Follow
Phillip Swazinna
Phillip Swazinna
AI Research Scientist, Siemens AG
Verified email at tum.de - Homepage
Title
Cited by
Cited by
Year
Overcoming model bias for robust offline deep reinforcement learning
P Swazinna, S Udluft, T Runkler
Engineering Applications of Artificial Intelligence 104, 104366, 2021
782021
Comparing model-free and model-based algorithms for offline reinforcement learning
P Swazinna, S Udluft, D Hein, T Runkler
IFAC Conference on Intelligent Control and Automation Sciences, 2022
332022
User-Interactive Offline Reinforcement Learning
P Swazinna, S Udluft, T Runkler
International Conference on Learning Representations (ICLR), 2023
132023
Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning
P Swazinna, S Udluft, T Runkler
IEEE Symposium Series on Computational Intelligence, 2021
122021
Learning Control Policies for Variable Objectives from Offline Data
M Weber, P Swazinna, D Hein, S Udluft, V Sterzing
2023 IEEE Symposium Series on Computational Intelligence (SSCI), 1674-1681, 2023
62023
Behavior constraining in weight space for offline reinforcement learning
P Swazinna, S Udluft, D Hein, T Runkler
European Symposium on Aritficial Neural Networks, Computational Intelligence …, 2021
62021
q-Space deep learning for Alzheimer’s disease diagnosis: Global prediction and weakly-supervised localization
V Golkov, P Swazinna, MM Schmitt, QA Khan, CMW Tax, M Serahlazau, ...
Proc. 27th Annu. Meeting ISMRM 1580, 2018
52018
Negative-unlabeled learning for diffusion MRI
P Swazinna, V Golkov, I Lipp, E Sgarlata, V Tomassini, DK Jones, ...
Proc. Intl. Soc. Mag. Reson. Med 27, 3480, 2019
32019
Towards user-interactive offline reinforcement learning
P Swazinna, S Udluft, T Runkler
3rd Offline RL Workshop: Offline RL as a''Launchpad'', 2022
12022
Iterative Batch Reinforcement Learning via Safe Diversified Model-based Policy Search
A Najib, S Depeweg, P Swazinna
arXiv preprint arXiv:2411.09722, 2024
2024
Method and control device for controlling a machine
P Swazinna, S Udluft
US Patent App. 18/141,529, 2023
2023
Method for configuring a control agent for a technical system, and control device
P Swazinna, S Udluft, T Runkler
US Patent App. 18/015,290, 2023
2023
Automatic Trade-off Adaptation in Offline RL
P Swazinna, S Udluft, T Runkler
arXiv preprint arXiv:2306.09744, 2023
2023
Policy Regularization for Model-Based Offline Reinforcement Learning
PA Swazinna
Technische Universität München, 2023
2023
ALICE III—Autonomes Lernen in Komplexen Umgebungen III
A von Beuningen, V Brandstetter, P von Bünau, S Depeweg, R Glauert, ...
2022
The system can't perform the operation now. Try again later.
Articles 1–15