Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
Abstract
We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games. We propose to employ encoder-decoder neural networks for this task, and introduce proxy tasks and baselines for evaluation to assess their ability of capturing basic game rules and high-level dynamics. By combining convolutional neural networks and recurrent networks, we exploit spatial and sequential correlations and train well-performing models on a large dataset of human games of StarCraft: Brood War. Finally, we demonstrate the relevance of our models to downstream tasks by applying them for enemy unit prediction in a state-of-the-art, rule-based StarCraft bot. We observe improvements in win rates against several strong community bots.
Cite
Text
Synnaeve et al. "Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger." Neural Information Processing Systems, 2018.Markdown
[Synnaeve et al. "Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/synnaeve2018neurips-forward/)BibTeX
@inproceedings{synnaeve2018neurips-forward,
title = {{Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger}},
author = {Synnaeve, Gabriel and Lin, Zeming and Gehring, Jonas and Gant, Dan and Mella, Vegard and Khalidov, Vasil and Carion, Nicolas and Usunier, Nicolas},
booktitle = {Neural Information Processing Systems},
year = {2018},
pages = {10738-10748},
url = {https://mlanthology.org/neurips/2018/synnaeve2018neurips-forward/}
}