Nicolai Dorka
Albert-Ludwigs-Universität Freiburg |
About me
- 10/2012 - 11/2015: Bachelor of Science in Mathematics, University of Göttingen
- 10/2012 - 11/2015: Bachelor of Arts Philosophy/Mathematics, University of Göttingen
- 10/2015 - 11/2017: Master of Science Mathematics, University of Göttingen
- 08/2018 - up to now: Working at the Autonomous Intelligent Systems group of Prof. Dr. Wolfram Burgard as PhD student
Research Interests
- (Deep) Reinforcement Learning
- Multi-Task and Transfer Learning
- Learning from Demonstrations
- Navigation
Publications
Journal and Conference Papers
-
Nicolai Dorka, Tim Welschehold, Wolfram Burgard
NEW: Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
International Conference on Learning Representations (ICLR), 2023.
Also at Workshop on Decision Awareness in Reinforcement Learning, International Conference on Machine Learning (ICML), 2022
Download BibTeX
-
Nicolai Dorka, Joschka Boedecker, Wolfram Burgard
Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning
IEEE Robotics and Automation Letters (RAL), 2023.
Also at Workshop on Deep Reinforcement Learning, Conference on Neural Information Processing Systems (NeurIPS), 2021
Download BibTeX
-
Nicolai Dorka*, Johannes Meyer*, Wolfram Burgard
Modality-Buffet for Real-Time Object Detection
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, USA, 2020
Download BibTeX
Workshop Papers
-
Jingwei Zhang*, Niklas Wetzel*, Nicolai Dorka*, Joschka Boedecker, Wolfram Burgard
Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
Workshop on Exploration in Reinforcement Learning (Spotlight Talk), Internatioal Conference on Machine Learning (ICML), Long Beach, USA, 2019
Download BibTeX Talk (starts 55:20)