DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets

Abstract

We propose DefogGAN, a generative approach to the problem of inferring state information hidden in the fog of war for real-time strategy (RTS) games. Given a partially observed state, DefogGAN generates defogged images of a game as predictive information. Such information can lead to create a strategic agent for the game. DefogGAN is a conditional GAN variant featuring pyramidal reconstruction loss to optimize on multiple feature resolution scales. We have validated DefogGAN empirically using a large dataset of professional StarCraft replays. Our results indicate that DefogGAN can predict the enemy buildings and combat units as accurately as professional players do and achieves a superior performance among state-of-the-art defoggers.

Cite

Text

Jeong et al. "DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I04.5853

Markdown

[Jeong et al. "DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/jeong2020aaai-defoggan/) doi:10.1609/AAAI.V34I04.5853

BibTeX

@inproceedings{jeong2020aaai-defoggan,
  title     = {{DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets}},
  author    = {Jeong, Yonghyun and Choi, Hyunjin and Kim, Byoungjip and Gwon, Youngjune},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {4296-4303},
  doi       = {10.1609/AAAI.V34I04.5853},
  url       = {https://mlanthology.org/aaai/2020/jeong2020aaai-defoggan/}
}