Asaf B Cassel

Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt$T Regret

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 b…