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: 'Angry Birds Dream Blast': Keeping It Fun with Deep Reinforcement Learning

Asko Relas (Senior Data Engineer, Rovio Entertainment)

Location: Room 2002, West Hall

Date: Tuesday, March 17

Time: 3:00pm - 3:30pm

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

Topic: Programming

Format: Session

Vault Recording: TBD

Audience Level: Intermediate

Rovio's Games Technology team have been using machine learning-focused technology in their award winning casual matching puzzle game, Angry Birds Dream Blast. They have used machine learning methods to streamline the game development process for level design and game design.

In his talk, Asko will present the work the team has done, employing deep reinforcement learning to estimate Angry Birds Dream Blast levels on the basis of difficulty and churn. By predicting difficulty and churn already during the content development process, they are creating better game experiences in Angry Birds Dream Blast by putting more fun levels in front of players, and reducing the time spent playtesting levels by hand.

Takeaway

Through using reinforcement learning agents, game developers are able to predict the difficulty and expected churn of unreleased levels, allowing them to create more engaging content with less time spent playtesting.

Intended Audience

The presentation will provide insights for machine learning developers especially, but also game producers, game designers, and others interested in applying machine learning to the game design and production process.