Block Course, 06.10.2025 - 10.10.2025, 9:00-18:00
Lecturers: Prof. Dr. Joschka Boedecker (Uni Freiburg), Prof. Dr. Moritz Diehl (Uni Freiburg), Prof. Dr. Sebastien Gros (NTNU Trondheim)
Exercises: Leonard Fichtner, Andrea Ghezzi and Jasper Hoffmann
Contacts: for any questions feel free to contact us mpcrl@cs.uni-freiburg.de.
Locations: Kollegiengebäude I, HS 1199, Platz der Universität 3, 79098 Freiburg, Google Maps
Event announcement: MPCRL25
Download our flyer and feel free to share it!
Preliminary timetable
JB: Joschka Boedecker, MD: Moritz Diehl, SG: Sebastien Gros, LF: Leonard Fichtner, AG: Andrea Ghezzi, JH: Jasper Hoffmann
Monday 6.10. | Tuesday 7.10. | Wednesday 8.10. | Thursday 9.10. | Friday 10.10. | |
---|---|---|---|---|---|
9:00 | Lecture 1 - Introduction to RL (JB) Markov Decision Process, Dynamic Programming, Bellman equation, Value function, Q function, Policy and value iteration | Lecture 4 (MD) MPC cont’d from linear to nonlinear MPC; sensitivity computation and implicit function theorem | Lecture 6 - Synthesis of MPC and RL (SG) Overview over Synthesis of MPC and RL | Lecture 8 (SG) RL + MPC Why does it work? | Lecture 10 (SG) AI for Decision Making |
10:30 | Coffee Break | ||||
11:00 | Lecture 2 - Introduction to Optimal Control (MD) Parallelism between DP and LQR; introduction to MPC; basics of numerical optimization for control | Exercise Acados interface + basic MPC with acados + DiffMPC layer with leap-c | Lecture 7 - An MPC prior for SAC (JH, LF) Integrating MPC into actor-critic methods with leap-c | Project Work / Tutorials | Project presentation |
12:30 | Lunch Break | ||||
14:00 | Lecture 3 - Actor-Critic Methods (JB) Temporal Difference, Actor-Critic Methods, Soft Actor-Critic | Lecture 5 (MD, AG, JH) Imitation Learning from MPC | Exercise MPC prior for SAC using leap-c | Lecture 9 TBA | Project presentation |
15:30 | Coffee Break | ||||
16:00 - 17:30 | Exercise Basics in PyTorch and Actor Critic methods | Exercise Imitation learning + Q&A on software | Project Work / Tutorials | Project Work / Tutorials | Free |
17:30 | Project Pitches | ||||
19:00 | Welcome reception | Dinner with participants |
Course topics (may be subject to updates)
- Dynamic Programming (DP) concepts and algorithms - value iteration and policy iteration
- Linear Quadratic Regulator (LQR) and Riccati equations
- Dynamic Systems: Simulation and Optimal Control
- Markov Decision Processes (MDP)
- Reinforcement Learning (RL) formulations and approaches
- Nonlinear Model Predictive Control
- When to use RL in MPC?
- Differentiable MPC within Actor-Critic methods
- Closed-loop tuning of MPC with RL
- Overview of possible synergies between MPC and RL
For details regarding registration checkout the event page MPCRL25
Formal requirements
Relevant only for students of the university of Freiburg.
In order to receive 3 ECTS for this course, students need to pass all of the following:
- Studienleistung (SL, ungraded)
- Participation in the exercise session
- Prüfungsleistung (PL, graded)
- Project report
Every student from the University of Freiburg needs to fill out the registration form.
Please also read the project instructions from above.
On the first day (October 6th), students further need to decide whether they want to commit themselves to do the PL. The registration will take via the PL registration form below.