mlsanityData to 14 Oct 2026

Latent Combinational Game Design

arXiv 2206.14203 ↗First posted 28 Jun 2022cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We present latent combinational game design -- an approach for generating playable games that blend a given set of games in a desired combination using deep generative latent variable models. We use Gaussian Mixture Variational Autoencoders (GMVAEs) which model the VAE latent space via a mixture of Gaussian components. Through supervised training, each component encodes levels from one game and lets us define blended games as linear combinations of these components. This enables generating new games that blend the input games as well as controlling the relative proportions of each game in the blend. We also extend prior blending work using conditional VAEs and compare against the GMVAE and additionally introduce a hybrid conditional GMVAE (CGMVAE) architecture which lets us generate whole blended levels and layouts. Results show that these approaches can generate playable games that blend the input games in specified combinations. We use both platformers and dungeon-based games to demonstrate our results.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 44 references that are in the map. First posted on arXiv 28 Jun 2022.

Builds on

21 of 44 references.

References · 21

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 220
  4. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 137
  5. 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
  6. 2019Procedural Content Generation through Quality Diversitycited by 45
  7. 2016The VGLC: The Video Game Level Corpuscited by 41
  8. 2016Super Mario as a String: Platformer Level Generation Via LSTMscited by 40
  9. 2021Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencodercited by 27
  10. 2020Conditional Level Generation and Game Blendingcited by 17
  11. 2019Tile Pattern KL-Divergence for Analysing and Evolving Game Levelscited by 16
  12. 2018Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Imagescited by 15
9 more
  1. 2020Open-Set Recognition with Gaussian Mixture Variational Autoencoderscited by 15
  2. 2020Controllable Level Blending between Games using Variational Autoencoderscited by 14
  3. 2020Exploring Level Blending across Platformers via Paths and Affordancescited by 14
  4. 2020Towards Game Design via Creative Machine Learning (GDCML)cited by 13
  5. 2020Conceptual Game Expansioncited by 11
  6. 2020Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoderscited by 11
  7. 2021Dungeon and Platformer Level Blending and Generation using Conditional VAEscited by 10
  8. 2020Game Level Clustering and Generation using Gaussian Mixture VAEscited by 9
  9. 2017Mechanics Automatically Recognized via Interactive Observation: Jumpingcited by 4

Built on by

Not cited yet.