Processing math: 100%

Single Timescale Actor-Critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees

Mo Zhou, Jianfeng Lu.

Year: 2023, Volume: 24, Issue: 222, Pages: 1−34


Abstract

We propose a single timescale actor-critic algorithm to solve the linear quadratic regulator (LQR) problem. A least squares temporal difference (LSTD) method is applied to the critic and a natural policy gradient method is used for the actor. We give a proof of convergence with sample complexity O(ε1log(ε1)2). The method in the proof is applicable to general single timescale bilevel optimization problems. We also numerically validate our theoretical results on the convergence.

PDF BibTeX code