Xianhao Chen

University of Hong Kong

Papers

1

Total Citations

5

H-Index

1

About

Xianhao Chen is an emerging researcher specializing in the robustness and security of deep reinforcement learning (DRL) systems, with a particular focus on adversarial attacks and agent reliability in real-world environments. His most notable work, "Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective" (2025), challenges conventional approaches to adversarial evaluation by shifting the analytical lens from individual sampled actions to the broader policy distribution — a conceptually significant reframing that addresses fundamental limitations in existing attack methodologies. This contribution is especially relevant as DRL systems increasingly face deployment in noisy, uncertain real-world settings where observation signals are inherently imperfect. With 5 citations already accumulated shortly after publication, the work is gaining early traction within the reinforcement learning security community. Chen's research sits at a critical intersection of machine learning robustness, AI safety, and practical deployment considerations — areas of growing urgency as autonomous systems become more prevalent. While still early in his research career, his willingness to fundamentally question established paradigms positions him as a thoughtful contributor to the ongoing conversation around building trustworthy and resilient AI agents.

Research Focus

Key Achievements

1
H-Index
1
Papers
5
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
5 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 9
🏛 Institutions: University of Hong Kong

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago