Mario Level Generation From Mechanics Using Scene Stitching
This addresses level design automation for game developers, but it is incremental as it builds on existing scene-based and algorithmic approaches.
The paper tackles the problem of generating Super Mario levels by stitching pre-generated scenes based on mechanic sequences from agent playthroughs, resulting in levels that match target mechanics while reducing emergent mechanics compared to a greedy method.
This paper presents a level generation method for Super Mario by stitching together pre-generated "scenes" that contain specific mechanics, using mechanic-sequences from agent playthroughs as input specifications. Given a sequence of mechanics, our system uses an FI-2Pop algorithm and a corpus of scenes to perform automated level authoring. The system outputs levels that have a similar mechanical sequence to the target mechanic sequence but with a different playthrough experience. We compare our system to a greedy method that selects scenes that maximize the target mechanics. Our system is able to maximize the number of matched mechanics while reducing emergent mechanics using the stitching process compared to the greedy approach.