Deep reinforcement learning for inventory control: A roadmap

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

Producció científica: Article en revista indexadaArticle de revisió (sistemàtica)Avaluat per experts

62 Cites (Scopus)


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 ( )
Idioma originalAnglès
Pàgines (de-a)401-412
Nombre de pàgines12
RevistaEuropean Journal of Operational Research
Data online anticipadade gen. 2022
Estat de la publicacióPublicada - 16 d’abr. 2022
Publicat externament


Navegar pels temes de recerca de 'Deep reinforcement learning for inventory control: A roadmap'. Junts formen un fingerprint únic.

Com citar-ho