Papers
3
Total Citations
52
H-Index
2
About
Yew-Soon Ong is a pioneering figure in artificial intelligence, renowned for his transformative contributions to evolutionary computation, multiagent reinforcement learning, and multitask optimization. His work bridges foundational theory and real-world applications, particularly through the development of gradient-based multiagent reinforcement learning (MARL) algorithms—his 2019 paper on policy gradient potential has garnered 42 citations, shaping modern MARL frameworks where agents collaboratively update strategies. Ong also advanced evolutionary algorithms for complex problems, such as his 2009 study on valley adaptive clearing genetic algorithms for locating first-order saddle points, critical in fields like chemical reaction rate estimation and robotics navigation. Most recently, his 2025 research on evolutionary heterogeneous multitasking for quality diversity optimization (1 citation) pushes boundaries by enabling algorithms to generate high-performance, behaviorally diverse solutions across multiple tasks simultaneously—a leap beyond single-task QD methods. With a career marked by innovation in cross-disciplinary optimization, Ong’s work has influenced AI, engineering, and scientific computing, earning him recognition as a leader in scalable, adaptive intelligence. His research continues to inspire students and researchers tackling complex, multi-objective challenges.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3