Training Dynamics and Induced Preconditioning of ReLU Policy Gradient for Scalar LQR

arXiv:2604.22138 · math.OC, cs.SY, eess.SY · Submitted 2026-04-24 · Read on arXiv

math.OC, cs.SY, eess.SY

Submitted: 2026-04-24

Updated: 2026-09-25

Terminology

• Benchmark — 2× in this paper · explained in 2 episodes
• Gradient Flow — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Degeneracy — 1× in this paper · explained in 3 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Sample Complexity — 1× in this paper · explained in 15 episodes

Sources

• Sample-Efficient Model-Free Policy Gradient Methods for Stochastic LQR via Robust Linear Regression
• Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Online Control via Counterfactual Tracking
• Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability
• Petrov-Galerkin operator inference with application to stability-encouraging identification