# Sequential Segment-based Level Generation and Blending using Variational Autoencoders

arXiv: https://arxiv.org/abs/2007.08746 · HTML: https://mlsanity.com/paper/2007.08746/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 14 of 14)

- [Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder](https://mlsanity.com/paper/2102.12463/) (2021)
- [DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft](https://mlsanity.com/paper/2404.15538/) (2024)
- [Dungeon and Platformer Level Blending and Generation using Conditional VAEs](https://mlsanity.com/paper/2106.12692/) (2021)
- [TaikoNation: Patterning-focused Chart Generation for Rhythm Action Games](https://mlsanity.com/paper/2107.12506/) (2021)
- [Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry](https://mlsanity.com/paper/2206.00106/) (2022)
- [Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations](https://mlsanity.com/paper/2105.12960/) (2021)
- [Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man](https://mlsanity.com/paper/2102.00337/) (2021)
- [Adversarial Random Forest Classifier for Automated Game Design](https://mlsanity.com/paper/2107.12501/) (2021)
- [Generating Game Levels of Diverse Behaviour Engagement](https://mlsanity.com/paper/2207.02100/) (2022)
- [Ensemble Learning For Mega Man Level Generation](https://mlsanity.com/paper/2107.12524/) (2021)
- [On Linking Level Segments](https://mlsanity.com/paper/2203.05057/) (2022)
- [Analysis of Robustness of a Large Game Corpus](https://mlsanity.com/paper/2504.03940/) (2025)
- [Level Generation with Constrained Expressive Range](https://mlsanity.com/paper/2504.05334/) (2025)
- [Game Level Blending using a Learned Level Representation](https://mlsanity.com/paper/2306.16666/) (2023)

## Abstract (arXiv)

Existing methods of level generation using latent variable models such as VAEs and GANs do so in segments and produce the final level by stitching these separately generated segments together. In this paper, we build on these methods by training VAEs to learn a sequential model of segment generation such that generated segments logically follow from prior segments. By further combining the VAE with a classifier that determines whether to place the generated segment to the top, bottom, left or right of the previous segment, we obtain a pipeline that enables the generation of arbitrarily long levels that progress in any of these four directions and are composed of segments that logically follow one another. In addition to generating more coherent levels of non-fixed length, this method also enables implicit blending of levels from separate games that do not have similar orientation. We demonstrate our approach using levels from Super Mario Bros., Kid Icarus and Mega Man, showing that our method produces levels that are more coherent than previous latent variable-based approaches and are capable of blending levels across games.