GAVEL: Generating Games Via Evolution and Language Models
This work addresses the challenge of automated game generation for game designers and researchers, offering a more expansive approach compared to prior domain-specific methods.
The authors tackled the problem of automatically generating novel and interesting games by developing a method that combines large language models and evolutionary computation to mutate and recombine game rules in the Ludii language, resulting in new games that explore regions of the rules space not covered by existing datasets.
Automatically generating novel and interesting games is a complex task. Challenges include representing game rules in a computationally workable form, searching through the large space of potential games under most such representations, and accurately evaluating the originality and quality of previously unseen games. Prior work in automated game generation has largely focused on relatively restricted rule representations and relied on domain-specific heuristics. In this work, we explore the generation of novel games in the comparatively expansive Ludii game description language, which encodes the rules of over 1000 board games in a variety of styles and modes of play. We draw inspiration from recent advances in large language models and evolutionary computation in order to train a model that intelligently mutates and recombines games and mechanics expressed as code. We demonstrate both quantitatively and qualitatively that our approach is capable of generating new and interesting games, including in regions of the potential rules space not covered by existing games in the Ludii dataset. A sample of the generated games are available to play online through the Ludii portal.