Entity Embedding as Game Representation
This addresses a key bottleneck for generating dynamic content in video games, though it is incremental as it builds on existing PCGML work.
The authors tackled the problem of representing dynamic game content like mechanics in PCGML by introducing 'entity embeddings' derived from an autoencoder, providing a consistent representation across multiple games.
Procedural content generation via machine learning (PCGML) has shown success at producing new video game content with machine learning. However, the majority of the work has focused on the production of static game content, including game levels and visual elements. There has been much less work on dynamic game content, such as game mechanics. One reason for this is the lack of a consistent representation for dynamic game content, which is key for a number of statistical machine learning approaches. We present an autoencoder for deriving what we call "entity embeddings", a consistent way to represent different dynamic entities across multiple games in the same representation. In this paper we introduce the learned representation, along with some evidence towards its quality and future utility.