Visualising Generative Spaces Using Convolutional Neural Network Embeddings

TL;DR

This paper presents a novel CNN embedding-based method for visualising and comparing the generative spaces of game level systems, demonstrating promising results but with some limitations across different domains.

Contribution

Introduces a CNN embedding approach for visualising game level generation spaces, offering a new tool for comparing procedural content generation systems.

Findings

Effective in visualising levels in some domains

Correlates visualisations with behavioral characteristics

Performance varies across different game domains

Abstract

As academic interest in procedural content generation (PCG) for games has increased, so has the need for methodologies for comparing and contrasting the output spaces of alternative PCG systems. In this paper we introduce and evaluate a novel approach for visualising the generative spaces of level generation systems, using embeddings extracted from a trained convolutional neural network. We evaluate the approach in terms of its ability to produce 2D visualisations of encoded game levels that correlate with their behavioural characteristics. The results across two alternative game domains, Super Mario and Boxoban, indicate that this approach is powerful in certain settings and that it has the potential to supersede alternative methods for visually comparing generative spaces. However its performance was also inconsistent across the domains investigated in this work, as well as it being susceptible to intermittent failure. We conclude that this method is worthy of further evaluation, but that future implementations of it would benefit from significant refinement.