Poster

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

Asaf Cassel · Tomer Koren

Keywords: [ RL, Decisions and Control Theory ]

[ Abstract ]
[ Paper ]
[ Visit Poster at Spot A4 in Virtual World ]
Wed 21 Jul 9 a.m. PDT — 11 a.m. PDT
 
Spotlight presentation: Reinforcement Learning Theory 1
Wed 21 Jul 6 a.m. PDT — 7 a.m. PDT

Abstract:

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.