Towards general game representations : decomposing games pixels into content and style

Abstract

Learning pixel representations of games can benefit artificial intelligence across several downstream tasks including game-playing agents, procedural content generation, and player modeling. However, the generalizability of these methods remains a challenge, as learned representations should ideally be shared across games with similar game mechanics. This could allow, for instance, game-playing agents trained on one game to perform well in similar games with no re-training. This paper explores how generalizable pre-trained computer vision encoders can be used for such tasks by decomposing the latent space into content and style embeddings. The goal is to minimize the domain gap between games of the same genre when it comes to game content and ignore differences in graphical style. We employ a pre-trained Vision Transformer encoder and a decomposition technique based on game genres to obtain separate content and style embeddings. Our findings show that the decomposed embeddings achieve style invariance across multiple games while still maintaining strong content extraction capabilities. We argue that the proposed decomposition of content and style offers better generalization across game environments independently of the downstream task.