Can Deep Reinforcement Learning Improve Inventory Management? Performance and Implementation of Dual Sourcing-Mode Problems

17 Pages Posted: 3 Jan 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: December 17, 2018

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 to classic, yet intractable dual-sourcing or dual-mode 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, reinforcement learning, deep learning, dual sourcing inventory model

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 and Implementation of Dual Sourcing-Mode Problems (December 17, 2018). 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

Register to save articles to
your library

Register

Paper statistics

Downloads
204
rank
142,847
Abstract Views
696
PlumX Metrics