Toward Designer Modeling Through Design Style Clustering

We propose modeling designer style in mixedinitiative game content creation tools as archetypical design traces. These design traces are formulated as transitions between design styles; these design styles are in turn found through clustering all intermediate designs along the way to making a complete design. This method is implemented in the Evolutionary Dungeon Designer, a research platform for mixed-initiative systems to create roguelike games. We present results both in the form of design styles for rooms, which can be analyzed to better understand the kind of rooms designed by users, and in the form of archetypical sequences between these rooms. We further discuss how the results here can be used to create stylesensitive suggestions. Such suggestions would allow the system to be one step ahead of the designer, offering suggestions for the next cluster, assuming that the designer will follow one of the archetypical design traces.

[1]  J. Togelius,et al.  PCGRL: Procedural Content Generation via Reinforcement Learning , 2020, AIIDE.

[2]  Alberto Alvarez,et al.  Learning the Designer's Preferences to Drive Evolution , 2020, EvoApplications.

[3]  Vishwa Shah,et al.  Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators , 2019, CHI.

[4]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[5]  Antonios Liapis,et al.  Your Gameplay Says It All: Modelling Motivation in Tom Clancy’s The Division , 2019, 2019 IEEE Conference on Games (CoG).

[6]  Matthew Guzdial,et al.  Co-Creative Level Design via Machine Learning , 2018, AIIDE Workshops.

[7]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[8]  Alessandro Canossa,et al.  Towards a Procedural Evaluation Technique: Metrics for Level Design , 2015, FDG.

[9]  Julian Togelius,et al.  Generating Map Sketches for Strategy Games , 2013, EvoApplications.

[10]  Julian Togelius,et al.  Search-Based Procedural Content Generation: A Taxonomy and Survey , 2011, IEEE Transactions on Computational Intelligence and AI in Games.

[11]  Fast Game Content Adaptation Through Bayesian-based Player Modelling , 2021, 2021 IEEE Conference on Games (CoG).

[12]  Julian Togelius,et al.  Designer modeling for Sentient Sketchbook , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[13]  Michael Mateas,et al.  Tanagra: Reactive Planning and Constraint Solving for Mixed-Initiative Level Design , 2011, IEEE Transactions on Computational Intelligence and AI in Games.

[14]  Jichen Zhu,et al.  Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation , 2018, 2018 IEEE Conference on Computational Intelligence and Games (CIG).

[15]  Julian Togelius,et al.  Pitako - Recommending Game Design Elements in Cicero , 2019, 2019 IEEE Conference on Games (CoG).

[16]  Eric D. Ragan,et al.  The Effects of Meaningful and Meaningless Explanations on Trust and Perceived System Accuracy in Intelligent Systems , 2019, HCOMP.

[17]  Antonios Liapis,et al.  SuSketch: Surrogate Models of Gameplay as a Design Assistant , 2021, IEEE Transactions on Games.

[18]  Corbeil-Essonnes The Legend of Zelda , 2011 .

[19]  Julian Togelius,et al.  Interactive Constrained MAP-Elites Analysis and Evaluation of the Expressiveness of the Feature Dimensions , 2020, ArXiv.

[20]  Julian Togelius,et al.  Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-Elites , 2019, 2019 IEEE Conference on Games (CoG).

[21]  Antonios Liapis,et al.  I Feel I Feel You: A Theory of Mind Experiment in Games , 2020, KI - Künstliche Intelligenz.

[22]  Julian Togelius,et al.  Ropossum: An Authoring Tool for Designing, Optimizing and Solving Cut the Rope Levels , 2013, AIIDE.

[23]  Boyang Li,et al.  Story Generation with Crowdsourced Plot Graphs , 2013, AAAI.

[24]  G. Dreifuss The Binding of Isaac , 1975 .

[25]  Matthew Guzdial,et al.  Explainable PCGML via Game Design Patterns , 2018, AIIDE Workshops.

[26]  Daniele Gravina,et al.  Modelling the Quality of Visual Creations in Iconoscope , 2019, GALA.

[27]  Antonios Liapis,et al.  Mixed-initiative content creation , 2016 .

[28]  Georgios N. Yannakakis,et al.  Player modeling using self-organization in Tomb Raider: Underworld , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[29]  Alberto Alvarez,et al.  Fostering creativity in the mixed-initiative evolutionary dungeon designer , 2018, FDG.

[30]  Steve Dahlskog,et al.  Towards pattern-based mixed-initiative dungeon generation , 2017, FDG.

[31]  Georgios N. Yannakakis,et al.  Artificial General Intelligence in Games: Where Play Meets Design and User Experience (NII Shonan Meeting 130) , 2019, NII Shonan Meet. Rep..

[32]  Jichen Zhu,et al.  Interactive Visualizer to Facilitate Game Designers in Understanding Machine Learning , 2019, CHI Extended Abstracts.

[33]  Julian Togelius,et al.  Talakat: bullet hell generation through constrained map-elites , 2018, GECCO.

[34]  Matthew Guzdial,et al.  Game Level Generation from Gameplay Videos , 2021, AIIDE.

[35]  Julian Togelius,et al.  Procedural Content Generation via Machine Learning (PCGML) , 2017, IEEE Transactions on Games.

[36]  Todd Lubart,et al.  How can computers be partners in the creative process: Classification and commentary on the Special Issue , 2005, Int. J. Hum. Comput. Stud..

[37]  J. Togelius,et al.  Baba is Y’all: Collaborative Mixed-Initiative Level Design , 2020, 2020 IEEE Conference on Games (CoG).

[38]  Julian Togelius,et al.  Designer Modeling for Personalized Game Content Creation Tools , 2021, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

[39]  Julian Togelius,et al.  Automated Playtesting With Procedural Personas Through MCTS With Evolved Heuristics , 2018, IEEE Transactions on Games.

[40]  Mark O. Riedl,et al.  Learning Player Tailored Content From Observation: Platformer Level Generation from Video Traces using LSTMs , 2021, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

[41]  Been Kim,et al.  Considerations for Evaluation and Generalization in Interpretable Machine Learning , 2018 .

[42]  Julian Togelius,et al.  Towards automatic personalised content creation for racing games , 2007, 2007 IEEE Symposium on Computational Intelligence and Games.

[43]  Julian Togelius,et al.  Experience-Driven Procedural Content Generation , 2011, IEEE Transactions on Affective Computing.