Lei Ying

Provable Policy Optimization for Reinforcement Learning from Trajectory Preferences with an Unknown Link Function

Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation

Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets

Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference

Rethinking Behavior Regularization in Offline Safe RL: A Region-Based Approach