Toward Co-creative Dungeon Generation via Transfer Learning

Co-creative Procedural Content Generation via Machine Learning However, running user subject studies for every game would be (PCGML) refers to systems where a PCGML agent and a human costly, and it would be difficult to find a user base with relevant work together to produce output content. One of the limitations of design experience for every game since most games do not have co-creative PCGML is that it requires co-creative training data for a their own Game Name Maker level design tool/game. Therefore, PCGML agent to learn to interact with humans. However, acquiring we need a way to develop high quality co-creative agents without this data is a difficult and time-consuming process.