Can Deep Reinforcement Learning Improve Inventory Management? Performance on Dual Sourcing, Lost Sales and Multi-Echelon Problems

26 Pages Posted: 3 Jan 2019 Last revised: 30 Jul 2019

See all articles by Joren Gijsbrechts

Joren Gijsbrechts

KU Leuven, Faculty of Business and Economics (FEB), Students

Robert N. Boute

Vlerick Leuven Gent Management School

Jan A. Van Mieghem

Northwestern University - Kellogg School of Management

Dennis Zhang

Washington University in St. Louis - John M. Olin Business School

Date Written: July 29, 2019

Abstract

The popularity of reinforcement learning is growing but is it effective in operations? We provide proof of concept that deep reinforcement learning (DRL) can be applied as a general-purpose technology to three classic, yet intractable inventory replenishment problems. Step-by-step guidance on how to apply DRL to a real data set is proffered together with the code and a careful discussion of its performance, strengths and weaknesses.

Keywords: artificial intelligence, deep reinforcement learning, inventory control, dual sourcing, lost sales, multi-echelon

JEL Classification: M11

Suggested Citation

Gijsbrechts, Joren and Boute, Robert N. and Van Mieghem, Jan Albert and Zhang, Dennis, Can Deep Reinforcement Learning Improve Inventory Management? Performance on Dual Sourcing, Lost Sales and Multi-Echelon Problems (July 29, 2019). Available at SSRN: https://ssrn.com/abstract=3302881 or http://dx.doi.org/10.2139/ssrn.3302881

Joren Gijsbrechts

KU Leuven, Faculty of Business and Economics (FEB), Students ( email )

Naamsestraat 69
Leuven, B-3000
Belgium

Robert N. Boute

Vlerick Leuven Gent Management School ( email )

Library
REEP 1
Gent, BE-9000
Belgium

Jan Albert Van Mieghem (Contact Author)

Northwestern University - Kellogg School of Management ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Dennis Zhang

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
907
Abstract Views
4,367
rank
27,065
PlumX Metrics