TOAD-GAN: A Flexible Framework for Few-Shot Level Generation in Token-Based Games

This work presents
T
oken-based
O
ne-shot
A
rbitrary
D
imension
G
enerative
A
dversarial
N
etwork (
TOAD-GAN
), a novel procedural content generation algorithm that generates token-based video game levels from only one example. We show that the created levels can be of arbitrary size, and the patterns of the training levels are well captured. The method can be extended with user interaction during the generation process to achieve certain token layouts and interpretations of the same base level by different generators. Our method is further evaluated with an extensive ablation study and level similarity metrics on the
Super Mario Bros.
benchmark. Finally, we extend our method to mix the style of multiple input levels, turning it into a framework for few-shot level generation.