# Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder

arXiv: https://arxiv.org/abs/2102.12463 · HTML: https://mlsanity.com/paper/2102.12463/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 56 references that are in the map.
- First posted on arXiv 24 Feb 2021.

## Builds on (most cited first, 30 of 30)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Go-Explore: a New Approach for Hard-Exploration Problems](https://mlsanity.com/paper/1901.10995/) (2019)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space](https://mlsanity.com/paper/1912.02400/) (2019)
- [Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network](https://mlsanity.com/paper/1805.00728/) (2018)
- [Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network](https://mlsanity.com/paper/2007.05674/) (2020)
- [Procedural Content Generation through Quality Diversity](https://mlsanity.com/paper/1907.04053/) (2019)
- [The VGLC: The Video Game Level Corpus](https://mlsanity.com/paper/1606.07487/) (2016)
- [Super Mario as a String: Platformer Level Generation Via LSTMs](https://mlsanity.com/paper/1603.00930/) (2016)
- [Mapping Hearthstone Deck Spaces through MAP-Elites with Sliding Boundaries](https://mlsanity.com/paper/1904.10656/) (2019)
- [Talakat: Bullet Hell Generation through Constrained Map-Elites](https://mlsanity.com/paper/1806.04718/) (2018)
- [Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks](https://mlsanity.com/paper/2004.00151/) (2020)
- [Baba is Y'all: Collaborative Mixed-Initiative Level Design](https://mlsanity.com/paper/2003.14294/) (2020)
- [CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation](https://mlsanity.com/paper/2004.01703/) (2020)
- [Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-Elites](https://mlsanity.com/paper/1906.05175/) (2019)
- [Diverse Agents for Ad-Hoc Cooperation in Hanabi](https://mlsanity.com/paper/1907.03840/) (2019)
- [Conditional Level Generation and Game Blending](https://mlsanity.com/paper/2010.07735/) (2020)
- [Automated Game Design via Conceptual Expansion](https://mlsanity.com/paper/1809.02232/) (2018)
- [Controllable Level Blending between Games using Variational Autoencoders](https://mlsanity.com/paper/2002.11869/) (2020)
- [Finding Game Levels with the Right Difficulty in a Few Trials through Intelligent Trial-and-Error](https://mlsanity.com/paper/2005.07677/) (2020)
- [Sequential Segment-based Level Generation and Blending using Variational Autoencoders](https://mlsanity.com/paper/2007.08746/) (2020)
- [Exploring Level Blending across Platformers via Paths and Affordances](https://mlsanity.com/paper/2009.06356/) (2020)
- [Mech-Elites: Illuminating the Mechanic Space of GVGAI](https://mlsanity.com/paper/2002.04733/) (2020)
- [Towards Game Design via Creative Machine Learning (GDCML)](https://mlsanity.com/paper/2008.13548/) (2020)
- [Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoders](https://mlsanity.com/paper/2006.09807/) (2020)
- [Generating Levels That Teach Mechanics](https://mlsanity.com/paper/1807.06734/) (2018)
- [Game Level Clustering and Generation using Gaussian Mixture VAEs](https://mlsanity.com/paper/2009.09811/) (2020)
- [Entity Embedding as Game Representation](https://mlsanity.com/paper/2010.01685/) (2020)
- [Mechanics Automatically Recognized via Interactive Observation: Jumping](https://mlsanity.com/paper/1707.03865/) (2017)

## Built on by (most cited first, 27 of 27)

- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [MarioGPT: Open-Ended Text2Level Generation through Large Language Models](https://mlsanity.com/paper/2302.05981/) (2023)
- [Deep Surrogate Assisted Generation of Environments](https://mlsanity.com/paper/2206.04199/) (2022)
- [Covariance Matrix Adaptation MAP-Annealing](https://mlsanity.com/paper/2205.10752/) (2022)
- [Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning](https://mlsanity.com/paper/2305.13795/) (2023)
- [The Five-Dollar Model: Generating Game Maps and Sprites from Sentence Embeddings](https://mlsanity.com/paper/2308.04052/) (2023)
- [Dungeon and Platformer Level Blending and Generation using Conditional VAEs](https://mlsanity.com/paper/2106.12692/) (2021)
- [Surrogate Assisted Generation of Human-Robot Interaction Scenarios](https://mlsanity.com/paper/2304.13787/) (2023)
- [Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity](https://mlsanity.com/paper/2210.09918/) (2022)
- [Lode Encoder: AI-constrained co-creativity](https://mlsanity.com/paper/2308.01312/) (2023)
- [Hierarchical Quality-Diversity for Online Damage Recovery](https://mlsanity.com/paper/2204.05726/) (2022)
- [Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry](https://mlsanity.com/paper/2206.00106/) (2022)
- [Evolving Populations of Diverse RL Agents with MAP-Elites](https://mlsanity.com/paper/2303.12803/) (2023)
- [Measuring Diversity of Game Scenarios](https://mlsanity.com/paper/2404.15192/) (2024)
- [Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination](https://mlsanity.com/paper/2504.20643/) (2025)
- [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)
- [Joint Level Generation and Translation Using Gameplay Videos](https://mlsanity.com/paper/2306.16662/) (2023)
- [Reconstructing Existing Levels through Level Inpainting](https://mlsanity.com/paper/2309.09472/) (2023)
- [Level Generation with Constrained Expressive Range](https://mlsanity.com/paper/2504.05334/) (2025)
- [Video Game Level Design as a Multi-Agent Reinforcement Learning Problem](https://mlsanity.com/paper/2510.04862/) (2025)
- [Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces](https://mlsanity.com/paper/2601.01082/) (2026)
- [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)
- [Targeted Analysis of High-Risk States Using an Oriented Variational Autoencoder](https://mlsanity.com/paper/2303.11410/) (2023)
- [LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search](https://mlsanity.com/paper/2404.14063/) (2024)
- [Level Generation with Quantum Reservoir Computing](https://mlsanity.com/paper/2505.13287/) (2025)

## Abstract (arXiv)

Several works have demonstrated the use of variational autoencoders (VAEs) for generating levels in the style of existing games and blending levels across different games. Further, quality-diversity (QD) algorithms have also become popular for generating varied game content by using evolution to explore a search space while focusing on both variety and quality. To reap the benefits of both these approaches, we present a level generation and game blending approach that combines the use of VAEs and QD algorithms. Specifically, we train VAEs on game levels and run the MAP-Elites QD algorithm using the learned latent space of the VAE as the search space. The latent space captures the properties of the games whose levels we want to generate and blend, while MAP-Elites searches this latent space to find a diverse set of levels optimizing a given objective such as playability. We test our method using models for 5 different platformer games as well as a blended domain spanning 3 of these games. We refer to using MAP-Elites for blending as Blend-Elites. Our results show that MAP-Elites in conjunction with VAEs enables the generation of a diverse set of playable levels not just for each individual game but also for the blended domain while illuminating game-specific regions of the blended latent space.