Use of Proximal Policy Optimization for the Joint Replenishment Problem

被引：74

作者：

Vanvuchelen, Nathalie ^{[1
]}

Gijsbrechts, Joren ^{[1
]}

Boute, Robert ^{[1
,2
]}

机构：

[1] Katholieke Univ Leuven, Res Ctr Operat Management, Fac Business & Econ, Naamsestr 69,Box 3500, B-3000 Leuven, Belgium

[2] Vlerick Business Sch, Technol & Operat Management Area, Ghent, Belgium

来源：

COMPUTERS IN INDUSTRY | 2020年 / 119卷

关键词：

Collaborative Shipping; Physical Internet; Joint Replenishment Problem; Machine Learning; Deep Reinforcement Learning; Proximal Policy Optimization; INVENTORY CONTROL; ORDER; TRANSPORTATION;

D O I：

10.1016/j.compind.2020.103239

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Deep reinforcement learning has been coined as a promising research avenue to solve sequential decision-making problems, especially if few is known about the optimal policy structure. We apply the proximal policy optimization algorithm to the intractable joint replenishment problem. We demonstrate how the algorithm approaches the optimal policy structure and outperforms two other heuristics. Its deployment in supply chain control towers can orchestrate and facilitate collaborative shipping in the Physical Internet. (C) 2020 Elsevier B.V. All rights reserved.

引用

页数：10