Xin Liu

Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov Framework

Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference Optimization

An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints

On Stochastic Contextual Bandits with Knapsacks in Small Budget Regime

Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization

Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints