Matthias Schultheis joined the lab in December 2019 as a PhD student. He is working in a joint project with (and partly at) the Bioinspired Communication Systems lab of TU Darmstadt supervised by Prof. Koeppl and Prof. Rothkopf.
His research aims at understanding and predicting human behavior by means of methods for Inverse Reinforcement Learning. In general, he is interested in various topics related to Probabilistic Modelling, Bayesian Inference, Human Decision Making, and Reinforcement Learning.
Before starting his PhD, he completed his Bachelor's degree in Computer Science and Master's degree in Autonomous Systems at the Technische Universitaet Darmstadt. In his Master's thesis, entitled Approximate Bayesian Reinforcement Learning for System Identification, he investigated model-based solutions for evoking near-optimal curious behavior in learning systems. In his Bachelor's studies he was a member of the Athena-Minerva Cybathlon-Team of TU Darmstadt and the Max Planck Institute for Intelligent Systems, which developed a Brain-Computer-Interface (BCI) system and participated in the BCI-Race at the Cybathlon 2016.
Presentations and Publications
- Schultheis, M.; Belousov, B.; Abdulsamad, H.; Peters, J. (2019). Receding Horizon Curiosity, Proceedings of the 3rd Conference on Robot Learning (CoRL).
- Belousov, B.; Abdulsamad, H.; Schultheis, M.; Peters, J. (2019). Belief space model predictive control for approximately optimal system identification, 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM).