Yi-Chen Teng
Papers
1
Total Citations
37
H-Index
1
About
Yi-Chen Teng is a rising researcher in reinforcement learning and robotics, whose work centers on curriculum learning for autonomous navigation. Her most-cited paper, "Curriculum Reinforcement Learning From Avoiding Collisions to Navigating Among Movable Obstacles in Diverse Environments" (2023, 37 citations), introduces a novel framework that progressively trains RL agents—starting from basic collision avoidance and advancing to complex navigation among movable obstacles. This approach significantly accelerates training convergence and enhances performance in dynamic, unstructured settings. Teng’s contributions address a critical challenge in robotics: enabling agents to adapt safely to environments where obstacles can be repositioned, a step toward more flexible real-world deployment. Her work has already garnered attention for its practical impact, with citations reflecting its relevance to the broader RL community. By demonstrating how structured curricula can bridge the gap between simulation and reality, Teng is helping to shape the next generation of intelligent, autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1