Abstract

We study the problem of regret minimization in partially observable linear quadratic control systems when the model dynamics are unknown a priori. We propose ExpCommit, an explore-then-commit algorithm that learns the model Markov parameters and then follows the principle of optimism in the face of uncertainty to design a controller. We propose a novel way to decompose the regret and provide an end-to-end sublinear regret upper bound for partially observable linear quadratic control. Finally, we provide stability guarantees and establish a regret upper bound of $\mathcalO(T^2/3)$ for ExpCommit, where $T$ is the time horizon of the problem.

Description

[2002.00082] Regret Minimization in Partially Observable Linear Quadratic Control

Links and resources

Tags

community

  • @kirk86
  • @dblp
@kirk86's tags highlighted