Explainable PCGML via Game Design Patterns
This addresses the challenge for game designers who need to manipulate PCGML models without expert knowledge, offering an incremental improvement in explainability.
The paper tackles the problem of making procedural content generation via machine learning (PCGML) more interpretable and tunable for game designers by introducing an explainable approach using game design patterns as a vocabulary for interaction. It demonstrates that this technique outperforms non-explainable versions in tests with expert designers, including those without machine learning expertise.
Procedural content generation via Machine Learning (PCGML) is the umbrella term for approaches that generate content for games via machine learning. One of the benefits of PCGML is that, unlike search or grammar-based PCG, it does not require hand authoring of initial content or rules. Instead, PCGML relies on existing content and black box models, which can be difficult to tune or tweak without expert knowledge. This is especially problematic when a human designer needs to understand how to manipulate their data or models to achieve desired results. We present an approach to Explainable PCGML via Design Patterns in which the design patterns act as a vocabulary and mode of interaction between user and model. We demonstrate that our technique outperforms non-explainable versions of our system in interactions with five expert designers, four of whom lack any machine learning expertise.