I am now a Machine Learning Engineer at Nuromedia. You can still reach me via gregor@robot-learning.de.

Gregor Gebhardt

Gregor joined the Intelligent Autonomous System (IAS) lab as a PhD student in January, 2015. During his PhD studies he was working on non-parametric methods for filtering, prediction and smoothing of time series as well as on non-parametric and deep representations of large sets of homogeneous observations for (deep) reinforcement learning.

Gregor started his studies in computer science at the Freie Universität Berlin, where he completed his Bachelor's degree with a thesis written under the supervision of Prof. Dr. Marc Toussaint and Dr. Tobias Lang. For his Master's studies he moved on to the Technische Universität Darmstadt, where the specialized Master's program "Autonomous Systems" gave him the opportunity to focus on the most interesting fields of computer science: machine learning, robotics, computer vision and control theory. He completed his Master's degree by a thesis entitled “Embedding Kalman Filters into Reproducing Kernel Hilbert Spaces", supervised by Prof. Dr. Gerhard Neumann and Prof. Dr. Jan Peters.

Research Interests

Machine Learning, Robotics, (Deep) Reinforcement Learning, Swarm Robotics

Key References

1. • Gebhardt, G.H.W.; Kupcsik, A.; Neumann, G. (2019). The Kernel Kalman Rule, Machine Learning Journal (MLJ), 108, 12, pp.2113–2157, Springer US.
         Bib
2. • Gebhardt, G.H.W.; Daun, K.; Schnaubelt, M.; Neumann, G. (submitted). Learning Policies for Object Manipulation with Robot Swarms, Submitted to Advanced Robotics (ARJ).
         Bib
3. • Gebhardt, G.H.W.; Hüttenrauch, M.; Neumann, G. (submitted). Using M-Embeddings to Learn Control Strategies for Robot Swarms, Submitted to Swarm Intelligence.
         Bib
4. • Gebhardt, G.H.W.; Daun, K.; Schnaubelt, M.; Neumann, G. (2018). Learning Robust Policies for Object Manipulation with Robot Swarms, Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).
         Bib
5. • Gebhardt, G.H.W.; Kupcsik, A.; Neumann, G. (2015). Learning Subspace Conditional Embedding Operators, Large-Scale Kernel Learning Workshop at ICML 2015.
           Bib