Qiyang Li

EXPO: Stable Reinforcement Learning with Expressive Policies

Decoupled Q-Chunking

Q-Learning with Adjoint Matching

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

Reinforcement Learning with Action Chunking

Flow Q-Learning

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration