Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics

03/02/2022

∙

by   Asaf Cassel, et al.

∙

3

∙

share

We consider the problem of controlling an unknown linear dynamical system under a stochastic convex cost and full feedback of both the state and cost function. We present a computationally efficient algorithm that attains an optimal √(T) regret-rate against the best stabilizing linear controller. In contrast to previous work, our algorithm is based on the Optimism in the Face of Uncertainty paradigm. This results in a substantially improved computational complexity and a simpler analysis.