Interactive Visualizer to Facilitate Game Designers in Understanding Machine Learning

Machine Learning (ML) is a useful tool for modern game designers but often requires a technical background to understand. This gap of knowledge can intimidate less technical game designers from employing ML techniques to evaluate designs or incorporate ML into game mechanics. Our research aims to bridge this gap by exploring interactive visualizations as a way to introduce ML principles to game designers. We have developed QUBE, an interactive level designer that shifts ML education into the context of game design. We present QUBE's interactive visualization techniques and evaluation through two expert panels (n=4, n=6) with game design, ML, and user experience experts.

[1]  Ian H. Witten,et al.  Interactive machine learning: letting users build classifiers , 2002, Int. J. Hum. Comput. Stud..

[2]  Michèle Sebag,et al.  Extreme compass and Dynamic Multi-Armed Bandits for Adaptive Operator Selection , 2009, 2009 IEEE Congress on Evolutionary Computation.

[3]  Phillip Coleman.  Ethics, Online Learning and Stakeholder Responsibility for a Code of Conduct in Higher Education , 2012 .

[4]  Julian Togelius,et al.  AI-based playtesting of contemporary board games , 2017, FDG.

[5]  Julian Togelius,et al.  Artificial Intelligence and Games , 2018, Springer International Publishing.

[6]  Julian Togelius,et al.  Evolving Game Skill-Depth using General Video Game AI agents , 2017, 2017 IEEE Congress on Evolutionary Computation (CEC).

[7]  Damiano Distante,et al.  Interactive Visualization Tools to Improve Learning and Teaching in Online Learning Environments , 2016, Int. J. Distance Educ. Technol..

[8]  Dino Schweitzer,et al.  Designing interactive visualization tools for the graphics classroom , 1992, SIGCSE '92.

[9]  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).

[10]  Martin Wattenberg,et al.  GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation , 2018, IEEE Transactions on Visualization and Computer Graphics.

[11]  D. R. Paulson,et al.  Active Learning in the College Classroom. , 1998 .

[12]  Desney S. Tan,et al.  EnsembleMatrix: interactive visualization to support machine learning with multiple classifiers , 2009, CHI.

[13]  Michael Mateas,et al.  Computational Support for Play Testing Game Sketches , 2009, AIIDE.

[14]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[15]  Ian H. Witten,et al.  WEKA: a machine learning workbench , 1994, Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference.