Tangjie Lv

Reinforcement Learning from Imperfect Corrective Actions and Proxy Rewards

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model

Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets

Unlock the Intermittent Control Ability of Model Free Reinforcement Learning

Bayesian Offline-to-Online Reinforcement Learning : A Realist Approach

Addressing Real-Time Fragmentary Interaction Control Problems via Muti-step Representation Reinforcement Learning