Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management

Bram J. De Moor, Joren Gijsbrechts, Robert N. Boute

Producció científica: Article en revista indexadaArticleAvaluat per experts

31 Cites (Scopus)

Resum

Deep reinforcement learning (DRL) has proven to be an effective, general-purpose technology to develop 'good' replenishment policies in inventory management. We show how transfer learning from existing, well-performing heuristics may stabilize the training process and improve the performance of DRL in inventory control. While the idea is general, we specifically implement potential-based reward shaping to a deep Q-network algorithm to manage inventory of perishable goods that, cursed by dimensionality, has proven to be notoriously complex. The application of our approach may not only improve inventory cost performance and reduce computational effort, the increased training stability may also help to gain trust in the policies obtained by black box DRL algorithms. (c) 2021 Elsevier B.V. All rights reserved.
Idioma originalAnglès
Pàgines (de-a)535-545
Nombre de pàgines11
RevistaEuropean Journal of Operational Research
Volum301
Número2
Data online anticipadad’abr. 2022
DOIs
Estat de la publicacióPublicada - 1 de set. 2022
Publicat externament

Fingerprint

Navegar pels temes de recerca de 'Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management'. Junts formen un fingerprint únic.

Com citar-ho