Mortar: Evolving Mechanics For Automatic Game Design

Muhammad Umair Nasir, Yuchen Li, Steven James, Julian Togelius

Keywords: Automatic Game Design, Procedural Content Generation, Quality Diversity Algorithms, Large Language Models

TL;DR: Mortar is a system that evolves mechanics and then evaluates them on automatically designed games through LLM and tree search.

Abstract: We present Mortar, a system for autonomously evolving game mechanics for automatic game design. Game mechanics define the rules and interactions that govern gameplay, and designing them manually is a time-consuming and expert-driven process. Mortar combines a quality-diversity algorithm with a large language model to explore a diverse set of mechanics, which are evaluated by synthesising complete games that incorporate both the evolved mechanic and those drawn from an archive. These are evaluated by composing complete games through a tree search procedure, where the resulting games are evaluated by their ability to preserve a skill-based ordering over players---that is, whether stronger players consistently outperform weaker ones. We assess the mechanics based on their contribution towards the skill-based ordering score in the game. We demonstrate that Mortar produces games that appear diverse and playable, and mechanics that contribute more towards the skill-based ordering score in the game. We perform ablation studies to assess the role of each system component and a user study to evaluate the games based on human feedback.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 7042