Manuel Wendl

About Me

I’m a Master’s student in Robotics at ETH Zurich, working on principled reinforcement learning (RL) algorithms, focusing on robustness, safety, and optimism in uncertain environments. My research aims to bridge theoretical rigor with real-world applicability, developing adaptive learning systems with provable guarantees for deployment in safety-critical domains such as autonomous systems, robotics, and human-machine collaboration.

At the Learning Adaptive Systems Group led by Prof. Andreas Krause, my current research focuses on safe deep reinforcement learning — exploring how learning agents can make reliable and safe decisions under uncertainty. Currently, I am on a research visit at the University of Cambridge, Department of Computer Science and Technology, under the supervision of Prof. Carl Henrik Ek.

Before joining ETH Zurich, I earned my Bachelor’s degree in Engineering Science from the Technical University of Munich (TUM), where I built a solid technical foundation across mechanical, electrical, and systems engineering, with a later focus on control theory, modeling, simulation, and machine learning.

I've conducted research on training provably robust agents using set-based reinforcement learning at the TUM Cyber-Physical Systems Group under the supervision of Prof. Matthias Althoff. I've also interned at BMW, and at MTU - Flying Fuel Cell.

Throughout my academic journey, I've been recognized with the Academic Scholarship of Germany (Deutschlandstipendium) during my Bachelor's studies and the Volkswagen Master Scholarship for my Master's program.