Weixin Wang

Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action Set

Diffusion Posterior Sampling for Nonlinear Contextual Bandits

Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment

Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits

Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction