Hannah Erlebach

About

I'm a first-year DPhil student in machine learning supervised by Jakob Foerster and funded by the Cooperative AI PhD fellowship.

I did my masters in machine learning at University College London, where my thesis was supervised by Tim Rocktaschel, and my undergraduate in maths at Cambridge.

I'm currently thinking about multi-agent learning, communication and theory of mind, bounded rationality and embedded agency, complexity, and active inference - with a view to developing a formal framework for communication and mutual understanding between diverse minds.

Research

Research from before my PhD.

• DUA: Discovering Universal Attacks Using Foundation Models. Master's thesis for UCL MSc in Machine Learning, 2025.
• Guiding Evolution of Artificial Life Using Vision-Language Models. Nikhil Baid, Hannah Erlebach, Paul Hellegouarch and Frederico Wieser. Published in Artificial Life Conference 2025. [arXiv]
• Mitigating Goal Misgeneralisation via Minimax Regret. Karim Abdel Sadek, Matthew Farrugia-Roberts, Usman Anwar, Hannah Erlebach, Christian Schroeder de Witt, David Krueger and Michael Dennis. Published in Reinforcement Learning Conference 2025. [arXiv]
• RACCOON: Regret-based Adaptive Curricula for Cooperation. Hannah Erlebach and Jonathan Cook. Published in CoCoMARL workshop at Reinforcement Learning Conference 2024.
• Welfare Diplomacy: Benchmarking Language Model Cooperation. Gabriel Mukobi, Hannah Erlebach, Niklas Lauffer, Lewis Hammond, Alan Chan and Jesse Clifton. Published in SoLaR workshop at NeurIPS 2023. [arXiv]