Xiaoyue Wan
Papers
1
Total Citations
20
H-Index
1
About
Xiaoyue Wan is a researcher at the forefront of safe reinforcement learning and its critical applications in network security. Her work addresses a fundamental challenge in deploying AI in high-stakes environments: how to enable autonomous agents to learn effectively without causing catastrophic failures during exploration. In her highly cited 2019 paper, "Reinforcement Learning with Safe Exploration for Network Security," Wan proposed a novel algorithm that balances learning efficiency with strict safety constraints, preventing dangerous actions that could lead to network outages or large-scale privacy breaches. This contribution, which has garnered 20 citations, is foundational for the practical deployment of RL in real-world security systems. By tackling the tension between exploration and safety, Wan’s research directly impacts the development of resilient, self-learning defenses against evolving cyber threats. Her work is essential reading for students and researchers interested in bridging reinforcement learning theory with robust, real-world safety-critical applications.
Research Focus
Key Achievements
Top Papers
- 1Reinforcement Learning with Safe Exploration for Network Security20 citations · 2019