Malte Mosbach

Research

Malte Mosbach

I am a PhD student in the Autonomous Intelligent Systems Group at University of Bonn advised by Sven Behnke.

About me

My research aims to make reinforcement learning practical for complex robot control by leveraging foundation models, scaling training, exploring student-teacher learning, developing robust representations, and more. If this excites you, please don't hesitate to reach out.

E-Mail me Connect on LinkedIn
Profile Picture

Selected Publications

A complete, up-to-date list of publications can be found on Google Scholar.

Grasp Anything: Combining Teacher-Augmented Policy Gradient Learning with Instance Segmentation to Grasp Arbitrary Objects

Learning Generalizable Tool Use with Non-rigid Grasp-pose Registration

Efficient Representations of Object Geometry for Reinforcement Learning of Interactive Grasping Policies

Accelerating Interactive Human-like Manipulation Learning with GPU-based Simulation and High-quality Demonstrations

Transfer of Hierarchical Reinforcement Learning Structures for Robotic Manipulation Tasks