InstitutTeam
Theresa Eimer

Theresa Eimer, M. Sc.

Theresa Eimer, M. Sc.
Adresse
Appelstraße 9a
30167 Hannover
Gebäude
Raum
Theresa Eimer, M. Sc.
Adresse
Appelstraße 9a
30167 Hannover
Gebäude
Raum

I have been working towards my PhD at the intersection of AutoML and Reinforcement Learning as a doctoral researcher at the Leibniz University since 2020. Previously I attained my Master's degree at the Albert-Ludwigs University of Freiburg through my thesis on "Improved Meta-Learning for Algorithm Control through Self-Paced Learning" under the supervision of Frank Hutter.

My 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.

Apart from that, I am interested in how Machine Learning systems can be integrated into our lives in an equitable and fair way.

Research Interests

  • Generalization in Reinforcement Learning
  • Dynamic Algorithm Configuration
  • Automated Reinforcement Learning
  • Meta Reinforcement Learning
  • Societal Impact of Machine Learning

Curriculum Vitae

  • Education

    2022: Chair for Diversity & Inclusion at the AutoML-Conf

    since 2020: Doctoral Researcher at the Leibniz University Hannover

    2016 - 2019: M.Sc. Computer Science at the Albert-Ludwigs University Freiburg
    Thesis: Improved Meta-Learning for Dynamic Algorithm Configuration
    Supervisor: Prof. Dr. Frank Hutter

    2013 - 2016: B.Sc. Computer Science at the University of Hamburg
    Thesis: On Thue Numbers
    Supervisor: Dr. Frank Heitmann

Publications

  • Steven Adriaensen, André Biedenkapp, Gresa Shala, Noor H. Awad, Theresa Eimer, Marius Lindauer, Frank Hutter (2022): Automated Dynamic Algorithm ConfigurationComputing Research Repository (CoRR) (2022)
    DOI: https://doi.org/10.48550/arXiv.2205.13881
    arXiv: 2205.13881
  • Carolin Benjamins, Theresa Eimer, Frederik Schubert, Aditya Mohan, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer (2022): Contextualize Me - The Case for Context in Reinforcement LearningArXiv Preprint
    arXiv: https://arxiv.org/abs/2202.04500
  • 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 (2022): Automated Reinforcement Learning (AutoRL): A Survey and Open ProblemsJournal of Artificial Intelligence Research (JAIR)
    arXiv: 2201.03916
  • Theresa Eimer, Carolin Benjamins, Marius Lindauer (2021): Hyperparameters in Contextual RL are Highly SituationalInternational Workshop on Ecological Theory of RL (at NeurIPS) | Datei |
  • Carolin Benjamins, Theresa Eimer, Frederik Schubert, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer (2021): CARL: A Benchmark for Contextual and Adaptive Reinforcement LearningWorkshop on Ecological Theory of Reinforcement Learning, NeurIPS 2021
    arXiv: 2110.02102
  • Frederik Schubert, Theresa Eimer, Bodo Rosenhahn, Marius Lindauer (2021): Automatic Risk Adaptation in Distributional Reinforcement Learning
    arXiv: 2106.06317
  • Theresa Eimer, André Biedenkapp, Frank Hutter, Marius Lindauer (2021): Self-Paced Context Evaluation for Contextual Reinforcement LearningProceedings of the international conference on machine learning (ICML)
    arXiv: 2106.05110
  • Theresa Eimer, André Biedenkapp, Maximilian Reimer, Steven Adriaensen, Frank Hutter, Marius Lindauer (2021): DACBench: A Benchmark Library for Dynamic Algorithm ConfigurationProceedings of the international joint conference on AI (IJCAI) 2021
    arXiv: 2105.08541
  • Theresa Eimer, André Biedenkapp, Frank Hutter, Marius Lindauer (2020): Towards Self-Paced Context Evaluation for Contextual Reinforcement LearningInternational Conference on Machine Learning (ICML) 2020 | Datei |
  • André Biedenkapp, H Furkan Bozkurt, Theresa Eimer, Frank Hutter, Marius Lindauer (2020): Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic FrameworkEuropean Conference on AI (ECAI) 2020 | Datei |
  • André Biedenkapp, H. Furkan Bozkurt, Theresa Eimer, Frank Hutter, Marius Lindauer (2020): Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic FrameworkEuropean Conference on Artificial Intelligence (ECAI) 2020
    DOI: 10.3233/FAIA200122

Projects

  • Dynamic Algorithm Configuration
    Da die Konfigurationen während der Laufzeit in Abhängigkeit vom aktuellen Zustand des Algorithmus ausgewählt werden sollten, kann es als ein Problem des Reinforcement Learning (RL) betrachtet werden, bei dem ein Agent in jedem Zeitschritt die zu verwendende Konfiguration auf der Grundlage der Leistung im letzten Schritt und des aktuellen Zustands des Algorithmus auswählt. Dies ermöglicht uns einerseits den Einsatz leistungsfähiger RL-Methoden, andererseits bringt RL auch eine Reihe von Herausforderungen mit sich, wie Instabilität, Rauschen und Ineffizienz bei der Abtastung, die bei Anwendungen wie DAC angegangen werden müssen. Daher umfasst die Forschung zu DAC auch die Forschung zu zuverlässigem, interpretierbarem, allgemeinem und schnellem Reinforcement Learning.
    Leitung: Prof. Dr. Marius Lindauer
    Jahr: 2019
    Förderung: DFG
    Laufzeit: 2019-2023
  • Dynamic Algorithm Configuration
    As configurations should be chosen during runtime depending on the current algorithm state, it can be viewed as a reinforcement learning (RL) problem where at each timestep an agent selects the configuration to use based on the performance in the last step and the current state of the algorithm. This enables us to use powerful RL methods on one hand; on the other, RL also brings a set of challenges like instability, noise and sample inefficiency that need to be addressed in applications such as DAC. Therefore research on DAC also includes research on reliable, interpretable, general and fast reinforcement learning.
    Leitung: Prof. Dr. Marius Lindauer
    Jahr: 2019
    Förderung: DFG
    Laufzeit: 2019-2023