Loading...
Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management
De Moor, Bram J. Gijsbrechts, Joren Boute, Robert
De Moor, Bram J.
Gijsbrechts, Joren
Boute, Robert
Citations
Altmetric:
Publication Type
Journal article with impact factor
Editor
Supervisor
Publication Year
2022
Journal
European Journal of Operational Research
Book
Publication Volume
301
Publication Issue
2
Publication Begin page
535
Publication End page
545
Publication Number of pages
Collections
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.
Research Projects
Organizational Units
Journal Issue
Keywords
Inventory, Perishable Inventory Management, Deep Reinforcement Learning, Reward Shaping, Transfer Learning