I am doing a PhD in the field of machine learning and robotics. I work in the empirical inference department and my supervisor is Jan Peters. Our aim is to build reinforcement learning algorithms that can learn control policies for complex robotics tasks such as robot table tennis. For that we need to include as much prior knowledge as possible into our models, since experiments on the real robot are usually expensive.
My interest are mostly in machine learning, reinforcement learning and Bayesian inference. But I also like algorithms and math, and before coming to the MPI I used to participate in competitions on these topics.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems