Online Control with Adversarial Disturbances
Naman Agarwal ⋅ Brian Bullins ⋅ Elad Hazan ⋅ Sham Kakade ⋅ Karan Singh
2019 Poster
Abstract
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.
Chat is not available.
Successful Page Load