Papers
1
Total Citations
11
H-Index
1
About
Yufei Kuang is a researcher advancing the frontiers of deep reinforcement learning, with a particular focus on developing algorithms that remain reliable when deployed in real-world environments. His work addresses a critical challenge: the performance degradation that occurs when policies trained in simulation encounter the inevitable discrepancies of physical systems. Kuang’s most cited work, "Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization" (2022, 11 citations), introduces a novel framework for learning policies that are inherently robust to disturbances in transition dynamics. Rather than explicitly modeling every possible perturbation, his approach conservatively constrains the policy’s behavior based on state-space analysis, enabling more stable and generalizable performance. This contribution is foundational for deploying reinforcement learning in safety-critical domains such as robotics and autonomous systems. Kuang’s research is characterized by a rigorous theoretical grounding combined with practical algorithmic design, making his work highly relevant for students and researchers seeking to bridge the gap between simulated training and reliable real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1