Suhee Jo
Papers
1
Total Citations
4
H-Index
1
About
Suhee Jo is a researcher at the intersection of artificial intelligence and formal verification, with a primary focus on ensuring safety in reinforcement learning (RL) systems. Her most-cited work, "Applying Quantitative Model Checking to Analyze Safety in Reinforcement Learning" (2024, 4 citations), addresses a critical gap in the field: while most RL research prioritizes reward maximization, Jo emphasizes the need to incorporate safety constraints and non-functional requirements in safety-critical applications. By integrating quantitative model checking techniques, she provides a rigorous framework for verifying that RL policies behave safely before deployment. This contribution is particularly vital for domains like autonomous driving, robotics, and healthcare, where unsafe actions can have severe consequences. Though early in her career, Jo's work signals a growing recognition that achieving high rewards is insufficient without formal safety guarantees. Her research bridges the gap between machine learning and formal methods, offering a path toward trustworthy AI systems. As the demand for safe autonomous systems increases, Jo's approach to embedding formal verification into RL training pipelines positions her as a rising voice in responsible AI development.
Research Focus
Key Achievements
Top Papers
- 1