Haoran Xu

Sample Efficient Offline RL via T-Symmetry Enforced Latent State-Stitching

Reinforcement Learning via Value Gradient Flow

Information-Theoretic Reward Decomposition for Generalizable RLHF

Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization

The Belief State Transformer

An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning

Pushing the Limit of Small-Efficient Offline Reinforcement Learning