SEED Research & Announcements Blogs Publications Open Source Careers Contact Us Research & Announcements Blogs Publications Open Source Careers Contact Us

Re•Work 2021: Augmenting Automated Game Testing with Deep Reinforcement Learning

Machine Learning

SEED’s own Linus Gisslén presented this talk at Re•Work 2021 on January 29, 2021, during the Deep Learning 2.0 Virtual Summit.

Game testing is slow and expensive, and is becoming even more so as games grow in size and complexity. Typical approaches such as scripted bots are effective for some tasks but aren’t dynamic enough to fully test modern AAA games.

SEED is looking into using ML to extend the scope of game testing. In this talk, Linus describes our efforts to use deep reinforcement learning to improve automated testing of games.

Linus Gisslén is a senior research engineer in machine learning at SEED. His current research focus is on reinforcement learning (RL) and procedurally-generated content (PCG).

Check out all the events and find out more about Re•Work 2021.

Watch the video of the presentation below.

Download the Presentation Slides

Download the presentation slides as PDF (6 MB).

 

Related News

Gigi Lightning Talks

SEED
Sep 26, 2024
SEED brought together developers to show off their prowess using the Gigi rapid prototyping platform for real-time rendering.

SEED's Adventure in Gameplay Innovation

SEED
Sep 13, 2024
SEED is branching out into the world of game mechanics, storytelling magic, and interactive wonders.

Objective Metrics for Evalutating Gesture Generation are Almost Useless

SEED
Sep 10, 2024
How do you evaluate something as subjective and ephemeral as human body language for natural and lifelike qualities?