cv
Basics
Name | Moritz Akiya Zanger |
moritz.a.zanger@gmail.com | |
Url | https://anyboby.github.io/ |
Summary | Machine Learning Researcher with a focus on Deep Reinforcement Learning. |
Work
-
2021.06 - 2025.05 Ph.D. in Computer Science and Artificial Intelligence
Sequential Decision Making, TU Delft, NL
Efficient Uncertainty Quantification in Deep Reinforcement Learning. Supervised by Prof. Matthijs T.J. Spaan and Dr. Wendelin Bohmer.
- Part of EU Horizons Project Epistemic AI
-
2021.05 - 2022.01 Research Assistant
Intelligent Systems, Karlsruhe Research Center of Information Technology, GER
Worked on natural language processing algorithms for requirements management with pretrained models (BERT).
-
2021.01 - 2021.05 Research Assistant
Cognitive Systems, Karlsruhe Research Center of Information Technology, GER
Developed gradient estimation techniques for trust-region methods in model-based RL.
Education
-
2017.10 - 2020.10 Karlsruhe, Germany
M.Sc. Mechanical Engineering
Karlsruhe Institute of Technology, Germany
Thesis Title: Model-Based Reinforcement Learning for Constrained Policy Optimization in Robot Locomotion. Supervised by Prof. Marius J. Zoellner
- Graduated with distinction
- Majored in Robotics and Medical Engineering
-
2015.09 - 2016.09 Sendai, JP
-
2012.10 - 2017.10 Karlsruhe, Germany
B.Sc. Mechanical Engineering
Karlsruhe Institute of Technology, Germany
- Majored in Engineering Design
-
Korntal, Germany
Awards
- 2022
MLSS Scholarship
Machine Learning Summer School, Krakow Poland
- 2018
Students@Bosch Fellow
Robert Bosch GmbH
- 2017
GfSE Student Award
German Association for Systems Engineering
- 2016
DAAD Annual Scholarship
German Academic Exchange Service
Publications
-
2025 Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model
Moritz A. Zanger, Pascal R. van der Vaart, Matthijs T. J. Spaan and Wendelin Bohmer
Preprint (Arxiv)
-
2025 Value Improved Actor Critic Algorithms
Yaniv Oren, Moritz A. Zanger, Pascal R. van der Vaart, Matthijs T. J. Spaan and Wendelin Bohmer
Preprint (Arxiv)
-
2024 Diverse Projection Ensembles for Distributional Reinforcement Learning
Moritz A. Zanger, Wendelin Bohmer, and Matthijs T. J. Spaan.
International Conference on Learning Representations (ICLR).
-
2021 Safe Continuous Control with Constrained Model-Based Policy Optimziation
Moritz A. Zanger, Karam Daaboul, and J. Marius. Zollner.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Skills
Python |
C++ |
Java |
MATLAB |
SQL |
Git |
Jax |
PyTorch |
Tensorflow |
Slurm |
ROS |
MuJoCo, Unity, CARLA |
Languages
German | |
Native speaker |
English | |
Fluent |
Japanese | |
Fluent |
Dutch | |
Intermediate |
Interests
Woodworking |
Kayaking |
Tennis |
References
Professor Matthijs T. J. Spaan | |
Director Sequential Decision Making, TU Delft |
Dr. Wendelin Boehmer | |
Assistant Professor Sequential Decision Making, TU Delft |
Dr. Frans A. Oliehoek | |
Associate Professor Sequential Decision Making, TU Delft |