2 papers
q-fin.RM2025
Robust Bayesian Dynamic Programming for On-policy Risk-sensitive Reinforcement Learning
Shanyu Han, Yangbo He, Yang Liu
We propose a novel framework for risk-sensitive reinforcement learning (RSRL) that incorporates robustness against transition uncertainty. We define two distinct yet coupled risk m…
stat.ME2025
Covariate Balancing Value Estimation for Optimal Individualized Treatment Rules
Yue Zhang, Shanshan Luo, Zhi Geng +1
Learning an optimal individualized treatment rule depends on reliable value comparisons across the candidate class. Standard doubly robust estimators are consistent when either the…