mlsanityData to 7 Oct 2026

Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient

arXiv 2302.13144 ↗First posted 25 Feb 2023math.OC cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We revisit in this paper the discrete-time linear quadratic regulator (LQR) problem from the perspective of receding-horizon policy gradient (RHPG), a newly developed model-free learning framework for control applications. We provide a fine-grained sample complexity analysis for RHPG to learn a control policy that is both stabilizing and ε-close to the optimal LQR solution, and our algorithm does not require knowing a stabilizing control policy for initialization. Combined with the recent application of RHPG in learning the Kalman filter, we demonstrate the general applicability of RHPG in linear control and estimation with streamlined analyses.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 25 Feb 2023.

Builds on

16 of 30 references.

References · 16

  1. 2018Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulatorcited by 211
  2. 2013Optimal rates for zero-order convex optimization: the power of two function evaluationscited by 190
  3. 2019On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shiftcited by 174
  4. 2019Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policiescited by 117
  5. 2015An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedbackcited by 105
  6. 2018Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systemscited by 56
  7. 2020Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizoncited by 43
  8. 2019Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approachcited by 33
  9. 2019LQR through the Lens of First Order Methods: Discrete-time Casecited by 30
  10. 2021Stabilizing Dynamical Systems via Policy Gradient Methodscited by 24
  11. 2021Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Controlcited by 23
  12. 2019Learning the Globally Optimal Distributed LQ Regulatorcited by 19
4 more
  1. 2021Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexitycited by 15
  2. 2023Learning the Kalman Filter with Fine-Grained Sample Complexitycited by 9
  3. 2022Towards a Theoretical Foundation of Policy Optimization for Learning Control Policiescited by 6
  4. 2021Learning Stabilizing Controllers of Linear Systems via Discount Policy Gradientcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 5; 2025: 1.

9 papers.

  1. 2024Decision Transformer as a Foundation Model for Partially Observable Continuous Controlcited by 5
  2. 2023Global Convergence of Receding-Horizon Policy Search in Learning Estimator Designscited by 4
  3. 2023Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithmscited by 4
  4. 2023Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergencecited by 3
  5. 2024Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspectivecited by 2
  6. 2024Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Gamescited by 2
  7. 2024Policy Optimization for PDE Control with a Warm Startcited by 1
  8. 2024Structure Matters: Dynamic Policy Gradientcited by 1
  9. 2025Sample Complexity of Linear Quadratic Regulator Without Initial Stabilitycited by 0