Wenjun Zou
Papers
1
Total Citations
14
H-Index
1
About
Wenjun Zou is a rising researcher in safe reinforcement learning (RL), with a focus on bridging theoretical guarantees and real-world deployment in safety-critical systems like robotics. Their most-cited work, “Safe Model-Based Reinforcement Learning With an Uncertainty-Aware Reachability Certificate” (2023, 14 citations), introduces a novel framework that integrates uncertainty quantification with reachability analysis to ensure constraint satisfaction during training. This approach reduces violations in model-based RL by providing formal safety certificates, addressing a key bottleneck in deploying RL in physical environments. Zou’s contributions lie at the intersection of control theory and machine learning, offering principled methods to balance exploration and safety. Their research is particularly impactful for applications where trial-and-error learning is costly or dangerous, such as autonomous navigation and manipulation. With growing recognition for advancing trustworthy AI, Zou’s work is shaping how researchers design RL algorithms that are not only efficient but also provably safe.
Research Focus
Key Achievements
Top Papers
- 1