# Controllable Game Level Generation: Assessing the Effect of Negative Examples in GAN Models

arXiv: https://arxiv.org/abs/2410.23108 · HTML: https://mlsanity.com/paper/2410.23108/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 30 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network](https://mlsanity.com/paper/1805.00728/) (2018)
- [The VGLC: The Video Game Level Corpus](https://mlsanity.com/paper/1606.07487/) (2016)
- [Bootstrapping Conditional GANs for Video Game Level Generation](https://mlsanity.com/paper/1910.01603/) (2019)
- [Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks](https://mlsanity.com/paper/2004.00151/) (2020)
- [TOAD-GAN: Coherent Style Level Generation from a Single Example](https://mlsanity.com/paper/2008.01531/) (2020)
- [DOOM Level Generation using Generative Adversarial Networks](https://mlsanity.com/paper/1804.09154/) (2018)
- [Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man](https://mlsanity.com/paper/2102.00337/) (2021)
- [Procedural content generation of puzzle games using conditional generative adversarial networks](https://mlsanity.com/paper/2306.15696/) (2023)

## Built on by (most cited first, 1 of 1)

- [Axiomatic Explainer Globalness via Optimal Transport](https://mlsanity.com/paper/2411.01126/) (2024)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) are unsupervised models designed to learn and replicate a target distribution. The vanilla versions of these models can be extended to more controllable models. Conditional Generative Adversarial Networks (CGANs) extend vanilla GANs by conditioning both the generator and discriminator on some additional information (labels). Controllable models based on complementary learning, such as Rumi-GAN, have been introduced. Rumi-GANs leverage negative examples to enhance the generator's ability to learn positive examples. We evaluate the performance of two controllable GAN variants, CGAN and Rumi-GAN, in generating game levels targeting specific constraints of interest: playability and controllability. This evaluation is conducted under two scenarios: with and without the inclusion of negative examples. The goal is to determine whether incorporating negative examples helps the GAN models avoid generating undesirable outputs. Our findings highlight the strengths and weaknesses of each method in enforcing the generation of specific conditions when generating outputs based on given positive and negative examples.