Andreas Schlaginhaufen
EPFL STI IGM SYCAMORE
ME C1 402 (Bâtiment ME)
Station 9
1015 Lausanne
Web site: Web site: https://www.epfl.ch/labs/sycamore/
Biography
Andreas Schlaginhaufen received his Bachelor's and Master’s degrees in Electrical Engineering and Information Technology from ETH Zurich, including an exchange semester at the University of Toronto, Canada. He interned with EWZ Zurich's power grid development team and ETH Zurich’s Learning & Adaptive Systems group. His master’s thesis focused on stable deep dynamics models for partially observed or time-delayed systems. His PhD research focuses on the theoretical and practical aspects of aligning reinforcement learning models with human preferences and expert demonstrations. His broader interests include safe reinforcement learning, convex analysis, and learning in games.Awards
Swiss Data Science Center PhD Fellowship
The SDSC PhD Fellowship is a competitive grant awarded to PhD students of EPFL and ETH Zurich, providing full funding for the entire length of the PhD and mentoring by the Swiss Data Science Center.
2022
Publications
Selected publications
| Andreas Schlaginhaufen, Maryam Kamgarpour Advances in Neural Information Processing Systems 38 (NeurIPS 2024) |
Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning |
| Titouan Renard*, Andreas Schlaginhaufen*, Tingting Ni*, Maryam Kamgarpour The 63rd IEEE Conference on Decision and Control (CDC 2024). |
Convergence of a model-free entropy-regularized inverse reinforcement learning algorithm |
| Andreas Schlaginhaufen, Maryam Kamgarpour Proceedings of the 40th International Conference on Machine Learning (ICML 2023) |
Identifiability and Generalizability in Constrained Inverse Reinforcement Learning |
| Andreas Schlaginhaufen, Philippe Wenk, Andreas Krause, Florian Dörfler Advances in Neural Information Processing Systems 35 (NeurIPS 2021) |
Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems |