Zihan Fang
Papers
1
Total Citations
2
H-Index
1
About
Zihan Fang is an emerging researcher specializing in deep reinforcement learning (DRL), robotic control, and adversarial robustness. Their work addresses one of the most pressing challenges in deploying intelligent systems in real-world environments: the vulnerability of DRL agents to environmental perturbations. In their notable 2025 paper, "State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning," Fang tackles the limitations of existing white-box adversarial attack methods that rely on local gradient information, proposing a more sophisticated state-aware framework for perturbation optimization. This contribution is particularly significant as it bridges the gap between laboratory-trained DRL models and the unpredictable conditions of physical robotic deployment — a critical bottleneck in modern robotics research. Although early in their publishing trajectory with 2 citations, the recency of this work suggests a researcher actively pushing boundaries in a high-demand field. Students and practitioners working at the intersection of machine learning security, reinforcement learning, and robotics will find Fang's research highly relevant as the community increasingly prioritizes robust and reliable autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1