Skip to yearly menu bar Skip to main content


Online Control with Adversarial Disturbances

Naman Agarwal · Brian Bullins · Elad Hazan · Sham Kakade · Karan Singh

Pacific Ballroom #155

Keywords: [ Theory and Algorithms ] [ Planning and Control ] [ Online Learning ]


We study the control of linear dynamical systems with adversarial disturbances, as opposed to statistical noise. We present an efficient algorithm that achieves nearly-tight regret bounds in this setting. Our result generalizes upon previous work in two main aspects: the algorithm can accommodate adversarial noise in the dynamics, and can handle general convex costs.

Live content is unavailable. Log in and register to view live content