Case-based myopic reinforcement learning for satisfying target service level in supply chain

Ick Hyun Kwon, Chang Ouk Kim, Jin Jun, Jung Hoon Lee

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In the last decade, driven by global competition in the marketplace, many companies have taken initiatives to revamp their supply chains in order to increase responsiveness to changes in the marketplace. The renovation of inventory control system is central to such an effort. However, experiences in industry have shown that the control of inventory in supply chain is not an easy task because of uncertainties inherent in customer demand. In this paper, we propose a reinforcement learning algorithm appropriate for the nonstationary inventory control problem of supply chain that has a large state space. Traditional reinforcement learning algorithms such as learning automata and Q-learning have the difficulty of slow convergence when applied to the situations with large state spaces. To resolve the problems of nonstationary customer demand and large state space, we develop a case-based myopic reinforcement learning (CMRL) algorithm. A simulation-based experiment was performed to show good performance of CMRL.

Original languageEnglish
Pages (from-to)389-397
Number of pages9
JournalExpert Systems with Applications
Volume35
Issue number1-2
DOIs
Publication statusPublished - 2008 Jul 1

Fingerprint

Reinforcement learning
Supply chains
Learning algorithms
Inventory control
Industry
Control systems
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications

Cite this

@article{e7e40b951d424fe0a9b1af9f98d14a5f,
title = "Case-based myopic reinforcement learning for satisfying target service level in supply chain",
abstract = "In the last decade, driven by global competition in the marketplace, many companies have taken initiatives to revamp their supply chains in order to increase responsiveness to changes in the marketplace. The renovation of inventory control system is central to such an effort. However, experiences in industry have shown that the control of inventory in supply chain is not an easy task because of uncertainties inherent in customer demand. In this paper, we propose a reinforcement learning algorithm appropriate for the nonstationary inventory control problem of supply chain that has a large state space. Traditional reinforcement learning algorithms such as learning automata and Q-learning have the difficulty of slow convergence when applied to the situations with large state spaces. To resolve the problems of nonstationary customer demand and large state space, we develop a case-based myopic reinforcement learning (CMRL) algorithm. A simulation-based experiment was performed to show good performance of CMRL.",
author = "Kwon, {Ick Hyun} and Kim, {Chang Ouk} and Jin Jun and Lee, {Jung Hoon}",
year = "2008",
month = "7",
day = "1",
doi = "10.1016/j.eswa.2007.07.002",
language = "English",
volume = "35",
pages = "389--397",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "1-2",

}

Case-based myopic reinforcement learning for satisfying target service level in supply chain. / Kwon, Ick Hyun; Kim, Chang Ouk; Jun, Jin; Lee, Jung Hoon.

In: Expert Systems with Applications, Vol. 35, No. 1-2, 01.07.2008, p. 389-397.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Case-based myopic reinforcement learning for satisfying target service level in supply chain

AU - Kwon, Ick Hyun

AU - Kim, Chang Ouk

AU - Jun, Jin

AU - Lee, Jung Hoon

PY - 2008/7/1

Y1 - 2008/7/1

N2 - In the last decade, driven by global competition in the marketplace, many companies have taken initiatives to revamp their supply chains in order to increase responsiveness to changes in the marketplace. The renovation of inventory control system is central to such an effort. However, experiences in industry have shown that the control of inventory in supply chain is not an easy task because of uncertainties inherent in customer demand. In this paper, we propose a reinforcement learning algorithm appropriate for the nonstationary inventory control problem of supply chain that has a large state space. Traditional reinforcement learning algorithms such as learning automata and Q-learning have the difficulty of slow convergence when applied to the situations with large state spaces. To resolve the problems of nonstationary customer demand and large state space, we develop a case-based myopic reinforcement learning (CMRL) algorithm. A simulation-based experiment was performed to show good performance of CMRL.

AB - In the last decade, driven by global competition in the marketplace, many companies have taken initiatives to revamp their supply chains in order to increase responsiveness to changes in the marketplace. The renovation of inventory control system is central to such an effort. However, experiences in industry have shown that the control of inventory in supply chain is not an easy task because of uncertainties inherent in customer demand. In this paper, we propose a reinforcement learning algorithm appropriate for the nonstationary inventory control problem of supply chain that has a large state space. Traditional reinforcement learning algorithms such as learning automata and Q-learning have the difficulty of slow convergence when applied to the situations with large state spaces. To resolve the problems of nonstationary customer demand and large state space, we develop a case-based myopic reinforcement learning (CMRL) algorithm. A simulation-based experiment was performed to show good performance of CMRL.

UR - http://www.scopus.com/inward/record.url?scp=44949146357&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44949146357&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2007.07.002

DO - 10.1016/j.eswa.2007.07.002

M3 - Article

VL - 35

SP - 389

EP - 397

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 1-2

ER -