Intelligent Autonomous Systems | Team / Daniel Palenicek

Daniel Palenicek

Research Interests

Reinforcement Learning
Model-based Reinforcement Learning
Machine Learning

Affiliations

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, RLC (Senior Reviewer), IROS, and various ML & Robotics workshops.

Teaching Assistant

Lecture	Years
CE and Robotics	SS 2022, WS 2022/23
Statistical Machine Learning	SS 2023, WS 2023/24
Probabilistic Methods in CS	WS 2024/25

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

Bib
Palenicek, D.; Lutter, M.; Carvalho, J.; Dennert, D.; Ahmad, F.; Peters, J. (submitted). Diminishing Return of Value Expansion Methods, Submitted to the IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI).
Bib
Vincent, T.; Palenicek, D.; Belousov, B.; Peters, J.; D'Eramo, C. (2025). Iterated Q-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning, Transactions on Machine Learning Research (TMLR).
Bib
Palenicek, D.; Vogt, F.; Peters, J. (2025). Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization, Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM).
Bib
Toelle, M.; Gruner, T.; Palenicek, D.; Guenster, J.; Liu, P.; Watson, J.; Tateo, D.; Peters, J. (2025). Towards Safe Robot Foundation Models, German Robotics Conference (GRC).
Bib
Bhatt, A.; Palenicek, D.; Belousov, B.; Argus, M.; Amiranashvili, A.; Brox, T.; Peters, J. (2024). CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity, International Conference on Learning Representations (ICLR), Spotlight.
Bib
Palenicek, D.; Gruner, T.; Schneider, T.; Böhm, A.; Lenz, J.; Pfenning, I. and Krämer, E.; Peters, J. (2024). Learning Tactile Insertion in the Real World, IEEE ICRA 2024 Workshop on Robot Embodiment through Visuo-Tactile Perception.
Bib
Palenicek, D.; Gruner, T.; Schneider, T.; Böhm, A.; Lenz, J.; Pfenning, I. and Krämer, E.; Peters, J. (2024). Learning Tactile Insertion in the Real World, 40th Anniversary of the IEEE International Conference on Robotics and Automation (ICRA@40).
Bib
Bhatt, A.; Palenicek, D.; Belousov, B.; Argus, M.; Amiranashvili, A.; Brox, T.; Peters, J. (2024). CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity, European Workshop on Reinforcement Learning (EWRL).
Bib
Lenz, J.; Gruner, T.; Palenicek, D.; Schneider, T.; Pfenning, I.; Peters J. (2024). Analysing the Interplay of Vision and Touch for Dexterous Insertion Tasks, CoRL 2024 Workshop on Learning Robot Fine and Dexterous Manipulation: Perception and Control.
Bib
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).
Bib
Gruner, T.; Belousov, B.; Muratore, F.; Palenicek, D.; Peters, J. (2023). Pseudo-Likelihood Inference, Advances in Neural Information Processing Systems (NIPS / NeurIPS).
Bib
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.
Bib
Palenicek, D.; Lutter, M., Peters, J. (2022). Revisiting Model-based Value Expansion, Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM).
Bib
Palenicek, D. (2021). A Survey on Constraining Policy Updates Using the KL Divergence, Reinforcement Learning Algorithms: Analysis and Applications, pp.49-57.
Bib
Zhou, M.; ...; Palenicek, D; ... (2020). SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving, Conference on Robot Learning (CoRL), Best System Paper Award.

Talks and Interviews

Supervised Theses and Projects

Thesis/Project	Topic	Student(s)	Together with
M.Sc. Thesis	Investigating bottlenecks of CrossQ's sample efficiency	Vogt F.
M.Sc. Thesis	On-robot Deep Reinforcement Learning for Quadruped Locomotion	Kinzel J.	Nico Bohlinger
B.Sc. Thesis	Diminishing Return of Value Expansion Methods in Offline Model-Based Reinforcement Learning	Dennert D.
B.Sc. Thesis	Diminishing Return of Value Expansion Methods in Discrete Model-Based Reinforcement Learning	Ahmad F.
RL:IP.SS24	Training Large Scale Robot Transformer Models	Scherer C.	Tim Schneider & Theo Gruner & Maximilian Tölle
RL:IP.SS24	XXX: eXploring X-Embodiment with RT-X	Jacobs T.	Tim Schneider & Theo Gruner & Maximilian Tölle
RL:IP.SS24	Unveiling the Unseen: Tactile Perception and Reinforcement Learning in the Real World	Böhm A., Krämer E.	Tim Schneider & Theo Gruner
RL:IP.WS23/24	XXX: eXploring X-Embodiment with RT-X	Dennert D., Scherer C., Ahmad F.	Tim Schneider & Theo Gruner & Maximilian Tölle
RL:IP.WS23/24	XXX: eXploring X-Embodiment with RT-X	Jacobs T.	Tim Schneider & Theo Gruner & Maximilian Tölle
RL:IP.WS23/24	Unveiling the Unseen: Tactile Perception and Reinforcement Learning in the Real World	Böhm A., Pfenning I., Lenz J.	Tim Schneider & Theo Gruner
RL:IP.SS23	Latent Tactile Representations for Model-based RL	Krämer E.	Tim Schneider & Theo Gruner