Min-Jae Cho
Papers
1
Total Citations
3
H-Index
1
About
Min-Jae Cho is a rising force in the intersection of artificial intelligence, control theory, and safety-critical systems. His primary research areas include meta-reinforcement learning, constrained optimization, and the development of adaptable safety guarantees for autonomous systems. Cho’s most notable contribution, "Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programming" (2024), addresses a fundamental barrier to deploying learning-enabled systems in high-stakes environments such as autonomous driving, robotic manipulation, and healthcare. By integrating differentiable convex programming into meta-reinforcement learning, his work enables agents to rapidly adapt to new tasks while maintaining provable safety constraints—a breakthrough for real-world reliability. Though early in his career, this work has already garnered 3 citations, signaling its growing influence. Cho’s research is particularly compelling for its practical focus: moving beyond theoretical AI performance to ensure that intelligent systems can operate safely and robustly under uncertainty. His achievements position him as a key contributor to the next generation of trustworthy autonomous technologies, making his work essential reading for students and researchers interested in safe AI deployment.
Research Focus
Key Achievements
Top Papers
- 1