Yufeng Qi

China University of Petroleum, East China

Papers

Total Citations

H-Index

About

Yufeng Qi is a rising researcher in reinforcement learning and robotics, whose work focuses on bridging the gap between simulated environments and real-world applications. His primary research areas include cross-domain policy adaptation, dynamics alignment, and transfer learning for autonomous systems. Qi's most notable contribution is his 2023 paper, "Cross-domain policy adaptation with dynamics alignment," which has already garnered 7 citations—a strong early impact indicator for a junior scholar. In this work, he introduced a novel framework that enables policies trained in one environment to adapt seamlessly to another by aligning underlying dynamics, addressing a critical bottleneck in deploying reinforcement learning agents across varied physical or simulated domains. This approach has significant implications for robotics, where transferring skills from simulation to real hardware often fails due to mismatched physics. Qi's research demonstrates a keen ability to tackle fundamental challenges in generalization and robustness, positioning him as a promising voice in the field. As his citation count grows, his work is likely to influence both theoretical advances and practical deployments in adaptive, autonomous systems.