Papers
1
Total Citations
3
H-Index
1
About
Wei Hung is a rising researcher in reinforcement learning (RL), with a focus on solving complex decision-making problems under real-world constraints. His key research areas include action-constrained RL, policy optimization, and safe learning in interactive environments. Hung’s most notable contribution is his work on the Frank-Wolfe Policy Optimization framework, which addresses a critical limitation in action-constrained RL: the “zero gradient” problem. By replacing traditional projection-based methods with a Frank-Wolfe approach, he enables more efficient and stable learning in settings where actions must satisfy strict constraints, such as robotic control and networked scheduling. His 2021 paper on this topic has garnered attention for its theoretical rigor and practical relevance, earning citations from researchers working at the intersection of optimization and RL. Hung’s work is particularly valuable for students and practitioners seeking to deploy RL in safety-critical or resource-limited systems. Through his research, he is helping to bridge the gap between theoretical RL advances and real-world deployment, making him a promising voice in the next generation of AI researchers.
Research Focus
Key Achievements
Top Papers
- 1