Deep reinforcement learning approach for solving joint pricing and inventory problem with reference price effects

作者：

Highlights：

• A joint pricing and inventory problem with reference price effects.

• A double deep Q-network algorithm characterized by a target network.

• Two ground truth algorithms and two common reinforcement learning algorithms are compared with.

• Behavior-based experiments and managerial insights are provided.

摘要

•A joint pricing and inventory problem with reference price effects.•A double deep Q-network algorithm characterized by a target network.•Two ground truth algorithms and two common reinforcement learning algorithms are compared with.•Behavior-based experiments and managerial insights are provided.

论文关键词：Dynamic pricing,Inventory control,Reference price effects,Machine learning,Deep reinforcement learning

论文评审过程：Received 20 July 2021, Revised 28 December 2021, Accepted 17 January 2022, Available online 20 January 2022, Version of Record 15 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116564