mlsanityData to 14 Oct 2026

Power-Constrained Policy Gradient Methods for LQR

arXiv 2507.15806 ↗First posted 21 Jul 2025math.OCcited by 0

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

Consider a discrete-time Linear Quadratic Regulator (LQR) problem solved using policy gradient descent when the system matrices are unknown. The gradient is transmitted across a noisy channel over a finite time horizon using analog communication by a transmitter with an average power constraint. This is a simple setup at the intersection of reinforcement learning and networked control systems. We first consider a communication-constrained optimization framework, where gradient descent is applied to optimize a non-convex function under noisy gradient transmission. We provide an optimal power allocation algorithm that minimizes an upper bound on the expected optimality error at the final iteration and show that adaptive power allocation can lead to better convergence rate as compared to standard gradient descent with uniform power distribution. We then apply our results to the LQR setting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 26 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

13 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Model-Free Learning for the Linear Quadratic Regulator over Rate-Limited Channels2 Jan

Other references · 12

  1. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  2. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 539
  3. 2018Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulatorcited by 250
  4. 2019Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communicationcited by 221
  5. 2021Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolationcited by 132
  6. 2018Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systemscited by 67
  7. 2020SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolationcited by 67
  8. 2021Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraintscited by 36
  9. 2021Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regretcited by 12
  10. 2020Gradient Statistics Aware Power Control for Over-the-Air Federated Learningcited by 6
  11. 2021Fundamental limits of over-the-air optimization: Are analog schemes optimal?cited by 3
  12. 2017Universal gradient descentcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches
  2. 2025Sample-Efficient Model-Free Policy Gradient Methods for Stochastic LQR via Robust Linear Regression
  3. 2024Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens
  4. 2025Second-Order Policy Gradient Methods for the Linear Quadratic Regulator
  5. 2026A Stochastic Gradient Descent Approach to Design Policy Gradient Methods for LQR
  6. 2025Convergence Guarantees of Model-free Policy Gradient Methods for LQR with Stochastic Data
  7. 2026Gradient Dominance in the Linear Quadratic Regulator: A Unified Analysis for Continuous-Time and Discrete-Time Systems
  8. 2025On the Robustness of Derivative-free Methods for Linear Quadratic Regulator