Forward Modeling For Partial Observation Strategy Games - A StarCraft Defogger

Authors:
Gabriel Synnaeve Facebook
Zeming Lin Facebook AI Research
Jonas Gehring Facebook AI Research
Dan Gant Facebook AI Research
Vegard Mella Facebook AI Research
Vasil Khalidov Facebook AI Research
Nicolas Carion Facebook AI Research Paris
Nicolas Usunier Facebook AI Research

Introduction:

The authors formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games.The authors 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.

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.

You may want to know: