Songyuan Zhang

ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation

Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning

Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control

HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems

Distributed Epigraph Form Multi-Agent Safe Reinforcement Learning