Procedural Content Generation via Knowledge Transformation (PCG-KT)

We introduce the concept of Procedural Content Generation via Knowledge Transformation (PCG-KT), a new lens and framework for characterizing PCG methods approaches in which content generation is enabled by process knowledge transformation -- transforming derived from one domain order to apply it another. Our work motivated substantial number recent works that focus on generating novel repurposing knowledge. Such have involved, example, performing transfer learning models trained game's adapt another content, as well recombining different generative distributions blend two or more games. arose part due limitations Machine Learning (PCGML) such producing games lacking training data entirely In this paper, we categorize under PCG-KT offering definition describing surveying existing using framework. Finally, conclude highlighting open problems directions future research area.