Usage
  • 46 views
  • 66 downloads

Accessible Game Development Via Symbolic Learning Program Synthesis

  • Author / Creator
    Sumner, Megan J.
  • Video game development is a highly technical practice that traditionally requires programming skills. This serves as a barrier to entry for would-be developers or those hoping to use games as part of their creative expression. While there have been prior game development tools focused on accessibility, they generally still require programming knowledge, or have major limitations in terms of the kinds of games they can make.

    In this thesis we introduce Mechanic Maker, a tool for creating a wide-range of game mechanics without programming. Game mechanics are defined as the basic activities in the game and the rules that govern them, for example, a character moving on screen due to input given on the keyboard. Instead of requiring programming to create game mechanics, Mechanic Maker relies on a backend symbolic learning system to synthesize game mechanics from examples. We conducted a user study to evaluate the benefits of the tool for participants with a variety of programming and game development experience. Our results suggested that participants' ability to use the tool was unrelated to their level of programming ability.

    We also explore how we can leverage data from the user study to create a database of learned rules. This database allowed us to create a Gaussian Mixture Model, which we use in a case-based reasoning system to attempt to speed up mechanic creation.

    We conclude that tools like ours could help democratize game development by making the practice accessible regardless of programming skills. Additionally, the usability assessment of Mechanic Maker showed that users could effectively use the tool. Finally, we determine that the case-based reasoning approach has the potential to speed up mechanic creation, but further work needs to be done to reduce user friction in Mechanic Maker.

  • Subjects / Keywords
  • Graduation date
    Fall 2024
  • Type of Item
    Thesis
  • Degree
    Master of Science
  • DOI
    https://doi.org/10.7939/r3-at5b-5v42
  • License
    This thesis is made available by the University of Alberta Library with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.