Fei Fang
Papers
2
Total Citations
24
H-Index
2
About
Fei Fang is a leading researcher in artificial intelligence, specializing in robust reinforcement learning (RL), game theory, and multi-agent systems. Her work addresses critical challenges in deploying RL agents in real-world environments, where model errors and adversarial attacks can undermine performance. Fang’s most notable contribution is her pioneering framework, Robust Adversarial Reinforcement Learning (RARL), which she reformulated as a Stackelberg game through adaptively-regularized adversarial training. This approach, detailed in her highly cited 2022 paper (22 citations), enhances agent resilience by dynamically balancing robustness and performance, offering a principled solution to a long-standing problem in RL. Her research has profound implications for safety-critical applications, such as autonomous driving and cybersecurity, where reliable decision-making under uncertainty is paramount. Fang’s work is widely recognized for its theoretical depth and practical impact, earning her a reputation as a thought leader in robust AI. With over 20 citations on her key paper alone, she continues to shape the future of trustworthy artificial intelligence, inspiring students and researchers to explore the intersection of game theory and machine learning for more resilient systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2