Before starting my PhD, I was a visiting student
researcher at the Center for Human-Compatible AI
of the University of California, Berkeley, and before that I received a master’s degree in
Data Science from ETH Zurich.
Before working on machine learning, I received a bachelor’s degree in physics from the University of Cologne,
working on computational condensed matter physics with
Prof. Simon Trebst.
My research has the goal to build robust intelligent systems that interact with the world.
Currently, I am mainly interested in using reinforcement learning (RL) to achieve complex
goals in the real world. RL has been successfully applied to situations with narrow and
well-defined goals, such as in video games; but this is generally not given in the real
world. To address this, I am interested in how RL systems can learn about
complex goals from human feedback.