Multi-agent Reinforcement Learning for Improving Supply Chain Visibility in Inventory Management

Multi-agent Reinforcement Learning for Improving Supply Chain Visibility in Inventory Management

2023 IEEE/ACM 27th International Symposium on Distributed Simulation and Real Time Applications (DS-RT)

10.1109/DS-RT58998.2023.00028

http://dx.doi.org/10.1109/ds-rt58998.2023.00028

Bo Zhang, Wen Jun Tan, Wentong Cai, Allan N Zhang

08 November 2023

Zhang, B., Tan, W. J., Cai, W., & Zhang, A. N. (2023, October 4). Multi-agent Reinforcement Learning for Improving Supply Chain Visibility in Inventory Management. 2023 IEEE/ACM 27th International Symposium on Distributed Simulation and Real Time Applications (DS-RT). https://doi.org/10.1109/ds-rt58998.2023.00028

This paper proposes a novel approach to enhance supply chain (SC) visibility, cooperation, and performance during inventory management while effectively mitigating the risk of information leakage by leveraging machine learning techniques. The SC inventory policies are optimized using multi-agent reinforcement learning (MaRL) and SC network topological information. Furthermore, we conduct a simulation-based evaluation that demonstrates the superior performance of our method compared to alternative optimization approaches. This research effectively addresses the dual objectives of ensuring information security and achieving cost reduction in SC inventory management.

Publisher Copyright

There was no specific funding for the research done

© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/20505

1550-652

Singapore Institute of Manufacturing Technology