DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets
This addresses the challenge of strategic decision-making for AI agents in real-time strategy games, representing an incremental improvement in a domain-specific application.
The paper tackles the problem of inferring hidden state information in the fog of war for real-time strategy games like StarCraft, using DefogGAN to generate defogged images from partial observations, achieving accuracy comparable to professional players and superior performance over state-of-the-art defoggers.
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.