KL-Regularized Policy Iteration for Adaptive LQR: Gain Updates and Probing from One Policy Improvement
math.OC, cs.SY, eess.SY
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/marginallyunstable/klpi4alqr
Terminology
Sources
- Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches
- LQR through the Lens of First Order Methods: Discrete-time Case
- Data-Enabled Policy Optimization for Direct Adaptive Learning of the LQR
- Fast Policy Learning for Linear Quadratic Control with Entropy Regularization
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise