Sohee Park
Papers
1
Total Citations
4
H-Index
1
About
Sohee Park is a researcher at the forefront of safe artificial intelligence, specializing in the intersection of reinforcement learning (RL) and formal verification. Her work addresses a critical gap in modern AI: while RL excels at maximizing rewards, it often neglects safety constraints essential for real-world deployment. Park’s major contribution lies in pioneering the application of quantitative model checking to RL systems, enabling rigorous analysis of safety properties during policy learning. Her 2024 paper, "Applying Quantitative Model Checking to Analyze Safety in Reinforcement Learning," has already garnered 4 citations, signaling growing recognition of this novel approach. By integrating formal methods with RL, Park provides a framework for ensuring that autonomous systems—from robotics to self-driving cars—operate within defined safety boundaries without sacrificing performance. Her research is particularly notable for bridging theoretical computer science and practical AI safety, offering a pathway to trustworthy autonomous decision-making. As the field of safe RL expands, Park’s work stands as a foundational contribution, promising to shape how researchers and engineers build reliable, constraint-aware learning systems.
Research Focus
Key Achievements
Top Papers
- 1