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.

Cited by in corpus (4)

• Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
• High-Level Strategy Selection under Partial Observability in StarCraft: Brood War
• A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings
• DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets