Zhuoran Li

Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training

Reparameterization Proximal Policy Optimization

From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos

Beyond Shallow Behavior: Task-Efficient Value-Based Multi-Task Offline MARL via Skill Discovery

Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks