Institut für Informationsverarbeitung (TNT)

I moved to the Institute of AI on July 1st 2022. My new website is here.

Theresa Eimer studied Computer Science at the Albert-Ludwigs Universität Freiburg and recieved her Master's degree in 2019. Her thesis "Improved Meta-Learning for Algorithm Control through Self-Paced Learning" showed the benefits of automatically generated learning curricula for Dynamic Algorithm Configuration. Since 2020 she is working towards a PhD as a doctoral researcher at the Institut für Informationsverarbeitung.

Her main research interest is AutoML, more specifically Dynamic Algorithm Configuration which aims to control algorithm hyperparameters on the fly in order to improve the algorithm's performance. A focus here is on the use of Transfer and Meta-Learning techniques for Reinforcement Learning in order to make training more efficient and enable knowledge transfer between instances and problems.

Publications

Show selected publications only

Steven Adriaensen, André Biedenkapp, Gresa Shala, Noor Awad, Theresa Eimer, Marius Lindauer, Frank Hutter
Automated Dynamic Algorithm Configuration
ArXiv, May 2022
(Arxiv.org) BibTeX
Carolin Benjamins, Theresa Eimer, Frederik Schubert, Aditya Mohan, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer
Contextualize Me - The Case for Context in Reinforcement Learning
ArXiv Preprint, February 2022
(Arxiv.org) BibTeX
Jack Parker-Holder, Raghu Rajan, Xingyou Song, André Biedenkapp, Yingjie Miao, Theresa Eimer, Baohe Zhang, Vu Nguyen, Roberto Calandra, Aleksandra Faust, Frank Hutter, Marius Lindauer
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
Journal of Artificial Intelligence Research (JAIR), 2022
(Arxiv.org) BibTeX
Theresa Eimer, Carolin Benjamins, Marius Lindauer
Hyperparameters in Contextual RL are Highly Situational
NeurIPS 2021 Workshop on Ecological Theory of Reinforcement Learning, December 2021
(pdf) BibTeX
Carolin Benjamins, Theresa Eimer, Frederik Schubert, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer
CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning
NeurIPS 2021 Workshop on Ecological Theory of Reinforcement Learning, December 2021
(Arxiv.org) BibTeX
Theresa Eimer, André Biedenkapp, Maximilian Reimer, Steven Adriaensen, Frank Hutter, Marius Lindauer
DACBench: A Benchmark Library for Dynamic Algorithm Configuration
Proceedings of the international joint conference on artificial intelligence (IJCAI), August 2021
(pdfArxiv.org) BibTeX
Theresa Eimer, Andre Biedenkapp, Frank Hutter, Marius Lindauer
Self-Paced Context Evaluation for Contextual Reinforcement Learning
Proceedings of the international conference on machine learning (ICML), July 2021
(Arxiv.org) BibTeX
Frederik Schubert, Theresa Eimer, Bodo Rosenhahn, Marius Lindauer
Towards Automatic Risk Adaption in Distributional Reinforcement Learning
Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 38th International Conference on Machine Learning (ICML), July 2021
(Arxiv.org) BibTeX
Frederik Schubert, Theresa Eimer, Bodo Rosenhahn, Marius Lindauer
Automatic Risk Adaptation in Distributional Reinforcement Learning
Arxiv Preprint, June 2021
(Arxiv.org) BibTeX
Theresa Eimer, Andre Biedenkapp, Frank Hutter, Marius Lindauer
Towards Self-Paced Context Evaluations for Contextual Reinforcement Learning
Workshop on Inductive Biases, Invariances and Generalization in Reinforcement Learning (BIG@ICML'20), July 2020
(pdf) BibTeX
Andre Biedenkapp, H. Furkan Bozkurt, Theresa Eimer, Frank Hutter, Marius Lindauer
Algorithm Control: Foundation of a New Meta-Algorithmic Framework
Proceedings of the European Conference on Artificial Intelligence (ECAI), 2020
(pdf) BibTeX