Zihan Zhang

Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^{\pi}$ Realizability for Deterministic Dynamics

Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback

Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO

Plug-in Sample Complexity For Constrained Reinforcement Learning

Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs

Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits

Deployment Efficient Reward-Free Exploration with Linear Function Approximation

Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback

Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback

Deployment Efficient Reward-Free Exploration with Linear Function Approximation