- preprint
Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning
Zhancun Mu, Guangyu Zhao, Yiwu Zhong, Chi Zhang†
Preprint • 2026
- conference
DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction
Zhancun Mu, Chi Zhang
NeurIPS 2026 • 2026