Advertisement

Identifying Rush Strategies Employed in StarCraft II Using Support Vector Machines

  • Teguh Budianto
  • Hyunwoo Oh
  • Yi Ding
  • Zi Long
  • Takehito Utsuro
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10507)

Abstract

This paper studies the strategies used in StarCraft II, a real-time strategy game (RTS) wherein two sides fight against each other in a battlefield context. We propose an approach which automatically classifies StarCraft II game-log collections into rush and non-rush strategies using a support vector machine (SVM). To achieve this, three types of features are evaluated: (i) the upper bound of variance in time series for the numbers of workers, (ii) the upper bound of the numbers of workers at a specific time, and (iii) the lower bound of the start time for building the second base. Thus, by evaluating these features, we obtain the optimal parameters combinations.

Keywords

Real-time strategy game StarCraft II Rush strategy 

References

  1. 1.
    Park, H., et al.: Prediction of early stage opponents strategy for StarCraft AI using scouting and machine learning. In: Proceedings of the WASA, pp. 7–12 (2012)Google Scholar
  2. 2.
    Liu, S., et al.: Player identification from RTS game replays. In: Proceedings of the 28th CATA, pp. 313–317 (2013)Google Scholar
  3. 3.
    Weber, B.G., Mateas, M.: A data mining approach to strategy prediction. In: Proceedings of the 5th CIG, pp. 140–147 (2009)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2017

Authors and Affiliations

  • Teguh Budianto
    • 1
  • Hyunwoo Oh
    • 2
  • Yi Ding
    • 1
  • Zi Long
    • 1
  • Takehito Utsuro
    • 1
  1. 1.Graduate School of Systems and Information EngineeringUniversity of TsukubaTsukubaJapan
  2. 2.Graduate School of Interdisciplinary Information StudiesThe University of TokyoTokyoJapan

Personalised recommendations