The use of continuous action representations to scale deep reinforcement learning for inventory control
Vanvuchelen, Nathalie De Moor, Bram J Boute, Robert N
Vanvuchelen, Nathalie
De Moor, Bram J
Boute, Robert N
Publication Type
Journal article with impact factor
Editor
Supervisor
Publication Year
2023-12-11
Journal
IMA Journal of Management Mathematics
Book
Publication Volume
36
Publication Issue
1
Publication Begin page
51
Publication End page
66
Publication Number of pages
Collections
Abstract
Abstract 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.
Research Projects
Organizational Units
Journal Issue
Keywords
4901 Applied Mathematics, 49 Mathematical Sciences