Lode Enhancer: Level Co-creation Through Scaling

Debosmita Bhaumik; Julian Togelius; Georgios N. Yannakakis; Ahmed Khalifa

doi:10.1145/3582437.3587206

Lode Enhancer: Level Co-creation Through Scaling

Debosmita Bhaumik, Julian Togelius, Georgios N. Yannakakis, Ahmed Khalifa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We explore AI-powered upscaling as a design assistance tool in the context of creating 2D game levels. Deep neural networks are used to upscale artificially downscaled patches of levels from the puzzle platformer game Lode Runner. The trained networks are incorporated into a web-based editor, where the user can create and edit levels at three different levels of resolution: 4x4, 8x8, and 16x16. An edit at any resolution instantly transfers to the other resolutions. As upscaling requires inventing features that might not be present at lower resolutions, we train neural networks to reproduce these features. We introduce a neural network architecture that is capable of not only learning upscaling but also giving higher priority to less frequent tiles. To investigate the potential of this tool and guide further development, we conduct a qualitative study with 3 designers to understand how they use it. Designers enjoyed co-designing with the tool, liked its underlying concept, and provided feedback for further improvement.

Original language	English (US)
Title of host publication	Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023
Editors	Phil Lopes, Filipe Luz, Antonios Liapis, Henrik Engstrom
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450398565
DOIs	https://doi.org/10.1145/3582437.3587206
State	Published - Apr 12 2023
Event	18th International Conference on the Foundations of Digital Games, FDG 2023 - Lisbon, Portugal Duration: Apr 11 2023 → Apr 14 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	18th International Conference on the Foundations of Digital Games, FDG 2023
Country/Territory	Portugal
City	Lisbon
Period	4/11/23 → 4/14/23

Keywords

mixed-initiative
neural networks
procedural content generation
supervised learning
upscaling

ASJC Scopus subject areas

Human-Computer Interaction
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software

Access to Document

10.1145/3582437.3587206

Cite this

Bhaumik, D., Togelius, J., Yannakakis, G. N., & Khalifa, A. (2023). Lode Enhancer: Level Co-creation Through Scaling. In P. Lopes, F. Luz, A. Liapis, & H. Engstrom (Eds.), Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023 Article 65 (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3582437.3587206

Lode Enhancer: Level Co-creation Through Scaling. / Bhaumik, Debosmita; Togelius, Julian; Yannakakis, Georgios N. et al.
Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023. ed. / Phil Lopes; Filipe Luz; Antonios Liapis; Henrik Engstrom. Association for Computing Machinery, 2023. 65 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Bhaumik, D, Togelius, J, Yannakakis, GN & Khalifa, A 2023, Lode Enhancer: Level Co-creation Through Scaling. in P Lopes, F Luz, A Liapis & H Engstrom (eds), Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023., 65, ACM International Conference Proceeding Series, Association for Computing Machinery, 18th International Conference on the Foundations of Digital Games, FDG 2023, Lisbon, Portugal, 4/11/23. https://doi.org/10.1145/3582437.3587206

Bhaumik D, Togelius J, Yannakakis GN, Khalifa A. Lode Enhancer: Level Co-creation Through Scaling. In Lopes P, Luz F, Liapis A, Engstrom H, editors, Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023. Association for Computing Machinery. 2023. 65. (ACM International Conference Proceeding Series). doi: 10.1145/3582437.3587206

Bhaumik, Debosmita ; Togelius, Julian ; Yannakakis, Georgios N. et al. / Lode Enhancer : Level Co-creation Through Scaling. Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023. editor / Phil Lopes ; Filipe Luz ; Antonios Liapis ; Henrik Engstrom. Association for Computing Machinery, 2023. (ACM International Conference Proceeding Series).

@inproceedings{4d339d32d93b4a51a43c04992a508bf7,

title = "Lode Enhancer: Level Co-creation Through Scaling",

abstract = "We explore AI-powered upscaling as a design assistance tool in the context of creating 2D game levels. Deep neural networks are used to upscale artificially downscaled patches of levels from the puzzle platformer game Lode Runner. The trained networks are incorporated into a web-based editor, where the user can create and edit levels at three different levels of resolution: 4x4, 8x8, and 16x16. An edit at any resolution instantly transfers to the other resolutions. As upscaling requires inventing features that might not be present at lower resolutions, we train neural networks to reproduce these features. We introduce a neural network architecture that is capable of not only learning upscaling but also giving higher priority to less frequent tiles. To investigate the potential of this tool and guide further development, we conduct a qualitative study with 3 designers to understand how they use it. Designers enjoyed co-designing with the tool, liked its underlying concept, and provided feedback for further improvement.",

keywords = "mixed-initiative, neural networks, procedural content generation, supervised learning, upscaling",

author = "Debosmita Bhaumik and Julian Togelius and Yannakakis, {Georgios N.} and Ahmed Khalifa",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 18th International Conference on the Foundations of Digital Games, FDG 2023 ; Conference date: 11-04-2023 Through 14-04-2023",

year = "2023",

month = apr,

day = "12",

doi = "10.1145/3582437.3587206",

language = "English (US)",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

editor = "Phil Lopes and Filipe Luz and Antonios Liapis and Henrik Engstrom",

booktitle = "Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023",

}

TY - GEN

T1 - Lode Enhancer

T2 - 18th International Conference on the Foundations of Digital Games, FDG 2023

AU - Bhaumik, Debosmita

AU - Togelius, Julian

AU - Yannakakis, Georgios N.

AU - Khalifa, Ahmed

PY - 2023/4/12

Y1 - 2023/4/12

N2 - We explore AI-powered upscaling as a design assistance tool in the context of creating 2D game levels. Deep neural networks are used to upscale artificially downscaled patches of levels from the puzzle platformer game Lode Runner. The trained networks are incorporated into a web-based editor, where the user can create and edit levels at three different levels of resolution: 4x4, 8x8, and 16x16. An edit at any resolution instantly transfers to the other resolutions. As upscaling requires inventing features that might not be present at lower resolutions, we train neural networks to reproduce these features. We introduce a neural network architecture that is capable of not only learning upscaling but also giving higher priority to less frequent tiles. To investigate the potential of this tool and guide further development, we conduct a qualitative study with 3 designers to understand how they use it. Designers enjoyed co-designing with the tool, liked its underlying concept, and provided feedback for further improvement.

AB - We explore AI-powered upscaling as a design assistance tool in the context of creating 2D game levels. Deep neural networks are used to upscale artificially downscaled patches of levels from the puzzle platformer game Lode Runner. The trained networks are incorporated into a web-based editor, where the user can create and edit levels at three different levels of resolution: 4x4, 8x8, and 16x16. An edit at any resolution instantly transfers to the other resolutions. As upscaling requires inventing features that might not be present at lower resolutions, we train neural networks to reproduce these features. We introduce a neural network architecture that is capable of not only learning upscaling but also giving higher priority to less frequent tiles. To investigate the potential of this tool and guide further development, we conduct a qualitative study with 3 designers to understand how they use it. Designers enjoyed co-designing with the tool, liked its underlying concept, and provided feedback for further improvement.

KW - mixed-initiative

KW - neural networks

KW - procedural content generation

KW - supervised learning

KW - upscaling

UR - http://www.scopus.com/inward/record.url?scp=85153580003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85153580003&partnerID=8YFLogxK

U2 - 10.1145/3582437.3587206

DO - 10.1145/3582437.3587206

M3 - Conference contribution

AN - SCOPUS:85153580003

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023

A2 - Lopes, Phil

A2 - Luz, Filipe

A2 - Liapis, Antonios

A2 - Engstrom, Henrik

PB - Association for Computing Machinery

Y2 - 11 April 2023 through 14 April 2023

ER -

Lode Enhancer: Level Co-creation Through Scaling

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this