Evolutionary Wave Function Collapse
For procedural content generation researchers, this work explores a hybrid method that leverages evolutionary search to guide WFC, but the improvements are limited to domains with local structure, making it an incremental contribution.
The paper combines Wave Function Collapse (WFC) with evolutionary search by evolving small input examples used by WFC, rather than directly evolving complete levels. Results show that this approach improves generation quality in domains where properties emerge from local relationships (e.g., maze connectivity), but remains challenging for domains requiring global constraints (e.g., Zelda-style dungeons).
Wave Function Collapse (WFC) is a widely used procedural content generation method that learns local adjacency constraints from example inputs to generate larger outputs. In this paper, we explore combining WFC with evolutionary search by evolving the small input examples used by WFC rather than directly evolving complete levels. In this approach, WFC acts as a genotype-to-phenotype mapping. The generated levels are then evaluated through domain-specific fitness functions. We evaluate the method in two domains with different relationships between local and global structure: Maze connectivity maps and Zelda-style dungeon layouts. Our results show that evolutionary optimization over WFC inputs improves generation quality in domains where properties emerge from local relationships, while domains requiring global constraints remain challenging. These findings suggest that evolutionary search can effectively guide WFC generation when target objectives align with local structure.