Daniel Palenicek

Research Interests
- Reinforcement Learning
- Model-based Reinforcement Learning
- Machine Learning
Affiliations
- TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
- Hessian Centre for Artificial Intelligence
Contact Information
daniel.palenicek@tu-darmstadt.de
Room E304, Building S2|02, TU Darmstadt, FB-Informatik, FG-IAS, Hochschulstr. 10, 64289 Darmstadt
+49-6151-16-25387
Reviewing
NeurIPS, ICLR, CoRL, and various Robotics & ML workshops.
Teaching Assistant
Lecture | Years |
Computational Engineering and Robotics | SS 2022, WS 2022/23 |
Statistical Machine Learning | SS 2023, WS 2023/24 |
Daniel joined the Intelligent Autonomous System lab on October 1st, 2021 as a Ph.D. student. He is part of the 3AI project with Hessian.AI. In his research, Daniel focuses on increasing sample efficiency of model-based reinforcement learning algorithms by studying the impact which model-errors have on the learning.
Before starting his Ph.D., Daniel completed his Bachelor's degree and Master's degree in Wirtschaftsinformatik at the Technische Universität Darmstadt. He wrote his Master's thesis entitled "Dyna-Style Model-Based Reinforcement Learning with Value Expansion" in the Computer Science Department under the supervision of Michael Lutter and Jan Peters. During his studies, Daniel further did two research internships, at the Bosch Center for AI and at Huawei Noah’s Ark Lab London.
Publications
-
- Bhatt, A.; Palenicek, D.; Belousov, B.; Argus, M.; Amiranashvili, A.; Brox, T.; Peters, J. (2023). CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity, arXiv preprint.
-
- Palenicek, D.; Lutter, M.; Carvalho, J.; Peters, J. (2023). Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning, International Conference on Learning Representations (ICLR).
-
- Gruner, T.; Belousov, B.; Muratore, F.; Palenicek, D.; Peters, J. (2023). Pseudo-Likelihood Inference, Advances in Neural Information Processing Systems (NIPS / NeurIPS).
-
- Palenicek, D.; Lutter, M., Peters, J. (2022). Revisiting Model-based Value Expansion, Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM).
-
- Cowen-Rivers, A.I.; Palenicek, D.; Moens, V.; Abdullah, M.A.; Sootla, A.; Wang, J.; Bou-Ammar, H. (2022). SAMBA: safe model-based & active reinforcement learning, Machine Learning.
-
- Palenicek, D. (2021). A Survey on Constraining Policy Updates Using the KL Divergence, Reinforcement Learning Algorithms: Analysis and Applications, pp.49-57.
-
- Belousov, B.; Abdulsamad H.; Klink, P.; Parisi, S.; Peters, J. (2021). Reinforcement Learning Algorithms: Analysis and Applications, Studies in Computational Intelligence, Springer International Publishing.
- Zhou, M.; Luo, J.; Villella, J.; Yang, Y.; Rusu, D.; Miao, J.; Zhang, W.; Alban, M.; Fadakar, I.; Chen, Z.; Chongxi-Huang, A.; Wen, Y.; Hassanzadeh, K.; Graves, D.; Chen, D.; Zhu, Z.; Nguyen, N.; Elsayed, M.; Shao, K.; Ahilan, S.; Zhang, B.; Wu, J.; Fu, Z.; Rezaee, K.; Yadmellat, P.; Rohani, M.; Perez-Nieves, N.; Ni, Y.; Banijamali, S.; Cowen-Rivers, A.; Tian, Z.; Palenicek, D.; Bou-Ammar, H.; Zhang, H.; Liu, W.; Hao, J.; Wang, J. (2020). SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving. Conference on Robot Learning (CoRL). Best System Paper Award. PDF
Supervised Projects
Thesis/Project | Student(s) | Topic | Together with |
RL:IP.WS23/24 | Dennert D., Scherer C., Ahmad F. | XXX: eXploring X-Embodiment with RT-X | Tim Schneider & Theo Gruner & Maximilian Tölle |
RL:IP.WS23/24 | Morton C., Jacobs T. | XXX: eXploring X-Embodiment with RT-X | Tim Schneider & Theo Gruner & Maximilian Tölle |
RL:IP.WS23/24 | Böhm A., Pfenning I., Lenz J. | Unveiling the Unseen: Tactile Perception and Reinforcement Learning in the Real World | Tim Schneider & Theo Gruner |
RL:IP.SS23 | Krämer E. | Latent Tactile Representations for Model-based RL | Tim Schneider & Theo Gruner |