Bootstrapping Conditional GANs for Video Game Level Generation

Torrado, Ruben Rodriguez; Khalifa, Ahmed; Green, Michael Cerny; Justesen, Niels; Risi, Sebastian; Togelius, Julian

doi:10.48550/arxiv.1910.01603

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With TOAD-GAN, we take this problem to the extreme regime of learning from only one single training level. Similar to other recent publications (Volz et al 2018;Torrado et al 2019;Volz et al 2020), TOAD-GAN is based on the GAN architecture.…”

Section: Methodssupporting

confidence: 54%

See 1 more Smart Citation

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

Awiszus

Schubert

Rosenhahn

2020

AIIDE

View full text Add to dashboard Cite

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.

show abstract

Section: Methodssupporting

confidence: 54%

“…Limited training data is one of the key problems of PCGML algorithms (Torrado et al 2019;Bontrager and Togelius 2020). Therefore, the goal of our work is the generation of new levels for SMB from very little training data.…”

Section: Methodsmentioning

confidence: 99%

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

Awiszus

Schubert

Rosenhahn

2020

AIIDE

View full text Add to dashboard Cite

show abstract

“…We extend this evaluation to several adaptations discussed in Section III. We apply two popular PCGML techniques, namely Markov Random Fields (MRF) [7] and Generative Adversarial Networks (GAN) [11], [18], [29] to CCS level generation. As argued in Section II-A, CCS levels exhibit several patterns at different scales.…”

Section: Methodsmentioning

confidence: 99%

Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning

Volz¹,

Justesen²,

Snodgrass³

et al. 2020

2020 IEEE Conference on Games (CoG)

Self Cite

View full text Add to dashboard Cite

Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically. While these approaches are able to generate content for different games (e.g. Super Mario Bros., DOOM, Zelda, and Kid Icarus), it is an open questions how well these approaches can capture large-scale visual patterns such as symmetry. In this paper, we propose match-three games as a domain to test PCGML algorithms regarding their ability to generate suitable patterns. We demonstrate that popular algorithm such as Generative Adversarial Networks struggle in this domain and propose adaptations to improve their performance. In particular we augment the neighborhood of a Markov Random Fields approach to not only take local but also symmetric positional information into account. We conduct several empirical tests including a user study that show the improvements achieved by the proposed modifications, and obtain promising results.

show abstract

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

Awiszus¹,

Schubert²,

Rosenhahn³

2020

Preprint

View full text Add to dashboard Cite

In this work, we present TOAD-GAN (Token-based Oneshot 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.

show abstract

Bootstrapping Conditional GANs for Video Game Level Generation

Cited by 3 publications

References 0 publications

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

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

Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning

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

Contact Info

Product

Resources

About