Hello!

I am a PhD student at the Max Planck Institute for Intelligent Systems and the University of Tübingen, advised by Claire Vernade and Michael Muehlebach.

My research focuses on the theoretical foundations of reinforcement learning (RL). I am particularly interested in understanding the potentials and limitations of RL in large, open-ended, and partially observable environments. During my PhD, I have developed novel algorithms and theoretical analyses for reactive reinforcement learning, learning with recurrent memory, and reinforcement learning without observations, among others. I am also interested in the intersections of machine learning with other disciplines, such as control theory and algorithmic information theory.

This fall, I will be visiting the University of Alberta to work with Martha White on actor-critic algorithms. At the beginning of my PhD, I interned at Google Research in Paris, where I worked on applying RL and graph neural networks to solve logistics problems. I did my master’s degree in machine learning at the University of Tübingen, where I worked with Georg Martius (at MPI-IS) on colored noise exploration in RL. Before that, I studied electrical engineering and computer science at the University of Duisburg-Essen, where I worked with Torsten Zesch on low-resource automatic speech recognition and at Siemens on operational forecasting for power plants.

I am currently looking for postdoc positions starting mid-2027.