Subin Huh
Papers
1
Total Citations
24
H-Index
1
About
Subin Huh is a rising researcher in the field of safe reinforcement learning, with a focus on ensuring reliability in high-stakes autonomous systems. Their key contributions center on developing Lyapunov-based approaches to guarantee probabilistic reachability and safety specifications, even when system models are incomplete or uncertain. This work is particularly vital for applications like autonomous driving and robotic surgery, where safety constraints are paramount. Huh’s most-cited paper, "Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach" (2020), has garnered 24 citations, reflecting its growing influence in bridging theoretical guarantees with practical deployment. By proposing model-free methods that maintain safety without requiring full system knowledge, Huh addresses a critical bottleneck in real-world reinforcement learning. Their research stands out for its rigorous mathematical foundation and direct relevance to emerging technologies, positioning Huh as a promising voice in the quest to make autonomous systems both intelligent and trustworthy. This work lays essential groundwork for future advances in safety-critical control.
Research Focus
Key Achievements
Top Papers
- 1