].
Boute, Robert N. ;
Gijsbrechts, Joren ;
van Jaarsveld, Willem ;
Vanvuchelen, Nathalie .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2022, 298 (02) :401-412
[4]   Effective Management for Blockchain-Based Agri-Food Supply Chains Using Deep Reinforcement Learning [J].
Chen, Huilin ;
Chen, Zheyi ;
Lin, Feiting ;
Zhuang, Peifen .
IEEE ACCESS, 2021, 9 :36008-36018
[5]   Optimization of Apparel Supply Chain Using Deep Reinforcement Learning [J].
Chong, Ji Won ;
Kim, Wooju ;
Hong, Jun Seok .
IEEE ACCESS, 2022, 10 :100367-100375
[6]   Reinforcement learning approaches for specifying ordering policies of perishable inventory systems [J].
Kara, Ahmet ;
Dogan, Ibrahim .
EXPERT SYSTEMS WITH APPLICATIONS, 2018, 91 :150-158
[7]   A note on the can-order policy for the two-item stochastic joint-replenishment problem [J].
Kayis, Enis ;
Bilgic, Taner ;
Karabulut, Deniz .
IIE TRANSACTIONS, 2008, 40 (01) :84-92
[8]  
Kempf KG, 2004, P AMER CONTR CONF, P4563
[9]  
Marilu Destino J.F., 2022, To Improve Your Supply Chain, Modernize Your Supply-Chain IT
[10]  
Mediavilla Mario Angos, 2022, Procedia CIRP, P1126, DOI 10.1016/j.procir.2022.05.119