Prediction of early stage opponents strategy for StarCraft AI using scouting and machine learning

  title={Prediction of early stage opponents strategy for StarCraft AI using scouting and machine learning},
  author={H. Park and Hochul Cho and Kwangyeol Lee and Kyung-Joong Kim},
  booktitle={WASA '12},
  • H. Park, Hochul Cho, +1 author Kyung-Joong Kim
  • Published in WASA '12 2012
  • Computer Science
  • StarCraft is one of the most famous Real-Time Strategy Games and there have been several competitions on AI bots. [...] Key Method In this paper, we apply a scouting algorithm and various machine learning algorithms to predict an opponents attack timing (strategy). Training data are collected from the games between our Xelnaga bot with the scouting algorithm and various online human players. Experimental results show that the machine learning approach based on realistic scouting data can be beneficial in…Expand Abstract
    20 Citations

    Figures, Tables, and Topics from this paper

    Replay-based strategy prediction and build order adaptation for StarCraft AI bots
    • 28
    • PDF
    Use of Machine Learning Techniques in Real-Time Strategy Games
    • 1
    Potential flows for controlling scout units in StarCraft
    • 9
    • PDF
    A Scouting Strategy for Real-Time Strategy Games
    • 4
    • PDF
    Opponent modeling with incremental active learning: A case study of Iterative Prisoner's Dilemma
    • 4
    • PDF
    Comparison of human and AI bots in StarCraft with replay data mining
    • 2
    • PDF
    Learning to recommend game contents for real-time strategy gamers
    • 7
    • PDF


    A data mining approach to strategy prediction
    • B. Weber, M. Mateas
    • Computer Science
    • 2009 IEEE Symposium on Computational Intelligence and Games
    • 2009
    • 233
    • Highly Influential
    • PDF
    Data Mining: Practical Machine Learning Tools and Techniques, 3/E
    • 559
    • Highly Influential