View, browse and sort the ever-growing list of sessions by day, pass type, topic, and format. With this Session Viewer, you can view GDC 2023 session details and speakers, and share your favorites via social media. You will be able to build your schedule and access it during the show via export or Mobile App, once live. Sessions do fill up and seating is first come, first serve, so arrive early to sessions that you would like to attend.
Seth Cooper (Associate Professor, Northeastern University)
Location: Room 2002, West Hall
Date: Tuesday, March 21
Time: 3:00 pm - 3:30 pm
Pass Type: All Access Pass, Summits Pass
Topic: Programming
Format: Lecture
Vault Recording: Video
Audience Level: All
In this presentation, Seth Cooper, Associate Professor at Northeastern University, will demonstrate how general constraint solvers can enable highly controllable tile map level generation and editing. Constraint solving allows designers to specify what they want in their levels, rather than needing to determine how to achieve it with hand-coded algorithms.
Seth will discuss a system that leverages state-of-the-art constraint solving techniques to generate and edit levels incorporating a variety of constraints. These include: constraints learned from example levels, constraints on what should be in a level and where it should be, and goal reachability constraints.
He will demonstrate the system in several games and show applications ranging from infilling and repair to generating diverse sets of levels. He will also discuss more recent and ongoing work using the system to blend features of different games, model more complex mechanics via constraints to create playability examples, and generate graph structures.
Attendees will learn about how constraint solvers can be applied to level generation and editing, and will gain insight into how design rules can be encoded into constraint satisfaction problems and how it might be applied to games they are working on.
This is for developers and designers interested in level generation and constraint solving.