mlsanityData to 7 Oct 2026

Dungeon and Platformer Level Blending and Generation using Conditional VAEs

arXiv 2106.12692 ↗First posted 17 Jun 2021cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Variational autoencoders (VAEs) have been used in prior works for generating and blending levels from different games. To add controllability to these models, conditional VAEs (CVAEs) were recently shown capable of generating output that can be modified using labels specifying desired content, albeit working with segments of levels and platformers exclusively. We expand these works by using CVAEs for generating whole platformer and dungeon levels, and blending levels across these genres. We show that CVAEs can reliably control door placement in dungeons and progression direction in platformer levels. Thus, by using appropriate labels, our approach can generate whole dungeons and platformer levels of interconnected rooms and segments respectively as well as levels that blend dungeons and platformers. We demonstrate our approach using The Legend of Zelda, Metroid, Mega Man and Lode Runner.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

20 of 35 references.

References · 20

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 136
  3. 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
  4. 2018Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Networkcited by 76
  5. 2016The VGLC: The Video Game Level Corpuscited by 41
  6. 2021Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencodercited by 27
  7. 2020Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networkscited by 22
  8. 2020Conditional Level Generation and Game Blendingcited by 17
  9. 2018DOOM Level Generation using Generative Adversarial Networkscited by 15
  10. 2020Controllable Level Blending between Games using Variational Autoencoderscited by 14
  11. 2020Sequential Segment-based Level Generation and Blending using Variational Autoencoderscited by 14
  12. 2020Exploring Level Blending across Platformers via Paths and Affordancescited by 14
8 more
  1. 2021Illuminating the Space of Beatable Lode Runner Levels Produced By Various Generative Adversarial Networkscited by 14
  2. 2020Towards Game Design via Creative Machine Learning (GDCML)cited by 12
  3. 2020Conceptual Game Expansioncited by 11
  4. 2020Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoderscited by 11
  5. 2020Game Level Clustering and Generation using Gaussian Mixture VAEscited by 9
  6. 2020Generative Adversarial Network Rooms in Generative Graph Grammar Dungeons for The Legend of Zeldacited by 8
  7. 2020Mario Level Generation From Mechanics Using Scene Stitchingcited by 8
  8. 2021Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Mancited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 1; 2025: 0; 2026: 1.

10 papers.

  1. 2023Level Generation Through Large Language Modelscited by 68
  2. 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 63
  3. 2022Mutation Models: Learning to Generate Levels by Imitating Evolutioncited by 9
  4. 2022TropeTwist: Trope-based Narrative Structure Generationcited by 8
  5. 2022Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometrycited by 5
  6. 2023Procedural Content Generation via Knowledge Transformation (PCG-KT)cited by 2
  7. 2023Joint Level Generation and Translation Using Gameplay Videoscited by 1
  8. 2026Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representationcited by 1
  9. 2022Latent Combinational Game Designcited by 0
  10. 2024Improving Conditional Level Generation using Automated Validation in Match-3 Gamescited by 0