Skip to main navigation Skip to search Skip to main content

Simulation-optimization using a reinforcement learning approach

  • Universidad del Norte
  • Universidad de la Sabana
  • University of South Florida

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

15 Citations (Scopus)

Abstract

The global optimization of complex systems such as industrial systems often necessitates the use of computer simulation. In this paper, we suggest the use of reinforcement learning (RL) algorithms and artificial neural networks for the optimization of simulation models. Several types of variables are taken into account in order to find global optimum values. After a first evaluation through mathematical functions with known optima, the benefits of our approach are illustrated through the example of an inventory control problem frequently found in manufacturing systems. Single-item and multi-item inventory cases are considered. The efficiency of the proposed procedure is compared against a commercial tool.

Original languageEnglish
Title of host publicationProceedings of the 2008 Winter Simulation Conference, WSC 2008
Pages1376-1383
Number of pages8
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 Winter Simulation Conference, WSC 2008 - Miami, FL, United States
Duration: 7 Dec 2008 → 10 Dec 2008

Publication series

NameProceedings - Winter Simulation Conference
ISSN (Print)0891-7736

Conference

Conference2008 Winter Simulation Conference, WSC 2008
Country/TerritoryUnited States
CityMiami, FL
Period7/12/08 → 10/12/08

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 9 - Industry, Innovation, and Infrastructure
    SDG 9 Industry, Innovation, and Infrastructure

ASJC Scopus subject areas

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Simulation-optimization using a reinforcement learning approach'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this