Yihan Du
Papers
1
Total Citations
2
H-Index
1
About
Yihan Du is a rising researcher in reinforcement learning (RL), with a focus on risk-sensitive and safe decision-making under uncertainty. Her work addresses a critical gap in RL: ensuring that agents not only maximize rewards but also avoid catastrophic outcomes. In her highly regarded 2022 paper, "Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path," Du introduces a novel formulation called Iterated CVaR RL, which aims to maximize the tail of the reward-to-go at each step, providing tight control over risk at every stage. This work lays foundational theory for risk-aware RL, offering provable efficiency guarantees. While her citation count is still growing, her contributions are already recognized as pioneering in the emerging area of risk-sensitive sequential decision-making. Du’s research is particularly impactful for applications where safety is paramount, such as autonomous driving, finance, and healthcare. Her ability to blend rigorous theoretical analysis with practical risk considerations marks her as a promising voice in the next generation of RL researchers, pushing the field beyond simple reward maximization toward more robust, trustworthy AI systems.
Research Focus
Key Achievements
Top Papers
- 1