Deep reinforcement learning for inventory control: A roadmap

Robert N. Boute, Joren Gijsbrechts, Willem van Jaarsveld, Nathalie Vanvuchelen

Research output: Indexed journal article Reviewpeer-review

59 Citations (Scopus)

Abstract

Deep reinforcement learning (DRL) has shown great potential for sequential decision-making, including early developments in inventory control. Yet, the abundance of choices that come with designing a DRL algorithm, combined with the intense computational effort to tune and evaluate each choice, may hamper their application in practice. This paper describes the key design choices of DRL algorithms to facilitate their implementation in inventory control. We also shed light on possible future research avenues that may elevate the current state-of-the-art of DRL applications for inventory control and broaden their scope by leveraging and improving on the structural policy insights within inventory research. Our discussion and roadmap may also spur future research in other domains within operations management. (c) 2021 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )
Original languageEnglish
Pages (from-to)401-412
Number of pages12
JournalEuropean Journal of Operational Research
Volume298
Issue number2
Early online dateJan 2022
DOIs
Publication statusPublished - 16 Apr 2022
Externally publishedYes

Keywords

  • Inventory management
  • Machine learning
  • Neural networks
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Deep reinforcement learning for inventory control: A roadmap'. Together they form a unique fingerprint.

Cite this