2 papers
math.OC2026
Hidden Star-Convexity in Policy Optimization for Gain-Scheduled LQR: Extended Version
Shiva Shakeri, Péter Baranyi, Mehran Mesbahi
We study policy optimization for gain-scheduled linear quadratic regulation, where one schedule of gains, interpolated through fixed weighting functions, is optimized against a fam…
eess.SY2026
Receding-Horizon Policy Gradient for Polytopic Controller Synthesis
Shiva Shakeri, Péter Baranyi, Mehran Mesbahi
We propose the Polytopic Receding-Horizon Policy Gradient (P-RHPG) algorithm for synthesizing Parallel Distributed Compensation (PDC) controllers via Tensor Product (TP) model tran…