# Game Level Clustering and Generation using Gaussian Mixture VAEs

arXiv: https://arxiv.org/abs/2009.09811 · HTML: https://mlsanity.com/paper/2009.09811/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2020.

## Built on by (most cited first, 9 of 9)

- [Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder](https://mlsanity.com/paper/2102.12463/) (2021)
- [An improved tabular data generator with VAE-GMM integration](https://mlsanity.com/paper/2404.08434/) (2024)
- [Dungeon and Platformer Level Blending and Generation using Conditional VAEs](https://mlsanity.com/paper/2106.12692/) (2021)
- [Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry](https://mlsanity.com/paper/2206.00106/) (2022)
- [Training Latent Variable Models with Auto-encoding Variational Bayes: A Tutorial](https://mlsanity.com/paper/2208.07818/) (2022)
- [Ensemble Learning For Mega Man Level Generation](https://mlsanity.com/paper/2107.12524/) (2021)
- [Clustering-based Tile Embedding (CTE): A General Representation for Level Design with Skewed Tile Distributions](https://mlsanity.com/paper/2210.12789/) (2022)
- [Reconstructing Existing Levels through Level Inpainting](https://mlsanity.com/paper/2309.09472/) (2023)
- [Latent Combinational Game Design](https://mlsanity.com/paper/2206.14203/) (2022)

## Abstract (arXiv)

Variational autoencoders (VAEs) have been shown to be able to generate game levels but require manual exploration of the learned latent space to generate outputs with desired attributes. While conditional VAEs address this by allowing generation to be conditioned on labels, such labels have to be provided during training and thus require prior knowledge which may not always be available. In this paper, we apply Gaussian Mixture VAEs (GMVAEs), a variant of the VAE which imposes a mixture of Gaussians (GM) on the latent space, unlike regular VAEs which impose a unimodal Gaussian. This allows GMVAEs to cluster levels in an unsupervised manner using the components of the GM and then generate new levels using the learned components. We demonstrate our approach with levels from Super Mario Bros., Kid Icarus and Mega Man. Our results show that the learned components discover and cluster level structures and patterns and can be used to generate levels with desired characteristics.