Online Control with Adversarial Disturbances
Naman Agarwal · Brian Bullins · Elad Hazan · Sham Kakade · Karan Singh

Thu Jun 13th 10:00 -- 10:05 AM @ Room 102

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.

Author Information

Naman Agarwal (Google AI Princeton)
Brian Bullins (Princeton University)
Elad Hazan (Princeton University)
Sham Kakade (University of Washington)
Karan Singh (Princeton University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors