Seminar on Theoretical Machine Learning

Topic: Online Control with Adversarial Disturbances

Speaker: Naman Agarwal

Affiliation: Online Control with Adversarial Disturbances

Date & Time: Monday February 11th, 2019, 12:15pm - 1:45pm

Location: White Levy Room

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that has full knowledge of the disturbances in hindsight. Our main result is an efficient algorithm that provides nearly tight regret bounds for this problem. From a technical standpoint, this work generalizes upon previous work in that our model allows for adversarial noise in the dynamics and allows for general convex costs.