# Controllable Level Blending between Games using Variational Autoencoders

arXiv: https://arxiv.org/abs/2002.11869 · HTML: https://mlsanity.com/paper/2002.11869/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 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)
- [Dungeon and Platformer Level Blending and Generation using Conditional VAEs](https://mlsanity.com/paper/2106.12692/) (2021)
- [Tile Embedding: A General Representation for Procedural Level Generation via Machine Learning](https://mlsanity.com/paper/2110.03181/) (2021)
- [Generating Lode Runner Levels by Learning Player Paths with LSTMs](https://mlsanity.com/paper/2107.12532/) (2021)
- [Procedural content generation of puzzle games using conditional generative adversarial networks](https://mlsanity.com/paper/2306.15696/) (2023)
- [tile2tile: Learning Game Filters for Platformer Style Transfer](https://mlsanity.com/paper/2208.07699/) (2022)
- [Procedural Content Generation via Knowledge Transformation (PCG-KT)](https://mlsanity.com/paper/2305.00644/) (2023)
- [Clustering-based Tile Embedding (CTE): A General Representation for Level Design with Skewed Tile Distributions](https://mlsanity.com/paper/2210.12789/) (2022)
- [Joint Level Generation and Translation Using Gameplay Videos](https://mlsanity.com/paper/2306.16662/) (2023)
- [Level Generation with Constrained Expressive Range](https://mlsanity.com/paper/2504.05334/) (2025)
- [Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation](https://mlsanity.com/paper/2603.26782/) (2026)
- [Latent Combinational Game Design](https://mlsanity.com/paper/2206.14203/) (2022)
- [Game Level Blending using a Learned Level Representation](https://mlsanity.com/paper/2306.16666/) (2023)
- [Learning Local Constraints for Reinforcement-Learned Content Generators](https://mlsanity.com/paper/2605.13570/) (2026)

## Abstract (arXiv)

Previous work explored blending levels from existing games to create levels for a new game that mixes properties of the original games. In this paper, we use Variational Autoencoders (VAEs) for improving upon such techniques. VAEs are artificial neural networks that learn and use latent representations of datasets to generate novel outputs. We train a VAE on level data from Super Mario Bros. and Kid Icarus, enabling it to capture the latent space spanning both games. We then use this space to generate level segments that combine properties of levels from both games. Moreover, by applying evolutionary search in the latent space, we evolve level segments satisfying specific constraints. We argue that these affordances make the VAE-based approach especially suitable for co-creative level design and compare its performance with similar generative models like the GAN and the VAE-GAN.