Dominik Jeurissen

Queen Mary University of London

Dominik holds an MSc in Artificial Intelligence from Maastricht University and a BSc in Computer Science with a focus on Applied Mathematics from RWTH Aachen. During his undergraduate studies, he worked for 3 years as a software engineer at INFORM GmbH, contributing to their supply management software, add*ONE.

His long-term goal is to develop fully autonomous agents that can act in complex environments while continually improving themselves. As a result, he is familiar with many related fields, including reinforcement learning, continual learning, large language models (LLMs), and imitation learning.

A description of Dominik's research:

"My PhD is a collaboration with Creative Assembly, focusing on researching AI for complex strategy games, such as Total War. With the recent rise of Large Language Models (LLMs), I'm exploring their potential to enhance game-playing agents. LLMs can instantly recall knowledge on almost any topic, perform basic reasoning, and are easily configured for a wide range of text-based tasks. These abilities make them especially promising for game development, where machine learning agents often struggle due to constantly changing game environments.

During an internship at Creative Assembly, I worked together with the Creative Assembly's R&D team and NVIDIA to develop a prototype for an Onboarding Assistant that aims to help players when they are stuck in the game. My current research aims to improve the assistant by exploring systems for retrieving dynamic gamestate information."