Computational Creativity for Game Development (Dagstuhl Seminar 24261)

Abstract

Developments in artificial intelligence are currently dominated by deep neural networks, trained on large data sets, which excel at pattern recognition. Variants of the "classic" deep neural networks have the ability to generate new data with statistical properties similar to the training set. Despite the impressive products of such creative artificial intelligence, the results are usually lacking in meaning. They contain mistakes that humans would avoid, and often produce content which is not functional. While the product of creative artificial intelligence can be used as a strong basis for humans to build upon, human intelligence and human creativity are almost always a necessary ingredient of the creative process. Moreover, the more relevant the meaning, purpose, and functionality of the product are, the less the creative process benefits from the involvement of artificial intelligence.
Game design and implementation are tasks which require a high amount of creativity, and which must lead to products which require a high amount of fine-tuned functionality. For example, a game "level" should not only look appealing, it should also be playable and it should be interesting to play. These are not features which can be acquired simply by "training on big data," which is what most developments in modern artificial intelligence are based on.
This report on Dagstuhl Seminar 24261 discusses to what extent modern artificial intelligence techniques can produce meaningful and functional game content.