Theresa Eimer

Researcher at the Insitutite of AI Hannover

pic.jpg

I am a researcher at the Leibniz University of Hannover currently working towards my PhD. I focus on making Reinforcement Learning agents more general by dynamically adapting their behavior. I’m interested in all things AutoRL, especially dynamic algorithm configuration for RL and curriculum learning, as well as generalization in RL.

I completed my master’s degree in computer science in 2019 at the University of Freiburg under the supervision of Prof. Frank Hutter. Since 2020 I’ve been a PhD candidate in Hannover supervised by Prof. Marius Lindauer. I have interned at MetaAI in London in 2022/23. If you want to chat (about research or otherwise), feel free to book a slot in my calendar!

news

Nov 18, 2024 After almost five years, I successfully defended my PhD thesis and received a grade of summa cum laude for it! Thank you to everyone who helped me along the way.
Oct 2, 2024 I’m very pleased to be selected as a fellow of the Zeit Zia program for 2024/25. Looking forward to meeting exciting people and learning a lot in the coming year!
Apr 30, 2024 Excited to announce the first edition of the AutoRL workshop at this year’s ICML!
Sep 25, 2023 I’m excited to have been chosen as one of the 19 young researchers invited to the Future of AI Summit in Aachen this week! I’ll be talking about my vision for AutoRL as a paradigm to make RL more robust, efficient and general.
Sep 21, 2023 I’ve had a great time in Brussels at EWRL. If you’re interested in my favorite papers, take a look at this Twitter thread.

latest posts

selected publications

  1. Self-Paced Context Evaluation for Contextual Reinforcement Learning
    In Proceedings of the Thirty-eighth International Conference on Machine Learning, Jul 2021
  2. Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
    Jack Parker-Holder, Raghu Rajan, Xingyou Song, André Biedenkapp, Yingjie Miao, Theresa Eimer, Baohe Zhang, Vu Nguyen, Roberto Calandra, Aleksandra Faust, Frank Hutter, and Marius Lindauer
    Journal of Artificial Intelligence Research (JAIR), Jul 2022
  3. Contextualize Me - The Case for Context in Reinforcement Learning
    Transactions on Machine Learning Research, Jul 2023