Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management
dc.contributor.author | De Moor, Bram J. | |
dc.contributor.author | Gijsbrechts, Joren | |
dc.contributor.author | Boute, Robert | |
dc.date.accessioned | 2021-11-03T09:31:55Z | |
dc.date.available | 2021-11-03T09:31:55Z | |
dc.date.issued | 2022 | en_US |
dc.identifier.issn | 0377-2217 | |
dc.identifier.doi | 10.1016/j.ejor.2021.10.045 | |
dc.identifier.uri | http://hdl.handle.net/20.500.12127/6986 | |
dc.description.abstract | 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. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Elsevier | en_US |
dc.subject | Inventory | en_US |
dc.subject | Perishable Inventory Management | en_US |
dc.subject | Deep Reinforcement Learning | en_US |
dc.subject | Reward Shaping | en_US |
dc.subject | Transfer Learning | en_US |
dc.title | Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management | en_US |
dc.identifier.journal | European Journal of Operational Research | en_US |
dc.source.volume | 301 | |
dc.source.issue | 2 | |
dc.source.beginpage | 535 | |
dc.source.endpage | 545 | |
dc.contributor.department | Research Center for Operations Management, KU Leuven, Naamsestraat 69, Box 3555, 3000 Leuven, Belgium | en_US |
dc.contributor.department | IESEG School of Management, Rue de la Digue 3, 59000 Lille, France | en_US |
dc.contributor.department | Católica Lisbon School of Business and Economics, Palma de Cima, 1649-023 Lisbon, Portugal | en_US |
vlerick.knowledgedomain | Operations & Supply Chain Management | en_US |
vlerick.typearticle | Vlerick strategic journal article | en_US |
vlerick.vlerickdepartment | TOM | en_US |
dc.identifier.vperid | 102358 | en_US |