Toward a Theoretical Foundation of Policy Optimization for Learning Control Policies

Bin Hu, Kaiqing Zhang, Na Li, Mehran Mesbahi, Maryam Fazel, Tamer Başar

Research output: Contribution to journalReview articlepeer-review

Abstract

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and reinforcement learning. This article surveys some of the recent developments on policy optimization, a gradient-based iterative approach for feedback control synthesis that has been popularized by successes of reinforcement learning. We take an interdisciplinary perspective in our exposition that connects control theory, reinforcement learning, and large-scale optimization. We review a number of recently developed theoretical results on the optimization landscape, global convergence, and sample complexityof gradient-based methods for various continuous control problems, such as the linear quadratic regulator (LQR), control, risk-sensitive control, linear quadratic Gaussian (LQG) control, and output feedback synthesis. In conjunction with these optimization results, we also discuss how direct policy optimization handles stability and robustness concerns in learning-based control, two main desiderata in control engineering. We conclude the survey by pointing out several challenges and opportunities at the intersection of learning and control.

Original languageEnglish (US)
Pages (from-to)123-158
Number of pages36
JournalAnnual Review of Control, Robotics, and Autonomous Systems
Volume6
DOIs
StatePublished - May 3 2023
Externally publishedYes

Keywords

  • feedback control synthesis
  • policy optimization
  • reinforcement learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Engineering (miscellaneous)
  • Human-Computer Interaction
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Toward a Theoretical Foundation of Policy Optimization for Learning Control Policies'. Together they form a unique fingerprint.

Cite this