## (closed) Master thesis

in machine learning, hierarchical reinforcement learning, robotics

The Machine Learning Research Lab (MLRL) is looking for a master student (d/f/m) in the domain of machine learning, control and robotics in Munich. The MLRL is part of Volkswagen Group IT and tackles fundamental research in machine learning and optimal control. We develop new methods for generative time series modelling and control of dynamical systems. In a final step, these algorithms are tested on real systems, e.g. robot arms or mobile robots. For this purpose a robot lab with a variety of robotic systems, motion capture systems, a diverse set of sensors and so forth is available.

In this thesis, we want to explore how to solve scenarios that require both high- and low-level
control operating in different frequencies using an hierarchical reinforcement learning framework. For example, consider a robot arm pushing a ball in difficult terrain (e.g. slanted) to a specific position in a maze using only a single finger. On a high level, the controller has to solve a navigation task, but on a low level the interaction while moving the object requires a very fast force feedback control loop such that constant contact with the ball is ensured so that it does not roll away. Analysing existing methods and developing a new algorithm for this type of task will be the focus of this thesis.

Please contact us at arg-min $$\text{@}$$ argmax.ai if you are interested. Mention "control MSc" in your email subject for this particular opening.