Procedural Maze Generation with Considering Difficulty from Human Players' Perspectives

In video game development, creating maps, enemies, and many other elements of game levels is one of the important process. In order to improve players' game experiences, game designers need to understand players' behavioral tendencies and create levels accordingly. Among various components of levels, this paper targets mazes and presents an automatic maze generation method with considering difficulty based on human players' tendencies. We first investigate the tendencies using supervised learning and create a test player considering human-likeness by using the tendencies. The test player simulates human players' behaviors when playing mazes and judges difficulty according to the simulation results. Maze evaluation results of subject experiments show that our method succeeds in generating mazes where the difficulty estimated by the test player matches human players'.Advances in Computer Games Conference (ACG 2021), November 202