Frederik Schubert studied computer engineering at Leibniz University in Hannover. He completed his master's degree in July 2019 with a thesis entitled "Multi-Task Learning by Neural Transfer Reinforcement Learning".

He has been working on his doctorate at TNT since September 2019. His research focuses on Reinforcement Learning and Procedural Content Generation, but he has also done work on object detection, small data classification and the analysis of hyperspectral images.

Semantic Scene Analysis

AI Competition

Reinforcement Learning

Publications

Show selected publications only

Frederik Schubert, Yannik Mahlau, Konrad Bethmann, Fabian Hartmann, Reinhard Caspary, Marco Munderloh, Jörn Ostermann, Bodo Rosenhahn
Quantized Inverse Design for Photonic Integrated Circuits
Preprint, December 2024
(arXiv.org) BibTeX
Yannik Mahlau, Frederik Schubert, Bodo Rosenhahn
Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
Proceedings of the 41st International Conference on Machine Learning (ICML), July 2024
(arXiv.org) BibTeX
Carolin Benjamins, Theresa Eimer, Frederik Schubert, Aditya Mohan, Sebastian Döhler, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer
Contextualize Me - The Case for Context in Reinforcement Learning
Transactions on Machine Learning Research, June 2023
(OpenReview, PDF, arXiv.org) BibTeX
Frederik Schubert, Carolin Benjamins, Sebastian Döhler, Bodo Rosenhahn, Marius Lindauer
POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning
Transactions on Machine Learning Research, April 2023
(OpenReview, PDF) BibTeX
Maren Awiszus, Frederik Schubert, Bodo Rosenhahn
Wor(l)d-GAN: Towards Natural Language Based PCG in Minecraft
IEEE Transactions on Games, IEEE, February 2022, edited by Georgios Yannakakis
(IEEEexplore) BibTeX
Christoph Reinders, Frederik Schubert, Bodo Rosenhahn
ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI), 2022
(arXiv.org, GitHub) BibTeX
Carolin Benjamins, Theresa Eimer, Frederik Schubert, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer
CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning
NeurIPS 2021 Workshop on Ecological Theory of Reinforcement Learning, December 2021
(arXiv.org) BibTeX
Maren Awiszus, Frederik Schubert, Bodo Rosenhahn
World-GAN: a Generative Model for Minecraft Worlds
IEEE Conference on Games, August 2021
(arXiv.org) BibTeX
Frederik Schubert, Theresa Eimer, Bodo Rosenhahn, Marius Lindauer
Towards Automatic Risk Adaption in Distributional Reinforcement Learning
Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 38th International Conference on Machine Learning (ICML), July 2021
(arXiv.org) BibTeX
Frederik Schubert, Theresa Eimer, Bodo Rosenhahn, Marius Lindauer
Automatic Risk Adaptation in Distributional Reinforcement Learning
Arxiv Preprint, June 2021
(arXiv.org) BibTeX
Frederik Schubert, Maren Awiszus, Bodo Rosenhahn
TOAD-GAN: a Flexible Framework for Few-Shot Level Generation in Token-Based Games
IEEE Transactions on Games, IEEE, March 2021, edited by Julian Togelius
(IEEEexplore) BibTeX
Maren Awiszus, Frederik Schubert, Bodo Rosenhahn
TOAD-GAN: Coherent Style Level Generation from a Single Example
AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment Best Student Paper Award , October 2020
(AAAI, GitHub, arXiv.org, Award, Talk (YouTube)) BibTeX

Other activities

Supervised Theses

Unsupervised Domain-Specific Pre-Training for Object Detection
Option Discovery in Hierarchical Reinforcement Learning
Defektprädiktion von Leiterplatten mit Verfahren der künstlichen Intelligenz
Wireframe Reconstruction from Single Images
Hyperbolic Embeddings in Distributional Reinforcement Learning
Implementation and Analysis of Sequential Model-Based Optimisation Methods for the Calibration of Numerical Groundwater Flow Models
Few-Shot Anomaly Detection Using Neural Cellular Automata
Feature-basierte Kombination von mehreren Bildern zur Klassifikation mit wenigen Trainingsbeispielen
Guided Diffusion Models with Few Training Examples
AlphaZero for Simultaneous Perfect-Information Games