Hannah Erlebach
Incoming DPhil in Machine Learning @ Oxford
London · UK
About
I’m an MSc student in Machine Learning at UCL and will be starting a DPhil at Oxford supervised by Jakob Foerster in October 2025, with full funding from the Cooperative AI PhD Fellowship. My research focuses on the intersection of AI safety, multi-agent systems and open-endedness.
You can contact me at hannah [dot] erlebach [at] gmail [dot] com.
Research
I'm currently working on open-ended techniques for automatically red-teaming LLMs. My previous research has focused on cooperation in language models and multi-agent reinforcement learning settings.
- 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]