Evolutionary Procedural 2D Map Generation using Novelty Search

Andreas Scheibenpflug, Johannes Karder, Susanne Schaller, Stefan Wagner, Michael Affenzeller

Abstract: This paper presents an evolutionary approach to procedural content generation of 2D maps for computer games. To provide better adaptability to the map designer's vision, user preference is incorporated to guide the algorithm. A cooperative method utilizes novelty search as a source of diverse solutions, which are then further optimized by multiple, subsequent genetic algorithms. We compare the results to a second approach based on multi-objective optimization, which takes the two conflicting goals of optimizing towards user preference and finding novel solutions as objective functions to build a Pareto front of maps.