Monday, October 06, 2025, 9:00 - Friday, October 10, 2025, 17:00

HS 1199, Kollegiengebäude I, Platz der Universität 3, D-79098 Freiburg

​Lecturers: Prof. Dr. Joschka Boedecker (Uni Freiburg), Prof. Dr. Moritz Diehl (Uni Freiburg)

Exercises: Leonard Fichtner, Andrea Ghezzi, Jasper Hoffmann

Contacts: for any questions feel free to contact  mpcrl@cs.uni-freiburg.de

Locations: Kollegiengebäude I, HS 1199, Platz der Universität 3, D-79098 Freiburg, Google Maps 
(Historic University building in the city center)

After a one-year break, we are excited to announce the fourth edition of this block course, building on the success of the previous editions (MPCRL23, MPCRL22, MPCRL21)!

This comprehensive course spans 5 days, in the first two days we will cover the foundation of both MPC and RL, and the in the remainder of the week we want to focus on the combination of MPC and RL.

The program will follow (approximately) the topics covered in our recent survey paper.

Lectures will be supported with intensive exercise/programming sessions. 

Ultimately, the participants will work on their own project in the domain of MPC / RL helped by the professors and the tutors. The project work can be an exciting opportunity to share ideas and collaborate with other participants.

Many projects developed in the past has led to peer-review publications!

In the exercises we will teach how to use our state-of-the-art software packages

• acados: Fast and embedded solvers for nonlinear optimal control.
• leap-c: Framework for efficient combination of MPC and RL using acados.

Registration will open soon!

Registration: within August 31, 2025, until the limit of 60 participants is reached (first come first served). The registration is recorded after the fee has been transferred and received.

Participation fee: 350 EUR (free of charge for master’s students from the University of Freiburg). The fee includes a welcome reception and a dinner with the participants. 

Cancellation policy: no refund possible.

Course topics

• 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

Checkout our teaching page!

Targeted audience

This block course is intended for master students and PhD students from engineering, computer science, mathematics, physics, and other mathematical sciences. 

For interested Master students:

• We accept registration only from master student from the University of Freiburg
• We strongly recommend the students to have taken: (Numerical Optimal or Numerical Optimal Control) or (Reinforcement Learning) courses
• The evaluation of the course will be based on the exercise sessions and the project works. Further details on evaluation will be published soon!

This course has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 953348.