Skip to main content

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

Publication ,  Journal Article
Zhou, M; Lu, J
Published in: Journal of Machine Learning Research
January 1, 2023

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(ε1 log(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.

Duke Scholars

Published In

Journal of Machine Learning Research

EISSN

1533-7928

ISSN

1532-4435

Publication Date

January 1, 2023

Volume

24

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4905 Statistics
  • 4611 Machine learning
  • 17 Psychology and Cognitive Sciences
  • 08 Information and Computing Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhou, M., & Lu, J. (2023). Single Timescale Actor-Critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees. Journal of Machine Learning Research, 24.
Zhou, M., and J. Lu. “Single Timescale Actor-Critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees.” Journal of Machine Learning Research 24 (January 1, 2023).
Zhou, M., and J. Lu. “Single Timescale Actor-Critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees.” Journal of Machine Learning Research, vol. 24, Jan. 2023.

Published In

Journal of Machine Learning Research

EISSN

1533-7928

ISSN

1532-4435

Publication Date

January 1, 2023

Volume

24

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4905 Statistics
  • 4611 Machine learning
  • 17 Psychology and Cognitive Sciences
  • 08 Information and Computing Sciences