Papers
2
Total Citations
80
H-Index
2
About
Simon Y. Foo is a leading researcher at the intersection of artificial intelligence and decision-making under uncertainty, with a primary focus on Deep Reinforcement Learning (DRL) and its application to Partially Observable Markov Decision Processes (POMDPs). His most significant contributions are a comprehensive two-part survey series (2021) that systematically maps the landscape of DRL techniques for solving POMDP problems. The first part, with 69 citations, establishes the theoretical foundations and explores applications in games, robotics, and natural language processing, while the second part extends this analysis to transportation, industrial systems, and communications. Together, these works provide an essential roadmap for researchers and practitioners, synthesizing complex advances in how agents learn optimal behaviors from incomplete environmental information. Foo’s surveys are notable for their breadth and clarity, serving as a go-to resource for those seeking to understand how DRL can tackle real-world sequential decision-making problems where full observability is impossible. His work has become a cornerstone for advancing autonomous systems that must operate reliably in uncertain, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2