A Data-driven Approach to Solve a Production Constrained Build-order Optimization Problem

Pengpeng Wang, Yifeng Zeng, Bilian Chen, Langcai Cao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

105 Downloads (Pure)

Abstract

Production constrained build-order optimization problems challenge artificial intelligence research in computer game applications due to an uncertain set of constraints. Traditional approaches provide subjective values in the constraint formulation therefore resulting in unexpected performance of the optimal build-order in a game. In this article, we propose a data-driven approach to solve a build-order optimization problem in StarCraft. We formulate the constraint by learning the parameter values from game replay data, which complements more precise problem formulation. To solve the optimization, we use the improved genetic algorithm by learning initial solutions from the data. We show the performance of the data-driven methods in a StarCraft simulation platform.
Original languageEnglish
Title of host publicationProceedings of the 38th Chinese Control Conference
EditorsMinyue Fu, Jian Sun
PublisherIEEE
Pages2692-2697
ISBN (Electronic)9789881563972
ISBN (Print)9789881563972
DOIs
Publication statusPublished - 17 Oct 2019
Event2019 Chinese Control Conference - Guangzhou, China
Duration: 27 Jul 201930 Jul 2019

Publication series

NameChinese Control Conference (CCC)
PublisherIEEE
Volume2019
ISSN (Electronic)1934-1768

Conference

Conference2019 Chinese Control Conference
Abbreviated titleCCC
CountryChina
CityGuangzhou
Period27/07/1930/07/19

Fingerprint Dive into the research topics of 'A Data-driven Approach to Solve a Production Constrained Build-order Optimization Problem'. Together they form a unique fingerprint.

  • Cite this

    Wang, P., Zeng, Y., Chen, B., & Cao, L. (2019). A Data-driven Approach to Solve a Production Constrained Build-order Optimization Problem. In M. Fu, & J. Sun (Eds.), Proceedings of the 38th Chinese Control Conference (pp. 2692-2697). (Chinese Control Conference (CCC); Vol. 2019). IEEE. https://doi.org/10.23919/ChiCC.2019.8866045