More Web Proxy on the site http://driver.im/

research-article

Open access

Addressing the fundamental tension of PCGML with discriminative learning

Authors:

Adam M. SmithAuthors Info & Claims

FDG '19: Proceedings of the 14th International Conference on the Foundations of Digital Games

Article No.: 89, Pages 1 - 9

https://doi.org/10.1145/3337722.3341845

Published: 26 August 2019 Publication History

Abstract

Procedural content generation via machine learning (PCGML) is typically framed as the task of fitting a generative model to full-scale examples of a desired content distribution. This approach presents a fundamental tension: the more design effort expended to produce detailed training examples for shaping a generator, the lower the return on investment from applying PCGML in the first place. In response, we propose the use of discriminative models, which capture the validity of a design rather the distribution of the content, trained on positive and negative example design fragments. Through a modest modification of WaveFunctionCollapse, a commercially-adopted PCG approach that we characterize as using elementary machine learning, we demonstrate a new mode of control for learning-based generators. We demonstrate how an artist might craft a focused set of additional positive and negative design fragments by critique of the generator's previous outputs. This interaction mode bridges PCGML with mixed-initiative design assistance tools by working with a machine to define a space of valid designs rather than just one new design.

References

[1]

Francois Chollet. 2017. Deep Learning with Python (1st ed.). Manning Publications Co., Greenwich, CT, USA.

Digital Library

[2]

Alexei A. Efros and William T. Freeman. 2001. Image Quilting for Texture Synthesis and Transfer. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '01). ACM, New York, NY, USA, 341--346.

Digital Library

[3]

Alexei A Efros and Thomas K Leung. 1999. Texture synthesis by non-parametric sampling. In Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, Vol. 2. IEEE, IEEE Computer Society, 1999, 1033--1038.

Digital Library

[4]

Mathieu Fehr and Nathanaël Courant. 2018. fast-wfc. https://github.com/math-fehr/fast-wfc, GitHub repository (2018).

[5]

David Donovan Garber. 1981. Computational Models for Texture Analysis and Texture Synthesis. Ph.D. Dissertation. University of Southern California, Los Angeles, CA, USA. AAI0551115.

[6]

Martin Gebser, Roland Kaminski, Benjamin Kaufmann, and Torsten Schaub. 2014. Clingo = ASP + Control: Preliminary Report. CoRR abs/1405.3694 (2014).

[7]

Jason Grinblat and Charles B. Bucklew. 2010. Caves of Qud. (2010).

[8]

Maxim Gumin. 2017. WaveFunctionCollapse Readme.md. (18 May 2017). Retrieved May 20, 2017 from https://github.com/mxgmn/WaveFunctionCollapse/blob/master/README.md

[9]

Matthew Guzdial, Nicholas Liao, and Mark Riedl. 2018. Co-Creative Level Design via Machine Learning. In The 5th Experimental AI in Games Workshop (EXAG). http://ceur-ws.org/Vol-2282/EXAG_126.pdf

[10]

Matthew Guzdial, Joshua Reno, Jonathan Chen, Gillian Smith, and Mark Riedl. 2018. Explainable PCGML via Game Design Patterns. In The 5th Experimental AI in Games Workshop(EXAG). http://ceur-ws.org/Vol-2282/EXAG_107.pdf

[11]

Paul Francis Harrison. 2006. Image Texture Tools: Texture Synthesis, Texture Transfer, and Plausible Restoration. Monash University. 95--117 pages.

[12]

Aaron Hertzmann, Charles E Jacobs, Nuria Oliver, Brian Curless, and David H Salesin. 2001. Image analogies. In Proceedings of the 28th annual conference on Computer graphics and interactive techniques. ACM, 327--340.

Digital Library

[13]

Rishabh Jain, Aaron Isaksen, Christoffer Holmgård, and Julian Togelius. 2016. Autoencoders for level generation, repair, and recognition. In Proceedings of the ICCC Workshop on Computational Creativity and Games.

[14]

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 (FDG '17). ACM, New York, NY, USA, Article 68, 10 pages.

Digital Library

[15]

Antonios Liapis, Gillian Smith, and Noor Shaker. 2016. Mixed-initiative content creation. In Procedural Content Generation in Games: A Textbook and an Overview of Current Research, Noor Shaker, Julian Togelius, and Mark J. Nelson (Eds.). Springer, 195--216.

[16]

Antonios Liapis, Georgios N Yannakakis, and Julian Togelius. 2013. Sentient Sketchbook: Computer-aided game level authoring. In FDG. 213--220.

[17]

A. Liapis, G. N. Yannakakis, and J. Togelius. 2014. Designer modeling for Sentient Sketchbook. In 2014 IEEE Conference on Computational Intelligence and Games. 1--8.

[18]

P. Merrell and D. Manocha. 2011. Model Synthesis: A General Procedural Modeling Algorithm. IEEE Transactions on Visualization and Computer Graphics 17, 6 (June 2011), 715--728.

Digital Library

[19]

K. R. Muller, S. Mika, G. Ratsch, K. Tsuda, and B. Scholkopf. 2001. Anintroduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks 12, 2 (Mar 2001), 181--201.

Digital Library

[20]

Joseph Osborn, Adam Summerville, and Michael Mateas. 2017. Automatic Mapping of NES Games with Mappy. In Proceedings of the 12th International Conference on the Foundations of Digital Games (FDG '17). ACM, New York, NY, USA, Article 78, 9 pages.

Digital Library

[21]

Gordon D Plotkin. 1971. A further note on inductive generalization. Machine intelligence 6, 101--124 (1971).

[22]

Stuart J. Russell and Peter Norvig. 2016. Artificial Intelligence: A Modern Approach (3 ed.). Pearson Education.

Digital Library

[23]

Dominik Sacha, Michael Sedlmair, Leishi Zhang, John A. Lee, Jaakko Peltonen, Daniel Weiskopf, Stephen C. North, and Daniel A. Keim. 2017. What you see is what you can change: Human-centered machine learning by interactive visualization. Neurocomputing 268 (2017), 164 -- 175. Advances in artificial neural networks, machine learning and computational intelligence.

Digital Library

[24]

Anurag Sarkar and Seth Cooper. 2018. Blending Levels from Different Games using LSTMs. In The 5th Experimental AI in Games Workshop (EXAG). http://ceur-ws.org/Vol-2282/EXAG_125.pdf

[25]

R. M. Smelik, T. Tutenel, K. J. De Kraker, and R. Bidarra. 2011. Semantic 3D Media and Content: A Declarative Approach to Procedural Modeling of Virtual Worlds. Comput. Graph. 35, 2 (April 2011), 352--363.

Digital Library

[26]

Gillian Smith, Jim Whitehead, and Michael Mateas. 2011. Tanagra: Reactive planning and constraint solving for mixed-initiative level design. IEEE Transactions on Computational Intelligence and AI in Games 3, 3 (2011), 201--215.

[27]

Sam Snodgrass. 2018. Markov Models for Procedural Content Generation. Ph.D. Dissertation. Drexel University.

[28]

Sam Snodgrass and Santiago Onta non. 2016. An Approach to Domain Transfer in Procedural Content Generation of Two-Dimensional Videogame Levels. (2016). https://aaai.org/ocs/index.php/AIIDE/AIIDE16/paper/view/13985

[29]

Sam Snodgrass and Santiago Ontanon. 2015. A hierarchical MDMC approach to 2D video game map generation. In Eleventh Artificial Intelligence and Interactive Digital Entertainment Conference.

[30]

Sam Snodgrass, Adam Summerville, and Santiago Ontañón. 2017. Studying the Effects of Training Data on Machine Learning-Based Procedural Content Generation. In Proceedings of the Thirteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-17). 122--128.

[31]

Oskar Stålberg, Richard Meredith, and Martin Kvale. 2018. Bad North. (2018). Plausible Concept.

[32]

Adam Summerville and Michael Mateas. 2016. Super Mario as a String: Platformer Level Generation Via LSTMs. CoRR abs/1603.00930 (2016). arXiv:1603.00930 http://arxiv.org/abs/1603.00930

[33]

Adam Summerville, Sam Snodgrass, Matthew Guzdial, Christoffer Holmgård, Amy K. Hoover, Aaron Isaksen, Andy Nealen, and Julian Togelius. 2017. Procedural Content Generation via Machine Learning (PCGML). CoRR abs/1702.00539 (2017). arXiv:1702.00539 http://arxiv.org/abs/1702.00539

[34]

Adam James Summerville, Sam Snodgrass, Michael Mateas, and Santiago Onta n'on Villar. 2016. The VGLC: The Video Game Level Corpus. Proceedings of the 7th Workshop on Procedural Content Generation (2016).

[35]

Adam James Summerville, Sam Snodgrass, Michael Mateas, and Santi Ontañón Villar. 2016. The VGLC: The Video Game Level Corpus. CoRR abs/1606.07487 (2016). arXiv:1606.07487 http://arxiv.org/abs/1606.07487

[36]

Vanessa Volz, Jacob Schrum, Jialin Liu, Simon M Lucas, Adam Smith, and Sebastian Risi. 2018. Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network. arXiv preprint arXiv:1805.00728 (2018).

Digital Library

[37]

Vanessa Volz, Jacob Schrum, Jialin Liu, Simon M. Lucas, Adam M. Smith, and Sebastian Risi. 2018. Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2018). ACM, New York, NY, USA, 8.

Digital Library

Cited By

Alaka SBidarra R(2024)Mixed-initiative generation of virtual worlds - a comparative study on the cognitive load of WFC and HSWFCProceedings of the 19th International Conference on the Foundations of Digital Games10.1145/3649921.3659852(1-8)Online publication date: 21-May-2024
https://dl.acm.org/doi/10.1145/3649921.3659852
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
Earle SJiang ZTogelius J(2024)Scaling, Control and Generalization in Reinforcement Learning Level Generators2024 IEEE Conference on Games (CoG)10.1109/CoG60054.2024.10645598(1-8)Online publication date: 5-Aug-2024
https://doi.org/10.1109/CoG60054.2024.10645598
Show More Cited By

Index Terms

Addressing the fundamental tension of PCGML with discriminative learning

Recommendations

Deep learning for procedural content generation
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, ...
Discriminative learning can succeed where generative learning fails

Generative algorithms for learning classifiers use training data to separately estimate a probability model for each class. New items are classified by comparing their probabilities under these models. In contrast, discriminative learning algorithms try ...
Transductive Multilabel Learning via Label Set Propagation

The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

FDG '19: Proceedings of the 14th International Conference on the Foundations of Digital Games

August 2019

822 pages

ISBN:9781450372176

DOI:10.1145/3337722

Conference Chair:
Sebastian Deterding
University of York
,
General Chair:
Foaad Khosmood
California Polytechnic State University
,
Program Chairs:
Johanna Pirker
Graz University of Technology
,
Thomas Apperley
CEGCS Tampere University

Copyright © 2019 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].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 26 August 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

FDG '19

FDG '19: The Fourteenth International Conference on the Foundations of Digital Games

August 26 - 30, 2019

California, San Luis Obispo, USA

Acceptance Rates

FDG '19 Paper Acceptance Rate 46 of 124 submissions, 37%;

Overall Acceptance Rate 152 of 415 submissions, 37%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

19
Total Citations
View Citations
567
Total Downloads

Downloads (Last 12 months)128
Downloads (Last 6 weeks)11

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Alaka SBidarra R(2024)Mixed-initiative generation of virtual worlds - a comparative study on the cognitive load of WFC and HSWFCProceedings of the 19th International Conference on the Foundations of Digital Games10.1145/3649921.3659852(1-8)Online publication date: 21-May-2024
https://dl.acm.org/doi/10.1145/3649921.3659852
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
Earle SJiang ZTogelius J(2024)Scaling, Control and Generalization in Reinforcement Learning Level Generators2024 IEEE Conference on Games (CoG)10.1109/CoG60054.2024.10645598(1-8)Online publication date: 5-Aug-2024
https://doi.org/10.1109/CoG60054.2024.10645598
Coutinho FChaimowicz L(2024)Pixel art character generation as an image-to-image translation problem using GANsGraphical Models10.1016/j.gmod.2024.101213132(101213)Online publication date: Apr-2024
https://doi.org/10.1016/j.gmod.2024.101213
Todd GEarle SNasir MGreen MTogelius J(2023)Level Generation Through Large Language ModelsProceedings of the 18th International Conference on the Foundations of Digital Games10.1145/3582437.3587211(1-8)Online publication date: 12-Apr-2023
https://dl.acm.org/doi/10.1145/3582437.3587211
Cooper SHalina EZhu JGuzdial M(2023)Re-trainable Procedural Level Generation via Machine Learning (RT-PLGML) as Game MechanicProceedings of the 18th International Conference on the Foundations of Digital Games10.1145/3582437.3587210(1-3)Online publication date: 12-Apr-2023
https://dl.acm.org/doi/10.1145/3582437.3587210
Alaka SBidarra R(2023)Hierarchical Semantic Wave Function CollapseProceedings of the 18th International Conference on the Foundations of Digital Games10.1145/3582437.3587209(1-10)Online publication date: 12-Apr-2023
https://dl.acm.org/doi/10.1145/3582437.3587209
Cooper S(2023)Sturgeon-GRAPH: Constrained Graph Generation from ExamplesProceedings of the 18th International Conference on the Foundations of Digital Games10.1145/3582437.3582465(1-9)Online publication date: 12-Apr-2023
https://dl.acm.org/doi/10.1145/3582437.3582465
Bateni BKarth ISmith A(2023)Better Resemblance without Bigger Patterns: Making Context-sensitive Decisions in WFCProceedings of the 18th International Conference on the Foundations of Digital Games10.1145/3582437.3582441(1-11)Online publication date: 12-Apr-2023
https://dl.acm.org/doi/10.1145/3582437.3582441
Lai GLeymarie FLatham W(2022)On Mixed-Initiative Content Creation for Video GamesIEEE Transactions on Games10.1109/TG.2022.317621514:4(543-557)Online publication date: Dec-2022
https://doi.org/10.1109/TG.2022.3176215
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

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

Media

Figures

Other

Tables

View Table of Contents