The use of continuous action representations to scale deep reinforcement learning for inventory control
IMA Journal of Management Mathematics · 11.12.2023 · 36 (1) · 51-66
DOI: 10.1093/imaman/dpae031 ↗Kurz gefasst
Fachartikel in der Zeitschrift IMA Journal of Management Mathematics, online erschienen am 14.11.2024. Verfasst von Nathalie Vanvuchelen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 22 Literaturangaben. Gefördert von: Research Foundation – Flanders.
Abstract (Originalsprache)
Accepted by: M. Zied Babai Deep reinforcement learning (DRL) can solve complex inventory problems with a multi-dimensional state space. However, most approaches use a discrete action representation and do not scale well to problems with multi-dimensional action spaces. We use DRL with a continuous action representation for inventory problems with a large (multi-dimensional) discrete action space. To obtain feasible discrete actions from a continuous action representation, we add a tailored mapping function to the policy network that maps the continuous outputs of the policy network to a feasible integer solution. We demonstrate our approach to multi-product inventory control. We show how a continuous action representation solves larger problem instances and requires much less training time than a discrete action representation. Moreover, we show its performance matches state-of-the-art heuristic replenishment policies. This promising research avenue might pave the way for applying DRL in inventory control at scale and in practice.
Förderung
- Research Foundation – Flanders
Zitieren
APA
Vanvuchelen, N., Moor, B. J. D., & Boute, R. N. (2023). The use of continuous action representations to scale deep reinforcement learning for inventory control. IMA Journal of Management Mathematics, 36(1), 51-66. https://doi.org/10.1093/imaman/dpae031
Vancouver
Vanvuchelen N, Moor BJD, Boute RN. The use of continuous action representations to scale deep reinforcement learning for inventory control. IMA Journal of Management Mathematics. 2023;36(1):51-66. doi:10.1093/imaman/dpae031
BibTeX
@article{Vanvuchelen2023,
author = {Vanvuchelen, Nathalie and Moor, Bram J De and Boute, Robert N},
title = {The use of continuous action representations to scale deep reinforcement learning for inventory control},
journal = {IMA Journal of Management Mathematics},
year = {2023},
volume = {36},
number = {1},
pages = {51--66},
doi = {10.1093/imaman/dpae031}
}
EUVIMED