Scholar
Jannis Blüml
Google Scholar ID: RN7YYrEAAAAJ
PhD candidate, TU Darmstadt
Citations & Impact
Citations
59
H-index
4
i10-index
2
Publications
13
Co-authors
9
list available
Contact
Resume (English only)
Academic Achievements
- Multiple publications, specific list not provided.
Research Experience
- - Supervised multiple B.Sc. and M.Sc. theses, covering topics such as symbolic input representations, LSTM-based beampath optimizer, ISMCTS enhancements, game phase-specific models, transformers for urban energy management, and using graph neural networks to improve generalization in self-play reinforcement learning.
- - Involved in teaching several courses and projects, including JaxTari Lab, Arcade 2.0, Object-centric Reinforcement Learning Lab, Introduction to Artificial Intelligence, and others.
Education
- - 2021 - now: PhD student at AIML, CS Department, TU Darmstadt, and hessian.AI, Germany
- - 2018 - 2021: M.Sc. Computer Science at TU Darmstadt, Germany
- - 2014 - 2018: B.Sc. Computer Science at TU Darmstadt, Germany
Background
- Research interests are centered around reinforcement learning, particularly using deep neural networks. Currently working on combining modern approaches with transformer networks and developing new methods. The overall goal is to better understand reasoning within RL, especially in partially observable environments.
