2 papers
cs.LG2026
Robust Reinforcement Learning for Dynamic Treatment Regimes under Model and Measurement Uncertainty
Chengze Xie, Xuan Wang, Ying Ding +2
We develop a robust reinforcement learning (RL) framework for learning adaptive treatment policies that generalize across patients and remain reliable under errors in the measured…
math.OC2026
(Cheap) Stochastic Policy Gradient Converges with High Probability for Linear Quadratic Regulator
Yan Li, Chengze Xie
We study the convergence of the vanilla stochastic policy gradient method applied to the linear quadratic regulator (LQR) problem. The method is cheap in the following sense: (1) a…