ML Anthology

Evolutionary Machine Learning for RTS Game StarCraft

Lianlong Wu, Andrew Markham
AAAI 2017 pp. 5007-5008
doi:10.1609/AAAI.V31I1.11109 /aaai/2017/wu2017aaai-evolutionary/

Abstract

Real-Time Strategy (RTS) games involve multiple agents acting simultaneously, and result in enormous state dimensionality. In this paper, we propose an abstracted and simplified model for the famous game StarCraft, and design a dynamic programming algorithm to solve the building order problem, which takes minimal time to achieve a specific target. In addition, Genetic Algorithms (GA) are used to find an optimal target for the opening stage.

AAAI Semantic Scholar

Cite

Text

Wu and Markham. "Evolutionary Machine Learning for RTS Game StarCraft." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.11109

Markdown

[Wu and Markham. "Evolutionary Machine Learning for RTS Game StarCraft." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/wu2017aaai-evolutionary/) doi:10.1609/AAAI.V31I1.11109

BibTeX

@inproceedings{wu2017aaai-evolutionary,
  title     = {{Evolutionary Machine Learning for RTS Game StarCraft}},
  author    = {Wu, Lianlong and Markham, Andrew},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {5007-5008},
  doi       = {10.1609/AAAI.V31I1.11109},
  url       = {https://mlanthology.org/aaai/2017/wu2017aaai-evolutionary/}
}