Jiheng Zhang

ONLINE RANKING WITH UNFAIR FEEDBACK AND HUMAN VERIFICATION: HIERARCHICAL ELIMINATION AND REGRET BOUNDS

Make Optimization Once and for All with Fine-grained Guidance

Single-Trajectory Distributionally Robust Reinforcement Learning

Robustify the Latent Space: Offline Distributionally Robust Reinforcement Learning with Linear Function Approximation

Improved Regret Bounds in Stochastic Contextual Bandits with Graph Feedback

Provably Efficient Learning in Partially Observable Contextual Bandit