Shengbo Xu
Papers
1
Total Citations
4
H-Index
1
About
Shengbo Xu is a researcher in robotics and artificial intelligence, with a primary focus on reinforcement learning and neuroevolution. His work explores how evolutionary algorithms can optimize artificial neural networks for continuous control tasks, particularly in legged robotics. Xu’s most cited paper, “Sample efficiency analysis of Neuroevolution algorithms on a quadruped robot” (2013, 4 citations), investigates the sample efficiency of neuroevolution methods in policy search for quadruped locomotion. This study contributes to understanding how evolutionary strategies can improve learning in high-dimensional, continuous state-action spaces—a critical challenge in robotics. While his citation count remains modest, Xu’s research addresses foundational issues in applying neuroevolution to real-world robotic systems, bridging the gap between theoretical algorithm design and practical deployment. His work is relevant for researchers interested in sample-efficient reinforcement learning, evolutionary robotics, and autonomous locomotion.
Research Focus
Key Achievements
Top Papers
- 1