Seth Cooper
ABSTRACT
Procedural level generation techniques that learn local neighborhoods from example levels (such as WaveFunctionCollapse) have risen in popularity. Usually the neighborhood structure (such as a regular grid) onto which a level is generated is fixed in advance and not generated. In this work, we present a constraint-based approach for graph generation that learns local neighborhood patterns (in the form of labeled nodes and edges) from example graphs. This allows the approach to generate graphs with varying structures that are still locally similar to the examples. We demonstrate the approach on several applications, such as abstract graphs describing Legend of Zelda dungeons. Additionally, using Super Mario Bros. levels, we show how techniques that run on a grid may be considered a special case of graph generation where each tile is a node connecting to its neighboring tiles’ nodes.
- Keven Ates, Jacek Kukluk, Lawrence Holder, Diane Cook, and Kang Zhang. 2006. Graph Grammar Induction on Structural Data for Visual Programming. In 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI’06). 232–242.Google Scholar
- Diane J. Cook and Lawrence B. Holder. 1994. Substructure discovery using minimum description length and background knowledge. Journal of Artificial Intelligence Research 1, 1 (Feb. 1994), 231–255.Google ScholarCross Ref
- Seth Cooper. 2022. Constraint-Based 2D Tile Game Blending in the Sturgeon System. In Proceedings of the Experimental AI in Games Workshop.Google Scholar
- Seth Cooper. 2022. Sturgeon: tile-based procedural level generation via learned and designed constraints. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 18, 1 (2022), 26–36.Google ScholarDigital Library
- Steve Dahlskog, Julian Togelius, and Mark J. Nelson. 2014. Linear levels through n-grams. In Proceedings of the 18th International Academic MindTrek Conference: Media Business, Management, Content & Services. 200–206.Google ScholarDigital Library
- Joris Dormans. 2010. Adventures in level design: generating missions and spaces for action adventure games. In Proceedings of the 2010 Workshop on Procedural Content Generation in Games(PCGames ’10). Association for Computing Machinery, 1–8.Google ScholarDigital Library
- Joris Dormans and Sander Bakkes. 2011. Generating missions and spaces for adaptable play experiences. IEEE Transactions on Computational Intelligence and AI in Games 3, 3 (Sept. 2011), 216–228.Google ScholarCross Ref
- Jose M. Font, Roberto Izquierdo, Daniel Manrique, and Julian Togelius. 2016. Constrained level generation through grammar-based evolutionary algorithms. In Applications of Evolutionary Computation(Lecture Notes in Computer Science), Giovanni Squillero and Paolo Burelli (Eds.). Springer International Publishing, 558–573.Google Scholar
- Luka Fürst, Marjan Mernik, and Viljan Mahnič. 2020. Graph grammar induction. In Advances in Computers, Ali R. Hurson and Veljko Milutinović (Eds.). Vol. 116. Elsevier, 133–181.Google Scholar
- Felipe Grando and Luís C. Lamb. 2018. On the effectiveness of the block two-level Erdős-Rényi generative network model. In 2018 IEEE Symposium on Computers and Communications (ISCC). 360–365.Google ScholarCross Ref
- Maxim Gumin. 2016. WaveFunctionCollapse. https://github.com/mxgmn/WaveFunctionCollapse.Google Scholar
- Eduardo Hauck and Claus Aranha. 2020. Automatic generation of Super Mario levels via graph grammars. In 2020 IEEE Conference on Games (CoG). 297–304.Google ScholarCross Ref
- Alexey Ignatiev, Antonio Morgado, and Joao Marques-Silva. 2018. PySAT: a Python toolkit for prototyping with SAT oracles. In Theory and Applications of Satisfiability Testing – SAT 2018. 428–437.Google ScholarDigital Library
- Chaima Jemmali, Carter Ithier, Seth Cooper, and Magy Seif El-Nasr. 2020. Grammar based modular level generator for a programming puzzle game. In Proceedings of the Experimental AI in Games Workshop. 7.Google Scholar
- Istvan Jonyer, Lawrence B. Holder, and Diane J. Cook. 2003. MDL-based context-free graph grammar induction. In Proceedings of the Sixteenth International Florida Artificial Intelligence Research Society Conference.Google Scholar
- Daniel Karavolos, Anders Bouwer, and Rafael Bidarra. 2015. Mixed-initiative design of game levels: integrating mission and space into level generation. Proceedings of the 10th International Conference on the Foundations of Digital Games (2015).Google Scholar
- Isaac Karth and Adam M. Smith. 2017. WaveFunctionCollapse is constraint solving in the wild. In Proceedings of the 12th International Conference on the Foundations of Digital Games. 68:1–68:10.Google ScholarDigital Library
- Isaac Karth and Adam M. Smith. 2019. Addressing the fundamental tension of PCGML with discriminative learning. In Proceedings of the 14th International Conference on the Foundations of Digital Games. 1–9.Google ScholarDigital Library
- Hwanhee Kim, Teasung Hahn, Sookyun Kim, and Shinjin Kang. 2020. Graph based wave function collapse algorithm for procedural content generation in games. IEICE Transactions on Information and Systems E103.D, 8 (2020), 1901–1910.Google Scholar
- Mark H. Liffiton and Jordyn C. Maglalang. 2012. A cardinality solver: more expressive constraints for free. In Theory and Applications of Satisfiability Testing – SAT 2012. 485–486.Google ScholarDigital Library
- Seung-Hwan Lim, Sangkeun Lee, Sarah S. Powers, Mallikarjun Shankar, and Neena Imam. 2016. Survey of approaches to generate realistic synthetic graphs. Technical Report ORNL/TM-2016/3. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). https://www.osti.gov/biblio/1339361Google Scholar
- Roland Linden, Ricardo Lopes, and Rafael Bidarra. 2013. Designing procedurally generated levels. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.Google Scholar
- Santiago Londoño and Olana Missura. 2015. Graph grammars for Super Mario Bros levels. In Sixth FDG Workshop on Procedural Content Generation.Google Scholar
- Abdelrahman Madkour, Stacy Marsella, Casper Harteveld, Magy Seif El-Nasr, and Jan-Willem van de Meent. 2021. Guiding generative graph grammars of dungeon mission graphs via examples. In Experimental AI in Games Workshop.Google Scholar
- Paul Merrell and Dinesh Manocha. 2010. Model synthesis: A general procedural modeling algorithm. IEEE transactions on visualization and computer graphics 17, 6 (2010), 715–728.Google Scholar
- Nintendo. 1985. Super Mario Bros.Game [NES].Google Scholar
- Nintendo. 1986. The Legend of Zelda. Game [NES].Google Scholar
- Jan Overgoor, Austin Benson, and Johan Ugander. 2019. Choosing to grow a graph: modeling network formation as discrete choice. In The World Wide Web Conference. 1409–1420.Google ScholarDigital Library
- Noor Shaker, Julian Togelius, and Mark J. Nelson. 2016. Procedural Content Generation in Games. Springer International Publishing.Google Scholar
- Sam Snodgrass and Santiago Ontañón. 2017. Learning to generate video game maps using Markov models. IEEE Transactions on Computational Intelligence and AI in Games 9, 4 (Dec. 2017), 410–422. Conference Name: IEEE Transactions on Computational Intelligence and AI in Games.Google Scholar
- Adam Summerville, Sam Snodgrass, Matthew Guzdial, Christoffer Holmgård, Amy K. Hoover, Aaron Isaksen, Andy Nealen, and Julian Togelius. 2018. Procedural Content Generation via Machine Learning (PCGML). IEEE Transactions on Games 10, 3 (Sept. 2018), 257–270.Google ScholarCross Ref
- Adam James Summerville, Sam Snodgrass, Michael Mateas, and Santiago Ontañón. 2016. The VGLC: The Video Game Level Corpus. arXiv:1606.07487 [cs] (July 2016).Google Scholar
- Anton Tsitsulin, Benedek Rozemberczki, John Palowitch, and Bryan Perozzi. 2022. Synthetic graph generation to benchmark graph learning. arXiv:2204.01376 [cs].Google Scholar
- Josep Valls-Vargas, Jichen Zhu, and Santiago Ontañón. 2017. Graph grammar-based controllable generation of puzzles for a learning game about parallel programming. In Proceedings of the 12th International Conference on the Foundations of Digital Games. 7:1–7:10.Google ScholarDigital Library
- Vanessa Volz, Niels Justesen, Sam Snodgrass, Sahar Asadi, Sami Purmonen, Christoffer Holmgård, Julian Togelius, and Sebastian Risi. 2020. Capturing local and global patterns in procedural content generation via machine learning. In 2020 IEEE Conference on Games (CoG). 399–406.Google ScholarCross Ref
Index Terms
- Sturgeon-GRAPH: Constrained Graph Generation from Examples
Recommendations
Sturgeon-MKIII: Simultaneous Level and Example Playthrough Generation via Constraint Satisfaction with Tile Rewrite Rules
FDG '23: Proceedings of the 18th International Conference on the Foundations of Digital GamesCompletability is a key aspect of procedural level generation. In this work, we present a constraint-based approach to level generation for 2D tile-based games that simultaneously generates a level and an example playthrough of the level demonstrating ...
On using graph partitioning with isomorphism constraint in procedural content generation
FDG '17: Proceedings of the 12th International Conference on the Foundations of Digital GamesThis paper describes an algorithm to solve the problem of partitioning a planar graph with a constraint on which partitions should be adjacent or nonadjacent. We explore the applications of the algorithm in Procedural Content Generation in games which ...
Overlaying a hypergraph with a graph with bounded maximum degree
AbstractLet G and H be respectively a graph and a hypergraph defined on a same set of vertices, and let F be a fixed graph. We say that G F-overlays a hyperedge S of H if F is a spanning subgraph of the subgraph of G induced by S,...
Comments