Deep learning for procedural content generation
- PDF / 2,098,703 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 91 Downloads / 224 Views
(0123456789().,-volV)(0123456789(). ,- volV)
S. I : NEURAL NETWORKS IN ART, SOUND AND DESIGN
Deep learning for procedural content generation Jialin Liu1 • Sam Snodgrass2 • Ahmed Khalifa3 • Sebastian Risi2,4 • Georgios N. Yannakakis2,5,6 Julian Togelius2,3
•
Received: 14 May 2020 / Accepted: 23 September 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Procedural content generation in video games has a long history. Existing procedural content generation methods, such as search-based, solver-based, rule-based and grammar-based methods have been applied to various content types such as levels, maps, character models, and textures. A research field centered on content generation in games has existed for more than a decade. More recently, deep learning has powered a remarkable range of inventions in content production, which are applicable to games. While some cutting-edge deep learning methods are applied on their own, others are applied in combination with more traditional methods, or in an interactive setting. This article surveys the various deep learning methods that have been applied to generate game content directly or indirectly, discusses deep learning methods that could be used for content generation purposes but are rarely used today, and envisages some limitations and potential future directions of deep learning for procedural content generation. Keywords Procedural content generation Game design Deep learning Machine learning Computational and artificial intelligence
1 Introduction & Julian Togelius [email protected]; [email protected] Jialin Liu [email protected] Sam Snodgrass [email protected] Ahmed Khalifa [email protected] Sebastian Risi [email protected] Georgios N. Yannakakis [email protected] 1
Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
2
Modl.ai, Copenhagen, Denmark
3
New York University, New York, USA
4
IT University of Copenhagen, Copenhagen, Denmark
5
Institute of Digital Games, University of Malta, Msida, Malta
6
Technical University of Crete, Chania, Greece
Deep learning has powered a remarkable range of inventions in content production in recent years, including new methods for generating audio, images, 3D objects, network layouts, and other content types across a range of domains. It stands to reason that many of these inventions would be applicable to games. In particular, modern video games require large quantities of high-definition media, which could potentially be generated through deep learning approaches. For example, promising recent methods for generating photo-realistic faces could be used for character creation in games. At the same time, video games have a long tradition of procedural content generation (PCG) [132], where some forms of game content have been generated algorithmically for a long time; the history of digital PCG in games stretches back four decades. In the
Data Loading...
