Details
| Original language | English |
|---|---|
| Title of host publication | Sixteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment |
| Editors | Levi Lelis, David Thue |
| Publication status | Published - 9 Oct 2020 |
| Event | Sixteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment - online Duration: 19 Oct 2020 → 22 Oct 2020 Conference number: 16 |
Publication series
| Name | Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment |
|---|---|
| Number | 1 |
| Volume | 16 |
| ISSN (Print) | 2326-909X |
| ISSN (electronic) | 2334-0924 |
Abstract
Keywords
- cs.LG, cs.NE, stat.ML
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Sixteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment . ed. / Levi Lelis; David Thue. 2020. (Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment; Vol. 16, No. 1).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - TOAD-GAN
T2 - Sixteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
AU - Awiszus, Maren
AU - Schubert, Frederik
AU - Rosenhahn, Bodo
N1 - Conference code: 16
PY - 2020/10/9
Y1 - 2020/10/9
N2 - 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.
AB - 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.
KW - cs.LG
KW - cs.NE
KW - stat.ML
UR - http://www.scopus.com/inward/record.url?scp=85092352540&partnerID=8YFLogxK
M3 - Conference contribution
SN - 978-1-57735-849-7
T3 - Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
BT - Sixteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
A2 - Lelis, Levi
A2 - Thue, David
Y2 - 19 October 2020 through 22 October 2020
ER -