GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of GDC sessions by time, pass type, topic, and format. With GDC Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App, once live.

If you've registered for GDC, you can use the same login credentials for your Session Scheduler account. Adding a session to your schedule does not guarantee you a seat. Sessions do fill up, so please arrive early to sessions that you would like to attend.

AI Summit: Adapting PvP Matchmaking Systems for Player-Versus-Level Dynamic Difficulty

Seth Cooper (Assistant Professor, Northeastern University)

Location: Room 2002, West Hall

Date: Monday, March 16

Time: 2:10pm - 2:40pm

Pass Type: All Access Pass, Core+Summits Pass, Summits Pass - Get your pass now!

Topic: Programming

Format: Session

Vault Recording: TBD

Audience Level: All

PvP matchmaking, based on rating systems like Elo, Glicko, and TrueSkill, is widely used for finding player matches in
multiplayer games. This session will cover how PvP matchmaking can be applied to player-versus-level (PvL) matchmaking: finding a good level for a player to play next. When a player attempts a level, we treat it as a match. Then we can use PvP systems as PvL systems, and simultaneously estimate the skill of players and the difficulty of levels. Matchmaking can then find
levels of appropriate difficulty for each player, to provide them with a challenge that adapts to their skill.

PvL matchmaking can be useful for games with many levels that players can progress through in a non-linear order.
Since PvL matchmaking estimates level difficulty, it can be used where levels are not hand-crafted by the designer,
such as in the case of procedurally or user generated levels, or levels imported from other sources.


Attendees will learn about how player-versus-player matchmaking systems can be adapted for player-versus-level matchmaking. Attendees will gain some insight into how this approach can help improve player retention and success, and how it might be applied to games they are working on.

Intended Audience

Game developers and designers who are interested in automated techniques for level ordering and dynamic difficulty adjustment. Familiarity with existing player rating and matchmaking systems is beneficial, but not required.