Place: Seminar Room KC 3N27
Contact: anders [dot] rantzer [at] control [dot] lth [dot] se
Save event to your calendar
Recently, there has been a surge of interest in studying the Linear
Quadratic Regulator (LQR) problem within the online learning community.
One of the main goals often considered by this community is to devise
learning algorithms and study their so-called regret. In this talk, I
will attempt to provide a comprehensive discussion on recent work on the
LQR problem from the online learning community. I will also present some
of our recent work on this topic where we devise a new learning
algorithm and provide guarantees on its expected regret. I will further
highlight the many desirable properties that our algorithm enjoys in
contrast with existing ones, notably from an algorithm design
perspective, where we allow our algorithm to update its policy
continuously. On a technical level, achieving a simple algorithm while
retaining strong regret guarantees poses serious challenges. We are able
to tackle these challenges by carefully leveraging recent tools from
random matrix theory and self-normalized processes.
Presented by Yassir Jedra from the Division of Decision and Control Systems at KTH
In 2020, we moved to temporary offices at KC4 in Kemicentrum. Here we will stay until 2023 while the M-building is being renovated. See "contact" (in About) for the new visiting adress.