Jiyoung Chang
Papers
1
Total Citations
4
H-Index
1
About
Jiyoung Chang is a researcher at the forefront of safe and trustworthy artificial intelligence, with a primary focus on reinforcement learning (RL) and formal verification. Their most cited work, "Applying Quantitative Model Checking to Analyze Safety in Reinforcement Learning" (2024), addresses a critical gap in the field: while RL excels at maximizing rewards, it often neglects essential safety constraints in high-stakes applications. Chang’s major contribution lies in integrating quantitative model checking—a rigorous formal method—into the RL pipeline, enabling systematic verification of safety properties before deployment. This approach allows researchers to analyze non-functional requirements like collision avoidance or resource limits, ensuring that learned policies are not only optimal but also provably safe. With 4 citations in a short time, this work is gaining traction as a foundational reference for safety-critical RL. Chang’s research is particularly impactful for autonomous systems, robotics, and healthcare, where a single unsafe action can have severe consequences. By bridging the gap between performance and safety, Jiyoung Chang is shaping a future where AI systems can be both powerful and trustworthy.
Research Focus
Key Achievements
Top Papers
- 1