Yunfan Li

Near-Optimal Sample Complexity for Online Constrained MDPs

Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design

Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning

Low-Switching Primal-Dual Algorithms for Safe Reinforcement Learning

Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning

DEXR: A Unified Approach Towards Environment Agnostic Exploration