Research Post
Human designers may find it difficult to anticipate the impact of small changes to some games, particularly in puzzle games. However, it is not difficult for computers to simulate all mechanical impacts of such small changes. This suggests that computers might be able to aid humans designers as they build and analyze game levels.
This paper takes one step towards this larger goal by studying how Exhaustive Procedural Content Generation (EPCG) can be used for analysis of incremental changes of existing game levels. Using an incremental EPCG approach, we analyze all of the levels in the popular puzzle game Snakebird, showing that incremental variations in the level designs can significantly increase the length of the shortest possible solution.
A user study on a subset of these modified levels shows that the modified levels are both interesting and challenging for humans to play. Thus, through the analysis of Snakebird, we demonstrate the broader potential for incremental applications of EPCG.
Jan 11th 2021
Research Post
Dec 10th 2020
Research Post
Oct 1st 2020
Research Post
This paper proposes the use of images as the input for a PCGML process to generate game levels. Intuitively, a user can submit an image, with the system returning the closest valid Super Mario Bros. game level.
Looking to build AI capacity? Need a speaker at your event?