skip to main content

Control Meets Learning Seminar

Wednesday, June 9, 2021
9:00am to 10:00am
Add to Cal
Online Event
Control has met learning: Aspirational lessons from adaptive control theory
Miroslav Krstic, Distinguished Professor of Mechanical and Aerospace Engineering, Director, Center for Control Systems and Dynamics, UC San Diego,

Adaptive control is a field thanks to whose six decades of activity many challenges in combining feedback control with online learning have been either overcome or understood to be insurmountable. As such, the results in this field are not only a veritable checklist of properties that future learning-based control methods, including those related to reinforcement learning, should strive to guarantee, but also a checklist of properties demonstrated or deemed hopeless. I will touch on learning-based feedback designs across the entire spectrum in terms of reliance on models - from the conventional model-based adaptive control, to non-model-based RL, to the entirely model-free "extremum seeking." I focus on fundamental questions but illustrate them with examples from robotics, aquatic locomotion, road traffic, and semiconductor manufacturing.

For more information, please contact Jolene Brink by email at [email protected] or visit Control Meets Learning Website.