Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret

Asaf Cassel · Tomer Koren

[ Abstract ] [ Livestream: Visit Reinforcement Learning Theory 1 ] [ Paper ]
Wed 21 Jul 6:25 a.m. — 6:30 a.m. PDT

We consider the task of learning to control a linear dynamical system under fixed quadratic costs, known as the Linear Quadratic Regulator (LQR) problem. While model-free approaches are often favorable in practice, thus far only model-based methods, which rely on costly system identification, have been shown to achieve regret that scales with the optimal dependence on the time horizon T. We present the first model-free algorithm that achieves similar regret guarantees. Our method relies on an efficient policy gradient scheme, and a novel and tighter analysis of the cost of exploration in policy space in this setting.

Chat is not available.