Procedural Generation of First Person Shooter Maps using Map-Elites

2026-05-28

AI Summary

This study addresses the challenge of balancing diversity and quality in first-person shooter (FPS) game map generation by proposing an evolutionary approach based on MAP-Elites with Sliding Boundaries (MESB). The work introduces two novel map representations—Point-Line and Spatial-Layout—and integrates topological structure with emergent gameplay properties as evaluation metrics to guide the evolutionary process. Experimental results demonstrate that the proposed method significantly outperforms existing representations, such as All-Black and Grid-Graph, in both the diversity and quality of generated maps, thereby validating the effectiveness and superiority of the new representations for automated FPS level generation.

Abstract

We investigate the application of MAP-Elites (a well-known quality diversity algorithm) to design levels for First-Person Shooter (FPS) games. We consider two well-known map representations (All-Black and Grid-Graph) and introduce two novel representations (Point-Line and Spatial-Layout) that improve the characterization of FPS maps. We define a series of metrics to describe maps' topological properties (which solely depend on maps' layout), and emergent properties (which must be evaluated through actual gameplay). We perform an in-depth analysis to identify the most suitable features to guide MAP-Elites illumination process. We apply MAP-Elites with Sliding Boundaries (MESB) to evolve populations of FPS maps. Our results show that the new representations can generate maps with higher diversity and quality than the representations previously used for evolving FPS maps.

Problem

• Procedural Generation
• First-Person Shooter
• MAP-Elites
• Level Design
• Map Representation

Innovation

• MAP-Elites
• procedural content generation
• FPS map representation
• quality diversity
• Sliding Boundaries