Thomas Schmied: Self-supervised offline reinforcement learning for real-world decision-making agents (MSc thesis)
Fabian Jogl: Using Structural Information to Improve Graph Neural Networks (MSc thesis)
Dominik Schmidt: Generalization and Transfer Learning in Multi-Task Reinforcement Learning (BSc thesis)
Maximilian Holzmüller: Procedural Level Generation for Video Games (BSc Thesis)
Dominik Schmidt. Dojo: A Large Scale Benchmark for Multi-Task Reinforcement Learning.Agent Learning in Open-Endedness ICLR Workshop 2022.
Fabian Jogl, Maximilian Thiessen, and Thomas Gärtner. Reducing Learning on Cell Complexes to Graphs.Geometrical and Topological Representation Learning ICLR Workshop 2022.
Fares Meghdouri, Thomas Schmied, Tanja Zseby, and Thomas Gärtner. Conditional Network Data Balancing With GANs.Deep Generative Models and Downstream Applications NeurIPS Workshop 2021.
Dominik Schmidt and Thomas Schmied. Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari.Deep Reinforcement Learning NeurIPS Workshop 2021.
Thomas Schmied and Maximilian Thiessen. Efficient Reinforcement Learning via Self-supervised learning and Model-based methods.Challenges of Real-World Reinforcement Learning NeurIPS Workshop 2020. (pdf)
Sabrina Herbst: Analysis of Bacteriophages—Predicting Hosts of Bacteriophages Based on
Molecular Sequence Data (BSc thesis)
Philip Vonderlind: Domain Transfer for Multi-Agent Reinforcement Learning (BSc thesis)