Scholar
Stefan Stojanovic
Google Scholar ID: jCkz9ykAAAAJ
KTH Royal Institute of Technology, Sweden
Citations & Impact
Citations
51
H-index
3
i10-index
2
Publications
6
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published multiple papers in conferences such as Neurips, ICML, ALT, etc. For more details, please check his Google Scholar page. His research is supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP-AI).
Research Experience
- As a PhD student, he has been involved in several research projects, including the study of how essential structures for task solving naturally emerge in self-supervised RL. He also supervises bachelor's and master's theses, examples include:
- - “Adaptive Reinforcement Learning for Real-World Systems with Delays” by Iga Pawlak (co-supervised with ABB)
- - “Frameskipping and Exploration Strategies for Deep Q-Networks” by Niklas Rolin and Vaka Soleyjardottir
- - “Multi-Agent Control in Warehousing: A Deep Q-Network Approach” by Adam Fischer and Martin Wilen
Education
- Currently a 4th year PhD student at the Division of Decision and Control Systems, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, under the supervision of Prof. Alexandre Proutiere; previously obtained an MSc in Electrical Engineering and Information Technology from ETH Zurich with distinction.
Background
- Research interests include reinforcement learning, self-supervised RL. During his PhD, he focuses on problems with specific low-dimensional structures, such as model-based RL, contextual bandits, and model-free RL.
Miscellany
- LinkedIn profile link available
Co-authors