Illuminating Diverse Neural Cellular Automata for Level Generation

TL;DR

This paper introduces a novel quality diversity approach using CMA-ME to generate diverse neural cellular automata for level design in video games, outperforming previous methods in exploring level space.

Contribution

It presents a new method for training diverse NCA-based level generators via a QD approach, enabling varied and capable level designs for multiple 2D games.

Findings

CMA-ME effectively generates diverse, solvable NCA level generators.

NCA representation explores level space better than CPPN baseline.

Generated NCAs meet complex game solvability criteria.

Abstract

We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels. While NCAs have so far only been trained via supervised learning, we present a quality diversity (QD) approach to generating a collection of NCA level generators. By framing the problem as a QD problem, our approach can train diverse level generators, whose output levels vary based on aesthetic or functional criteria. To efficiently generate NCAs, we train generators via Covariance Matrix Adaptation MAP-Elites (CMA-ME), a quality diversity algorithm which specializes in continuous search spaces. We apply our new method to generate level generators for several 2D tile-based games: a maze game, Sokoban, and Zelda. Our results show that CMA-ME can generate small NCAs that are diverse yet capable, often satisfying complex solvability criteria for deterministic agents. We compare against a Compositional Pattern-Producing Network (CPPN) baseline trained to produce diverse collections of generators and show that the NCA representation yields a better exploration of level-space.