We are delighted to announce that our latest research paper, which focuses on the application of deep reinforcement learning (DRL) algorithms to supply chain inventory management (SCIM), has been accepted for publication in the prestigious International Journal of Production Research.

This groundbreaking study provides an in-depth analysis of how DRL can be used to optimise inventory levels across multiple local warehouses, taking into account stochastic and seasonal demand fluctuations. By framing the SCIM challenge as a Markov decision process, our research rigorously tested a range of state-of-the-art DRL algorithms to find the most effective solutions.

In addition, we are pleased to present an open source software library that tackles the SCIM problem, which is now publicly available on GitHub.

For those interested in exploring our findings further, the first 50 downloads of our paper are available for free.

Click here to read the paper

This initiative aims to facilitate access to our research and encourage further academic and practical advances in the field of supply chain management.

Stranieri, F., Stella, F., & Kouki, C. (2024). Performance of deep reinforcement learning algorithms in two-echelon inventory control systems. International Journal Of Production Research, 1‑16. https://doi.org/10.1080/00207543.2024.2311180

Share this post:
Share with FacebookShare with LinkedInShare with TwitterSend to a friendCopy to clipboard