# Bootstrapping Conditional GANs for Video Game Level Generation

arXiv: https://arxiv.org/abs/1910.01603 · HTML: https://mlsanity.com/paper/1910.01603/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2019.

## Built on by (most cited first, 30 of 35)

- [Level Generation Through Large Language Models](https://mlsanity.com/paper/2302.05817/) (2023)
- [On the Constrained Time-Series Generation Problem](https://mlsanity.com/paper/2307.01717/) (2023)
- [Deep Surrogate Assisted Generation of Environments](https://mlsanity.com/paper/2206.04199/) (2022)
- [On the Importance of Environments in Human-Robot Coordination](https://mlsanity.com/paper/2106.10853/) (2021)
- [Creativity and Machine Learning: A Survey](https://mlsanity.com/paper/2104.02726/) (2021)
- [Practical PCG Through Large Language Models](https://mlsanity.com/paper/2305.18243/) (2023)
- [Learning Controllable 3D Level Generators](https://mlsanity.com/paper/2206.13623/) (2022)
- [Word2World: Generating Stories and Worlds through Large Language Models](https://mlsanity.com/paper/2405.06686/) (2024)
- [DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft](https://mlsanity.com/paper/2404.15538/) (2024)
- [Illuminating the Space of Beatable Lode Runner Levels Produced By Various Generative Adversarial Networks](https://mlsanity.com/paper/2101.07868/) (2021)
- [Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset](https://mlsanity.com/paper/2202.10184/) (2022)
- [Mutation Models: Learning to Generate Levels by Imitating Evolution](https://mlsanity.com/paper/2206.05497/) (2022)
- [Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution](https://mlsanity.com/paper/2104.06106/) (2021)
- [Physics-informed attention-based neural network for solving non-linear partial differential equations](https://mlsanity.com/paper/2105.07898/) (2021)
- [The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in Games](https://mlsanity.com/paper/2503.21474/) (2025)
- [Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry](https://mlsanity.com/paper/2206.00106/) (2022)
- [Measuring Diversity of Game Scenarios](https://mlsanity.com/paper/2404.15192/) (2024)
- [Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations](https://mlsanity.com/paper/2105.12960/) (2021)
- [Minimal Neural Network Models for Permutation Invariant Agents](https://mlsanity.com/paper/2205.07868/) (2022)
- [Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man](https://mlsanity.com/paper/2102.00337/) (2021)
- [Fast Game Content Adaptation Through Bayesian-based Player Modelling](https://mlsanity.com/paper/2105.08484/) (2021)
- [Adversarial Random Forest Classifier for Automated Game Design](https://mlsanity.com/paper/2107.12501/) (2021)
- [Procedural content generation of puzzle games using conditional generative adversarial networks](https://mlsanity.com/paper/2306.15696/) (2023)
- [Word2Minecraft: Generating 3D Game Levels through Large Language Models](https://mlsanity.com/paper/2503.16536/) (2025)
- [Keiki: Towards Realistic Danmaku Generation via Sequential GANs](https://mlsanity.com/paper/2107.02991/) (2021)
- [Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes](https://mlsanity.com/paper/2209.15052/) (2022)
- [Ensemble Learning For Mega Man Level Generation](https://mlsanity.com/paper/2107.12524/) (2021)
- [Controllable Path of Destruction](https://mlsanity.com/paper/2305.18553/) (2023)
- [PCGPT: Procedural Content Generation via Transformers](https://mlsanity.com/paper/2310.02405/) (2023)
- [Controllable Game Level Generation: Assessing the Effect of Negative Examples in GAN Models](https://mlsanity.com/paper/2410.23108/) (2024)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have shown im-pressive results for image generation. However, GANs facechallenges in generating contents with certain types of con-straints, such as game levels. Specifically, it is difficult togenerate levels that have aesthetic appeal and are playable atthe same time. Additionally, because training data usually islimited, it is challenging to generate unique levels with cur-rent GANs. In this paper, we propose a new GAN architec-ture namedConditional Embedding Self-Attention Genera-tive Adversarial Network(CESAGAN) and a new bootstrap-ping training procedure. The CESAGAN is a modification ofthe self-attention GAN that incorporates an embedding fea-ture vector input to condition the training of the discriminatorand generator. This allows the network to model non-localdependency between game objects, and to count objects. Ad-ditionally, to reduce the number of levels necessary to trainthe GAN, we propose a bootstrapping mechanism in whichplayable generated levels are added to the training set. Theresults demonstrate that the new approach does not only gen-erate a larger number of levels that are playable but also gen-erates fewer duplicate levels compared to a standard GAN.