Litcius/Paper detail

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

Frederik Schubert, Maren Awiszus, Bodo Rosenhahn

2021IEEE Transactions on Games17 citationsDOI

Abstract

This work presents <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</i> oken-based <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> ne-shot <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</i> rbitrary <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</i> imension <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</i> enerative <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</i> dversarial <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i> etwork ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TOAD-GAN</i> ), 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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Super Mario Bros.</i> benchmark. Finally, we extend our method to mix the style of multiple input levels, turning it into a framework for few-shot level generation.

Topics & Concepts

Security tokenComputer scienceInformation retrievalArtificial intelligenceComputer networkArtificial Intelligence in GamesDigital Games and MediaVideo Analysis and Summarization
TOAD-GAN: A Flexible Framework for Few-Shot Level Generation in Token-Based Games | Litcius