After successful completion of the course, students are able to understand the advanced theory of reinforcement learning as well as to implement and to apply advanced reinforcement-learning algorithms to selected, realistic problems.

Theory and application of advanced reinforcement-learning algorithms, including in particular mathematical foundations and recent research results.

Online lecture and lecture notes.  In the tutorial part of the class, algorithms are implemented (recommended in Julia, but also in another language if desired) and later on presented together with relevant theory.

Tutorial part.  Oral and/or written exam (depending on number of participants).

VU Reinforcement Learning 101.789 or very good knowledge in reinforcement learning (in particular the textbook by Sutton & Barto).