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

Manufacturing & Service Operations Management

35 Pages Posted: 3 Jan 2019 Last revised: 16 Nov 2021

See all articles by Joren Gijsbrechts

Joren Gijsbrechts

Catholic University of Portugal (UCP) - Catolica Lisbon School of Business and Economics

Robert N. Boute

KU Leuven - Faculty of Business and Economics (FEB); Vlerick Business School - Operations & Technology Management Center

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 2, 2021

Abstract

(Forthcoming in Manufacturing & Service Operations Management)

Problem definition: Is Deep Reinforcement Learning (DRL) effective at solving inventory problems?

Academic/practical relevance: Given that DRL has successfully been applied in computer games and robotics, supply chain researchers and companies are interested in its potential in inventory management. We provide a rigorous performance evaluation of DRL in three classic and intractable inventory problems: lost sales, dual-sourcing and multi-echelon inventory management.

Methodology: We model each inventory problem as a Markov Decision Process and apply and tune the Asynchronous Advantage Actor Critic (A3C) DRL algorithm for a variety of parameter settings.

Results: We demonstrate that the A3C algorithm can match performance of state-of-the-art heuristics and other approximate dynamic programming methods. While the initial tuning was computationally- and time-demanding, only small changes to the tuning parameters were needed for the other studied problems.

Managerial implications: Our study provides evidence that DRL can effectively solve inventory problems. This is especially promising when problem-dependent heuristics are lacking. Yet generating structural policy insight or designing specialized policies that are (ideally provably) near optimal remains desirable.

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 2, 2021). Manufacturing & Service Operations Management, Available at SSRN: https://ssrn.com/abstract=3302881 or http://dx.doi.org/10.2139/ssrn.3302881

Joren Gijsbrechts

Catholic University of Portugal (UCP) - Catolica Lisbon School of Business and Economics ( email )

Palma de Cima
Lisbon, 1649-023
Portugal

Robert N. Boute

KU Leuven - Faculty of Business and Economics (FEB) ( email )

Naamsestraat 69
Leuven, B-3000
Belgium

Vlerick Business School - Operations & Technology Management Center ( email )

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

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,931
Abstract Views
7,690
rank
10,655
PlumX Metrics