EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

4147. Optimizing a Multi-echelon, Multi-Product, Lost-Sales Inventory Management System through Deep Reinforcement Learning

Invited abstract in session TA-3: (Deep) Reinforcement Learning for Combinatorial Optimization 3, stream Data Science Meets Optimization.

Tuesday, 8:30-10:00
Room: 1005 (building: 202)

Authors (first author is the speaker)

1. Fatemeh Fakhredin
Kühne Logistics University
2. Joern Meissner
Kuehne Logistics University

Abstract

Our study is going to address a lost-sales inventory management problem spanning multiple echelons and products, aiming to maximize network profit while determining optimal quantities from upstream suppliers. We utilize deep reinforcement learning (DRL) to optimize inventory management in these complex supply networks.

We begin by constructing a complex inventory management model accommodating lost sales and intricate cost structures. Employing DRL, we develop a framework to tackle this problem and evaluate its efficacy.

Our investigation extends to various scenarios, encompassing changes in lead time, fixed and sourcing costs, holding expenses, lost sales penalties, and demand variations. Therefore, the overarching research question we will attempt to address is: Does deep reinforcement learning produce superior policies for the multi-echelon, multi-product, lost-sales inventory management problem, in comparison with standard reinforcement learning?

Keywords

Status: accepted

Back to the list of papers