Tobias Sutter

Dr.

Tobias Sutter

Alumni

ETH Zurich

I am excited to work in the intersection of data science and automation with the goal to contribute towards a better theoretical understanding.

Tobias Sutter was a Postdoc at the Risk Analytics and Optimization Group at EPF Lausanne as well as the Learning & Adaptive Systems Group in the Institute for Machine Learning at ETH Zurich. He joined NCCR Automation from August 2020 to August 2021. He received his Ph.D. in Electrical Engineering from ETH Zurich (2017). He has been awarded the IEEE George S. Axelby Outstanding Paper Award (2016) and the ETH medal for outstanding doctoral thesis (2018). His research interests lie in the intersection of reinforcement learning, mathematical optimization and data science.

Tobias Sutter now works as assistant professor at the computer science department at the university of Konstanz.

Scientific Publications

Published

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Conference on Neural Information Processing Systems (NeurIPS 2021)

Vol 34 Pages 29754-29767

Tobias Sutter, Andreas Krause, Daniel Kuhn

2021

Doi.org Collection

Published

Efficient Learning of a Linear Dynamical System with Stability Guarantees

IEEE Transactions on Automatic Control

Vol 68 No 5 Pages 2790-2804

Wouter Jongeneel, Tobias Sutter, Daniel Kuhn

2021

Doi.org Collection

Distributionally Robust Optimization with Markovian Data

38th International Conference on Machine Learning (ICML 2021)

Tobias Sutter, Daniel Kuhn

2021

Collection

Research projects as Researcher

Title

Principal Investigators

Distributionally robust reinforcement learning

Daniel Kuhn, Andreas Krause

Summary

This project uses ideas from mathematical optimization and learning theory to derive statistical guarantees for reinforcement learning (RL). While there has recently been significant progress in the understanding of finite-sample guarantees for the linear quadratic regulator (LQR) problem, it remains unclear how to generalize these results beyond the LQR setting. We plan to establish a principled approach to RL based on distributionally robust optimization with the goal to derive statistical guarantees for RL problems beyond the LQR setup. We also aim to develop efficient computational algorithms.

People involved