DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets
arXiv:2003.01927
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.
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Playing Atari with Deep Reinforcement Learning
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
- Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks
- Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
- Clear the Fog: Combat Value Assessment in Incomplete Information Games with Convolutional Encoder-Decoders