Nico Bohlinger
Research Interests
Reinforcement Learning, Robotics, Morphology-aware and Multi-Embodiment Learning, Active Learning, Intrinsic Motivation, Locomotion
Affiliation
TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
Contact
nico.bohlinger@tu-darmstadt.de
Room E327, Building S2|02, TU Darmstadt, FB-Informatik, FG-IAS, Hochschulstr. 10, 64289 Darmstadt
+49-6151-16-25380
Nico Bohlinger joined the Intelligent Autonomous System lab on July 15, 2023, as a PhD student.
He is working on multi-embodiment and morphology-aware robot learning by applying Deep Reinforcement Learning (DRL) and developing novel neural network architectures and learning frameworks.
His main robot platforms are currently the Unitree H1 humanoid and the Unitree A1, Unitree Go2 and MAB Silver Badger quadrupeds.
Nico holds a bachelor's degree in Business Informatics from the Offenburg University of Applied Sciences and a master's degree in Bioinformatics from the Goethe University Frankfurt.
He was previously part of the RoboCup teams Magma and Sweaty in Offenburg and developed DRL environments to learn complex soccer skills; here is a recent interview with him in German.
Furthermore, he is developing the research-focused DRL framework RL-X.
Publications
Conferences
- Ai, B.; Dai, L.; Bohlinger, N.; Li, D.; Mu, T.; Wu, Z.; Fay, K.; Christensen, H.I.; Peters, J.; Su, H. (2025). Towards Embodiment Scaling Laws in Robot Locomotion, Under review.
- Bohlinger, N.; Kinzel, J.; Palenicek, D.; Antczak, L.; Peters, J. (2025). Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion, Under review.
- Stasica, M.; Bick, A.; Bohlinger, N.; Mohseni, O.; Fritzsche, J.; Hübler, C.; Peters, J.; Seyfarth, A. (2025). Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations, Under review.
- Bohlinger, N.; Peters, J. (2025). Massively Scaling Explicit Policy-conditioned Value Functions, Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM).
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2025). Morphology-Aware Legged Locomotion with Reinforcement Learning, German Robotics Conference (GRC).
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2024). One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion, Conference on Robot Learning (CoRL).
Workshops & Symposia
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2025). Learning Robot Locomotion for Multiple Embodiments, The 12th International Symposium on Adaptive Motion of Animals and Machines and 2nd LokoAssist Symposium (AMAM).
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2024). One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion, CoRL 2024 Workshop on Morphology-Aware Policy and Design Learning Workshop.
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2024). One Policy to Run Them All: Towards an End-to-end Learning Approach to Multi-Embodiment Locomotion, RSS 2024 Workshop on Embodiment-Aware Robot Learning.
- Bohlinger, N.; Tateo, D.; Kicki, P.; Walas, K.; Peters, J. (2024). Benefits of an Actuated Spine in Agile Quadruped Locomotion, ICRA 2024 Workshop on Bio-inspired Robotics and Robotics for Biology.
- Bohlinger, N.; Dorer, K. (2023). RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup, RoboCup 2023: Robot World Cup XXVI, Springer-Verlag.
Others
- Bohlinger, N. (2023). Intrinsically Motivated Agents for Goal Discovery in High Dimensional State Spaces, Master Thesis.
- Bohlinger, N.; Braun, H.; Dorer, K.; Ehlers, L.; Huber, D.; Huber, H.; Glaser, S.; Schillings, R.; Scholz, J.; Wolffram, M. (2022). The magmaOffenburg 2022 RoboCup 3D Simulation Team.
Supervised Theses and Projects
| Thesis/Project | Topic | Student(s) | Together with |
| M.Sc. Thesis | Starting State Proposal for Efficient Deep Reinforcement Learning | Michelle Shaia | Aryaman Reddi |
| M.Sc. Thesis | Embodiment Adaptive Control | Dichen Li @ UC San Diego | Bo Ai |
| M.Sc. Thesis | On-robot Deep Reinforcement Learning for Quadruped Locomotion | Jonathan Kinzel | Daniel Palenicek |
| M.Sc. Thesis | Gait Analysis of Quadruped Robots during Vertical Ground Perturbations | Arne Bick | Maximilian Stasica, Omid Mohseni |
| Robot Learning: Integrated Project | Learning Torque Control for Quadrupeds | Daniel Schmidt, Lina Gaumann | |
| Robot Learning: Integrated Project | Student-Teacher Learning for simulated Quadrupeds | Keagan Holmes, Oliver Griess, Oliver Grein | |
| Expert Project in Robot Learning | Deep Reinforcement Learning with the Unitree Go2 robot in MJX | Leon Magnus | Oleg Arenz |
| Humanoid Robotics Seminar | Reinforcement Learning for Humanoid Locomotion | Qiao Sun |
Others
- Reviewed for: ICRA 2024, IROS 2024, ICRA 2025, IROS 2025, CoRL 2025
- TA for: Robot Learning SS24, Probabilistic Methods in Computer Science WS24/25