mlsanityData to 14 Oct 2026

TOAD-GAN: Coherent Style Level Generation from a Single Example

arXiv 2008.01531 ↗First posted 4 Aug 2020cs.LG cs.NE stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

In this work, we present TOAD-GAN (Token-based One-shot Arbitrary Dimension Generative Adversarial Network), a novel Procedural Content Generation (PCG) algorithm that generates token-based video game levels. TOAD-GAN follows the SinGAN architecture and can be trained using only one example. We demonstrate its application for Super Mario Bros. levels and are able to generate new levels of similar style in arbitrary sizes. We achieve state-of-the-art results in modeling the patterns of the training level and provide a comparison with different baselines under several metrics. Additionally, we present an extension of the method that allows the user to control the generation process of certain token structures to ensure a coherent global level layout. We provide this tool to the community to spur further research by publishing our source code.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 7; 2023: 3; 2024: 3; 2025: 2.

22 papers.

Sort:

By area:

  1. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  2. 2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 46
  3. 2021CARL: A Benchmark for Contextual and Adaptive Reinforcement Learningcited by 21
  4. 2021Illuminating the Space of Beatable Lode Runner Levels Produced By Various Generative Adversarial Networkscited by 14
  5. 2021World-GAN: a Generative Model for Minecraft Worldscited by 14
  6. 2024DreamGarden: A Designer Assistant for Growing Games from a Single Promptcited by 10
  7. 2022RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Networkcited by 6
  8. 2022Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometrycited by 5
  9. 2021Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variationscited by 4
  10. 2022ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixingcited by 4
  11. 2022Hyperparameters in Contextual RL are Highly Situationalcited by 4
  12. 2023Balancing of competitive two-player Game Levels with Reinforcement Learningcited by 4
10 more
  1. 2024G-PCGRL: Procedural Graph Data Generation via Reinforcement Learningcited by 4
  2. 2022SinTra: Learning an inspiration model from a single multi-track music segmentcited by 2
  3. 2022BlendGAN: Learning and Blending the Internal Distributions of Single Images by Spatial Image-Identity Conditioningcited by 2
  4. 2021Ensemble Learning For Mega Man Level Generationcited by 1
  5. 2023Tree-Based Reconstructive Partitioning: A Novel Low-Data Level Generation Approachcited by 1
  6. 2024Controllable Game Level Generation: Assessing the Effect of Negative Examples in GAN Modelscited by 1
  7. 2021Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learningcited by 0
  8. 2023Evolutionary Machine Learning and Gamescited by 0
  9. 2025Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learningcited by 0
  10. 2025Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learningcited by 0