Papers
2
Total Citations
80
H-Index
2
About
Xuanchen Xiang has made impactful contributions at the intersection of deep reinforcement learning and sequential decision-making under uncertainty. His research focuses on advancing Deep Reinforcement Learning (DRL) techniques to solve Partially Observable Markov Decision Processes (POMDP)—a critical challenge in artificial intelligence where agents must act with incomplete information. Xiang’s most notable work is a comprehensive two-part survey series (2021), which systematically reviews DRL applications for POMDP problems across diverse domains. The first part, with 69 citations, covers foundational methods and applications in games, robotics, and natural language processing, while the second extends to transportation, industries, and communications. Together, these papers serve as a key resource for researchers and practitioners, synthesizing advances in a rapidly evolving field. By bridging theoretical frameworks with real-world use cases, Xiang’s work helps demystify how DRL can handle complex, partially observable environments—a crucial step toward more robust and autonomous AI systems. His surveys are widely referenced, reflecting their value in guiding both newcomers and experts in applying DRL to challenging POMDP problems.
Research Focus
Key Achievements
Top Papers
- 1
- 2