Sie sind hier: Startseite › People › Jasper Hoffmann

Jasper Hoffmann

PhD Student

Jasper 

Contact

Institut für Informatik
Albert-Ludwigs-Universität
Freiburg Georges-Koehler-Allee 201
79110 Freiburg im Breisgau

Interests

  • Rare Events
  • Distributional Reinforcement Learning
  • Model Predictive Control
  • Autonomous Driving
  • Active Learning

Teaching

  • TA MPCRL Seasonal School, Winter 26/27
  • TA MPCRL Seasonal School, Winter 25/26
  • TA Reinforcement Learning, Winter 24/25
  • TA MPCRL Seasonal School, Summer 23
  • TA Seminar & Proseminar, Summer 23
  • TA Reinforcement Learning, Winter 22/23
  • TA MPCRL Seasonal School, Summer 22
  • TA Q-learning Proseminar, Summer 22
  • TA Reinforcement Learning, Winter 21/22
  • TA MPCRL Seasonal School, Summer 21

Publications

2026

Seyed Mahdi B. Azad, Jasper Hoffmann, Iman Nematollahi, Hao Zhu, Abhinav Valada, Joschka Boedecker. Spectral Alignment in Forward-Backward Representations via Temporal Abstraction. 2026. arxiv

Julien Brosseit, Jasper Hoffmann, Joschka Boedecker. Mind the Budget: Accelerating Deep Reinforcement Learning using Constrained Early Exit Neural Networks. International Conference on Machine Learning (ICML). 2026.

Jasper Hoffmann*, Dirk Reinhardt*, Harald Taxt Walnum, Leonard Fichtner, Anna Rothenhäusler, Joschka Bödecker, Sebastien Gros. Model Predictive Control and Deep Reinforcement Learning in the House. IEEE Conference on Control Technology and Applications (CCTA). 2026.

Fünfgeld, H., Christen, A., Briegel, F., Schrodi, S., Speidel, A., Felder, C., Hoffmann, J., Irscheid, L., Merkle, D., Meyer, J. and Schindler, D. Optimizing urban greening and densification in the context of outdoor heat: Opportunities for AI-supported urban adaptation. Landscape and Urban Planning, 268, p.105574. 2026.

Hao Zhu, Jasper Hoffmann, Baohe Zhang, Joschka Boedecker. Fitting reinforcement learning model to behavioral data under bandits. Frontiers in Applied Mathematics and Statistics, 12, p.1762084. 2026.

2025

Akhil S Anand, Shambhuraj Sawant, Jasper Hoffmann, Dirk Reinhardt, Sebastien Gros. Closing the Sim2Real Performance Gap in RL. Reinforcement Learning Conference (RLC). 2026. arxiv

 Hao Zhu, Shengchao Yan, Jasper Hoffmann, and J. Boedecker. Multi-convex Programming for Discrete Latent Factor Models Prototyping. 2025. arxiv

Rudolf Reiter*, Jasper Hoffmann*, Dirk Reinhardt, Florian Messerer, Katrin Baumgärtner, Shamburaj Sawant, Joschka Boedecker, Moritz Diehl, Sebastien Gros. Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification. Annual Reviews in Control, 61, p.101045. 2026. arxiv

Jonathan Frey, Katrin Baumgärtner, Gianluca Frison, Dirk Reinhardt, Jasper Hoffmann, Leonard Fichtner, Sebastien Gros, Moritz Diehl. Differentiable Nonlinear Model Predictive Control. 2025. arxiv

Meyer J, Hoffmann J, Schulz F, Merkle D, Buescher D, Reiterer A, Boedecker J, Burgard W. Label-Efficient Point Cloud Segmentation with Active Learning. arXiv preprint arXiv:2512.05759. 2025.

2024

Felix Schulz*, Jasper Hoffmann*, Yuan Zhang and Joschka Boedecker. Learning When to Trust the Expert for Guided Exploration in RL. ICML Workshop on Foundations of RL and Control (FoRLaC). 2024. openreview

Rudolf Reiter, Andrea Ghezzi, Katrin Baumgärtner, Jasper Hoffmann, Robert D. McAllister and Moritz Diehl. AC4MPC: Actor-Critic Reinforcement Learning for Nonlinear Model Predictive Control. 2024. arxiv

Yuan Zhang, Jasper Hoffmann and Joschka Boedecker. UDUC: An Uncertainty-driven Approach for Learning-based Robust Control. 27th European Conference on Artificial Intelligence (ECAI). 2024. arxiv

Jasper Hoffmann, Diego Fernandez, Julien Brosseit, Julian Bernhard, Klemens Esterle, Moritz Werling, Michael Karg, and Joschka Boedecker. PlanNetX: Learning an Efficient Neural Network Planner from MPC for Longitudinal Control. 6th Annual Learning for Dynamics & Control Conference (L4DC). 2024. arxiv

2023

Andrea Ghezzi*, Jasper Hoffman*, Jonathan Frey, Joschka Boedecker, Moritz Diehl. Imitation Learning from Nonlinear MPC via the Exact Q-Loss and its Gauss-Newton Approximation. Proceedings of the IEEE Conference on Decision and Control (CDC). 2023. arxiv

Rudolf Reiter, Jasper Hoffmann, Joschka Boedecker and Moritz Diehl. A Hierarchical Approach for Strategic Motion Planning in Autonomous Racing. European Control Conference (ECC). 2023. arxiv

2021

Jasper Hoffmann*, Shashank Agnihotri*, Tonmoy Saikia, Thomas Brox. Towards improving robustness of compressed CNNs. ICML Workshop on Uncertainty and Robustness in Deep Learning (UDL). 2021. web