Dominik Jeurissen

Queen Mary University of London

I have always been fascinated by automating complex tasks. As a result, my bachelor's focused on software development paired with applied mathematics, and my master's focused on Artificial Intelligence. I'm particularly interested in reinforcement learning (RL) and continual learning. With the recent hype around large language models (LLMs), I am now focusing on utilizing LLMs to play games. I spent much of my free time playing board games with friends, jogging, cooking, and learning new things.

A description of Dominik's research:

Playtesting Games with Large Language Models

With tight deadlines and a constantly evolving game, properly testing a game is challenging. Using AI agents to simplify this work sounds promising, but machine learning is often too slow, and manually implementing the agents takes time. As such, one particularly exciting application for QA is to use Large Language Models (LLMs) as zero-shot game-playing agents. 

LLM-based agents can play games without pre-training, making them a valuable asset for testing a constantly changing game. But how well do they play games? What are their strengths, and what do they struggle with? My research focuses on answering these questions and more.