AAAI Publications, Workshops at the Thirty-Second AAAI Conference on Artificial Intelligence

Font Size: 
Combinatorial Creativity for Procedural Content Generation via Machine Learning
Matthew J. Guzdial, Mark O. Riedl

Last modified: 2018-06-20


In this paper we propose the application of techniques from the field of creativity research to machine learned models within the domain of games. This application allows for the creation of new, distinct models without additional training data. The techniques in question are combinatorial creativity techniques, defined as techniques that combine two sets of input to create novel output sets. We present a survey of prior work in this area and a case study applying some of these techniques to pre-trained machine learned models of game level design.


machine learning; computational creativity

Full Text: PDF