Research Projects

Active

Abstract Forward Models for Modern Games

Game AI · Forward Model Learning · Statistical Forward Planning

This project aims to provide the games industry with access to the latest and most proficient Game AI methods. Statistical Forward Planning (SFP) techniques, such as Monte Carlo Tree Search (MCTS) or Rolling Horizon Evolutionary Algorithms (RHEA), have recently achieved remarkable performance in games research.

This project addresses the main reasons behind the small uptake of SFP methods in the games industry: the lack of fast and reliable Forward Models (FM) that can be abstracted for use by SFP algorithms in modern video games. SFP needs an FM to work, but complex models are expensive to use without introducing abstractions or simplifications, which also make the model inaccurate.

Related Publications →

Current Funding

2026–2029

Start Package Grant

Funding by Novo Nordisk Foundation · Role: Principal Investigator

Developing new forms of artificial intelligence that are not only powerful, but also safe, transparent, and easy to use. With this grant, we will be enabling synergies between the University of Southern Denmark, Odense's cluster in Robotics and health sciences. Building these new collaborations in Denmark and beyond will help to turn cutting-edge AI research into real-world tools that benefit society.

Research Project
2022–2026

Abstract Swarm Competition

The Genetic and Evolutionary Computation Conference (GECCO); IEEE Congress on Evolutionary Computation (IEEE CEC) · Role: Co-Organiser

This competition aims to motivate work in the broad field of multi-agent systems and logistics. We have prepared a benchmarking framework which allows the development of multi-agent swarms to process a variety of test environments. Those can be extremely diverse, dynamic and variable of size. The ultimate goal of this competition is to foster comparability of multi-agent systems in logistics-related problems (e. g., in hospital logistics).

Competition

Funding information coming soon

You would like to join a new project or you are searching for collaborators?

I am open to research collaborations, joint grant applications, and industry partnerships. My group has expertise in machine learning, game AI, causal learning, and decision-making under uncertainty, most specifically in areas with broad applicability in game development, robotics, autonomous systems, and industrial process control.

Get in Touch

Past Funding

2022–2025

HybrInt – Hybrid Intelligence through Interpretable AI

Funding by Lower Saxony Ministry of Science and Culture (MWK), through the zukunft.niedersachsen program of the Volkswagen Foundation · Role: Principal Investigator

The aim of this project is to strengthen basic AI research jointly at Leibniz University Hannover and Osnabrück University in the name of hybrid intelligence. The key idea is to combine the strengths of the complementary heterogeneous intelligence of humans and machine: human intelligence is defined by the ability to learn, reason, and interact with the environment based on their knowledge, whereas AI is attributed to machines. This includes tasks, such as language processing, object recognition, model building, and applying that knowledge to solve problems.

Research Project
2018–2020

Hearthstone AI International Research Competition

IEEE Conference on Computational Intelligence and Games (CIG/CoG) · Role: Organiser & Principal Investigator

Organised a three-year international research competition on AI for the collectible card game Hearthstone, advancing the state of the art in game-playing agents and state estimation under partial observability.

Competition
2016–2019

Energy-Optimal Control of Fuel-Fired Power Plants

Cooperation: University of Bremen & Salzgitter AG · Role: Research Associate

Developed machine learning methods for automatic control of industrial power plants under rapidly varying boundary conditions, targeting reduction of external fuel usage and capping of electrical power peaks.

Industry Project