BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract)

Donghyeon Lee, Man-Je Kim, Chang Wook Ahn

AAAI 2020 pp. 13849-13850

doi:10.1609/AAAI.V34I10.7197 /aaai/2020/lee2020aaai-battlenet/

Abstract

In a real-time strategy (RTS) game, StarCraft II, players need to know the consequences before making a decision in combat. We propose a combat outcome predictor which utilizes terrain information as well as squad information. For training the model, we generated a StarCraft II combat dataset by simulating diverse and large-scale combat situations. The overall accuracy of our model was 89.7%. Our predictor can be integrated into the artificial intelligence agent for RTS games as a short-term decision-making module.

PDF AAAI Semantic Scholar

Cite

Text

Lee et al. "BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7197

Markdown

[Lee et al. "BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/lee2020aaai-battlenet/) doi:10.1609/AAAI.V34I10.7197

BibTeX

@inproceedings{lee2020aaai-battlenet,
  title     = {{BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract)}},
  author    = {Lee, Donghyeon and Kim, Man-Je and Ahn, Chang Wook},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13849-13850},
  doi       = {10.1609/AAAI.V34I10.7197},
  url       = {https://mlanthology.org/aaai/2020/lee2020aaai-battlenet/}
}