research-article

Illuminating diverse neural cellular automata for level generation

Authors:

Matthew C. Fontaine,

Stefanos Nikolaidis,

Julian TogeliusAuthors Info & Claims

GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference

Pages 68 - 76

https://doi.org/10.1145/3512290.3528754

Published: 08 July 2022 Publication History

Abstract

We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels. While NCAs have so far only been trained via supervised learning, we present a quality diversity (QD) approach to generating a collection of NCA level generators. By framing the problem as a QD problem, our approach can train diverse level generators, whose output levels vary based on aesthetic or functional criteria. To efficiently generate NCAs, we train generators via Covariance Matrix Adaptation MAP-Elites (CMA-ME), a quality diversity algorithm which specializes in continuous search spaces. We apply our new method to generate level generators for several 2D tile-based games: a maze game, Sokoban, and Zelda. Our results show that CMA-ME can generate small NCAs that are diverse yet capable, often satisfying complex solvability criteria for deterministic agents. We compare against a Compositional Pattern-Producing Network (CPPN) baseline trained to produce diverse collections of generators and show that the NCA representation yields a better exploration of level-space.

References

[1]

Chad Adams and Sushil Louis. 2017. Procedural maze level generation with evolutionary cellular automata. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 1--8.

[2]

Alberto Alvarez, Steve Dahlskog, Jose Font, and Julian Togelius. 2019. Empowering quality diversity in dungeon design with interactive constrained map-elites. In 2019 IEEE Conference on Games (CoG). IEEE, 1--8.

Digital Library

[3]

L. Cazenille. 2018. QDpy: A Python framework for Quality-Diversity. https://gitlab.com/leo.cazenille/qdpy.

[4]

Bert Wang-Chak Chan. 2020. Lenia and Expanded Universe. In ALIFE 2020: The 2020 Conference on Artificial Life. MIT Press, 221--229.

[5]

Konstantinos Chatzilygeroudis, Antoine Cully, Vassilis Vassiliades, and Jean-Baptiste Mouret. 2020. Quality-Diversity Optimization: a novel branch of stochastic optimization. arXiv preprint arXiv:2012.04322 (2020).

[6]

Tae Jong Choi and Julian Togelius. 2021. Self-Referential Quality Diversity through Differential MAP-Elites. Association for Computing Machinery, New York, NY, USA, 502--509.

Digital Library

[7]

Hugo Cisneros, Josef Sivic, and Tomas Mikolov. 2019. Evolving structures in complex systems. In 2019 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 230--237.

[8]

Cédric Colas, Vashisht Madhavan, Joost Huizinga, and Jeff Clune. 2020. Scaling map-elites to deep neuroevolution. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference. 67--75.

Digital Library

[9]

Edoardo Conti, Vashisht Madhavan, Felipe Petroski Such, Joel Lehman, Kenneth O Stanley, and Jeff Clune. 2018. Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 5032--5043.

[10]

Antoine Cully, Jeff Clune, Danesh Tarapore, and Jean-Baptiste Mouret. 2015. Robots that can adapt like animals. Nature 521, 7553 (2015), 503.

[11]

Omar Delarosa, Hang Dong, Mindy Ruan, Ahmed Khalifa, and Julian Togelius. 2021. Mixed-initiative level design with rl brush. In International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar). Springer, 412--426.

Digital Library

[12]

Sam Earle. 2020. Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scales. In AIIDE Workshops.

[13]

Sam Earle, Maria Edwards, Ahmed Khalifa, Philip Bontrager, and Julian Togelius. 2021. Learning Controllable Content Generators. In 2021 IEEE Conference on Games (COG'21). IEEE.

[14]

Matthew C Fontaine, Ruilin Liu, Ahmed Khalifa, Jignesh Modi, Julian Togelius, Amy K Hoover, and Stefanos Nikolaidis. 2021. Illuminating mario scenes in the latent space of a generative adversarial network. In AAAI Conference on Artificial Intelligence.

[15]

Matthew C Fontaine and Stefanos Nikolaidis. 2021. Differentiable Quality Diversity. arXiv e-prints (2021), arXiv-2106.

[16]

Matthew C Fontaine, Julian Togelius, Stefanos Nikolaidis, and Amy K Hoover. 2020. Covariance matrix adaptation for the rapid illumination of behavior space. In Proceedings of the 2020 genetic and evolutionary computation conference. 94--102.

Digital Library

[17]

Jonathan Frankle and Michael Carbin. 2018. The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635 (2018).

[18]

David Ha. 2016. Generating Abstract Patterns with TensorFlow. hlog.otoro.net (2016). https://blog.otoro.net/2016/03/25/generating-abstract-patterns-with-tensorflow/

[19]

Nikolaus Hansen. 2016. The CMA evolution strategy: A tutorial. arXiv preprint arXiv:1604.00772 (2016).

[20]

Nikolaus Hansen and Andreas Ostermeier. 2001. Completely derandomized self-adaptation in evolution strategies. Evolutionary computation 9, 2 (2001), 159--195.

[21]

Lawrence Johnson, Georgios N Yannakakis, and Julian Togelius. 2010. Cellular automata for real-time generation of infinite cave levels. In Proceedings of the 2010 Workshop on Procedural Content Generation in Games. 1--4.

Digital Library

[22]

Paul Kent and Juergen Branke. 2020. Bop-elites, abayesian optimisation algorithm for quality-diversity search. arXiv preprint arXiv:2005.04320 (2020).

[23]

Manuel Kerssemakers, Jeppe Tuxen, Julian Togelius, and Georgios N Yannakakis. 2012. A procedural procedural level generator generator. In 2012 IEEE Conference on Computational Intelligence and Games (CIG). IEEE, 335--341.

[24]

Ahmed Khalifa, Philip Bontrager, Sam Earle, and Julian Togelius. 2020. Pcgrl: Procedural content generation via reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Vol. 16. 95--101.

[25]

Gustav Larsson, Michael Maire, and Gregory Shakhnarovich. 2016. Fractalnet: Ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016).

[26]

Joel Lehman and Kenneth O Stanley. 2011. Evolving a diversity of virtual creatures through novelty search and local competition. In Proceedings of the 13th annual conference on Genetic and evolutionary computation. 211--218.

Digital Library

[27]

Alexander Mordvintsev, Ettore Randazzo, Eyvind Niklasson, and Michael Levin. 2020. Growing neural cellular automata. Distill 5, 2 (2020), e23.

[28]

Gregory Morse and Kenneth O Stanley. 2016. Simple evolutionary optimization can rival stochastic gradient descent in neural networks. In Proceedings of the Genetic and Evolutionary Computation Conference 2016. 477--484.

[29]

Jean-Baptiste Mouret and Jeff Clune. 2015. Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909 (2015).

[30]

Eyvind Niklasson, Alexander Mordvintsev, Ettore Randazzo, and Michael Levin. 2021. Self-Organising Textures. Distill 6, 2 (2021), e00027--003.

[31]

Maxwell Nye and Andrew Saxe. 2018. Are efficient deep representations learn-able?. In ICLR Workshops.

[32]

Justin K Pugh, Lisa B Soros, and Kenneth O Stanley. 2016. Quality diversity: A new frontier for evolutionary computation. Frontiers in Robotics and AI 3 (2016), 40.

[33]

Justin K Pugh, Lisa B Soros, Paul A Szerlip, and Kenneth O Stanley. 2015. Confronting the challenge of quality diversity. In Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation. 961--974.

Digital Library

[34]

Chris Reinke, Mayalen Etcheverry, and Pierre-Yves Oudeyer. 2019. Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems. In International Conference on Learning Representations.

[35]

Jimmy Secretan, Nicholas Beato, David B D Ambrosio, Adelein Rodriguez, Adam Campbell, and Kenneth O Stanley. 2008. Picbreeder: evolving pictures collaboratively online. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 1759--1768.

Digital Library

[36]

Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. 2020. Implicit neural representations with periodic activation functions. Advances in Neural Information Processing Systems 33 (2020).

[37]

Jacob M Springer and Garrett T Kenyon. 2020. It's Hard for Neural Networks To Learn the Game of Life. arXiv preprint arXiv:2009.01398 (2020).

[38]

Kenneth O Stanley. 2007. Compositional pattern producing networks: A novel abstraction of development. Genetic programming and evolvahle machines 8, 2 (2007), 131--162.

[39]

Kenneth O Stanley and Risto Miikkulainen. 2002. Evolving neural networks through augmenting topologies. Evolutionary computation 10, 2 (2002), 99--127.

[40]

Shyam Sudhakaran, Djordje Grbic, Siyan Li, Adam Katona, Elias Najarro, Claire Glanois, and Sebastian Risi. 2021. Growing 3D Artefacts and Functional Machines with Neural Cellular Automata. In 2021 Conference on Artificial Life. https://arxiv.org/abs/2103.08737

[41]

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 (2018), 257--270.

[42]

Penelope Sweetser and Janet Wiles. 2005. Combining influence maps and cellular automata for reactive game agents. In International Conference on Intelligent Data Engineering and Automated Learning. Springer, 524--531.

Digital Library

[43]

Ended Learning Team, Adam Stooke, Anuj Mahajan, Catarina Barros, Charlie Deck, Jakob Bauer, Jakub Sygnowski, Maja Trebacz, Max Jaderberg, Michael Mathieu, et al. 2021. Open-Ended Learning Leads to Generally Capable Agents. arXiv preprint arXiv:2107.12808 (2021).

[44]

Bryon Tjanaka, Matthew C. Fontaine, Yulun Zhang, Sam Sommerer, Nathan Dennler, and Stefanos Nikolaidis. 2021. pyribs: A bare-bones Python library for quality diversity optimization. https://github.com/icaros-usc/pyribs.

[45]

Stephen Wolfram. 1984. Cellular automata as models of complexity. Nature 311, 5985 (1984), 419--424.

[46]

Georgios N Yannakakis and Julian Togelius. 2011. Experience-driven procedural content generation. IEEE Transactions on Affective Computing 2, 3 (2011), 147--161.

Digital Library

[47]

Hejia Zhang, Matthew Fontaine, Amy Hoover, Julian Togelius, Bistra Dilkina, and Stefanos Nikolaidis. 2020. Video game level repair via mixed integer linear programming. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Vol. 16. 151--158.

Cited By

Earle SKokkinos FNie YTogelius JRaileanu R(2024)DreamCraft: Text-Guided Generation of Functional 3D Environments in MinecraftProceedings of the 19th International Conference on the Foundations of Digital Games10.1145/3649921.3649943(1-15)Online publication date: 21-May-2024
https://dl.acm.org/doi/10.1145/3649921.3649943
Beukman MFokam MKruger MAxelrod GNasir MIngram BRosman BJames S(2024)Hierarchically Composing Level Generators for the Creation of Complex StructuresIEEE Transactions on Games10.1109/TG.2023.329761916:2(459-469)Online publication date: Jun-2024
https://doi.org/10.1109/TG.2023.3297619
Charity MDave IKhalifa ATogelius J(2024)Baba is Y'all 2.0: Design and Investigation of a Collaborative Mixed-Initiative SystemIEEE Transactions on Games10.1109/TG.2022.322352716:1(75-89)Online publication date: Mar-2024
https://doi.org/10.1109/TG.2022.3223527
Show More Cited By

Index Terms

Illuminating diverse neural cellular automata for level generation
1. Computing methodologies
  1. Artificial intelligence
    1. Search methodologies
      1. Continuous space search
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks

Recommendations

Procedural Game Map Generation using Multi-leveled Cellular Automata by Machine learning
ISAIMS '21: Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences

The concept of Procedural Content Generation (PCG) has been intensively applied in the game industry for its capability of producing infinite game maps without any human effort. Innumerable games, such as Minecraft, Terraria, and No Man's Sky, ...
Universal pattern generation by cellular automata

We construct a reversible, one-dimensional cellular automaton that has the property that a finite initial configuration generates all finite patterns over its state alphabet. We also conjecture that a related cellular automaton satisfies the stronger ...
One-dimensional pattern generation by cellular automata
Abstract
To determine the computational capacity of cellular automata they are often investigated towards their ability to accept formal languages within certain time constraints. In this paper, we take up an opposite position and look at cellular automata ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference

July 2022

1472 pages

ISBN:9781450392372

DOI:10.1145/3512290

Editor:
Jonathan E. Fieldsend
University of Exeter
,
General Chair:
Markus Wagner
The University of Adelaide

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGEVO: ACM Special Interest Group on Genetic and Evolutionary Computation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 July 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

GECCO '22

Sponsor:

SIGEVO

GECCO '22: Genetic and Evolutionary Computation Conference

July 9 - 13, 2022

Massachusetts, Boston

Acceptance Rates

Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
386
Total Downloads

Downloads (Last 12 months)123
Downloads (Last 6 weeks)8

Reflects downloads up to 30 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Earle SKokkinos FNie YTogelius JRaileanu R(2024)DreamCraft: Text-Guided Generation of Functional 3D Environments in MinecraftProceedings of the 19th International Conference on the Foundations of Digital Games10.1145/3649921.3649943(1-15)Online publication date: 21-May-2024
https://dl.acm.org/doi/10.1145/3649921.3649943
Beukman MFokam MKruger MAxelrod GNasir MIngram BRosman BJames S(2024)Hierarchically Composing Level Generators for the Creation of Complex StructuresIEEE Transactions on Games10.1109/TG.2023.329761916:2(459-469)Online publication date: Jun-2024
https://doi.org/10.1109/TG.2023.3297619
Charity MDave IKhalifa ATogelius J(2024)Baba is Y'all 2.0: Design and Investigation of a Collaborative Mixed-Initiative SystemIEEE Transactions on Games10.1109/TG.2022.322352716:1(75-89)Online publication date: Mar-2024
https://doi.org/10.1109/TG.2022.3223527
Gašperov BĐurasević MJakobovic D(2024)Leveraging More of Biology in Evolutionary Reinforcement LearningApplications of Evolutionary Computation10.1007/978-3-031-56855-8_6(91-114)Online publication date: 3-Mar-2024
https://dl.acm.org/doi/10.1007/978-3-031-56855-8_6
Zhang YFontaine MBhatt VNikolaidis SLi JOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Arbitrarily scalable environment generators via neural cellular automataProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3668621(57212-57225)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3668621
Beukman MIngram BLiu IRosman BEger MCardona-Rivera R(2023)Hierarchical WaveFunction collapseProceedings of the Nineteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment10.1609/aiide.v19i1.27498(23-33)Online publication date: 8-Oct-2023
https://dl.acm.org/doi/10.1609/aiide.v19i1.27498
Boldi RSpector LSilva SPaquete L(2023)Can the Problem-Solving Benefits of Quality Diversity Be Obtained without Explicit Diversity Maintenance?Proceedings of the Companion Conference on Genetic and Evolutionary Computation10.1145/3583133.3596336(2152-2156)Online publication date: 15-Jul-2023
https://dl.acm.org/doi/10.1145/3583133.3596336
Grillotti LFlageat MLim BCully ASilva SPaquete L(2023)Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain DomainsProceedings of the Genetic and Evolutionary Computation Conference10.1145/3583131.3590498(156-164)Online publication date: 15-Jul-2023
https://dl.acm.org/doi/10.1145/3583131.3590498
Tjanaka BFontaine MLee DZhang YBalam NDennler NGarlanka SKlapsis NNikolaidis SSilva SPaquete L(2023)pyribs: A Bare-Bones Python Library for Quality Diversity OptimizationProceedings of the Genetic and Evolutionary Computation Conference10.1145/3583131.3590374(220-229)Online publication date: 15-Jul-2023
https://dl.acm.org/doi/10.1145/3583131.3590374
Surana SLim BCully A(2023)Efficient Learning of Locomotion Skills through the Discovery of Diverse Environmental Trajectory Generator Priors2023 IEEE International Conference on Robotics and Automation (ICRA)10.1109/ICRA48891.2023.10161267(12134-12141)Online publication date: 29-May-2023
https://doi.org/10.1109/ICRA48891.2023.10161267
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents