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.
@article{arxiv.1812.00054,
title = {Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger},
author = {Gabriel Synnaeve and Zeming Lin and Jonas Gehring and Dan Gant and Vegard Mella and Vasil Khalidov and Nicolas Carion and Nicolas Usunier},
journal= {arXiv preprint arXiv:1812.00054},
year = {2018}
}