Jiahao Ling
Papers
2
Total Citations
10
H-Index
2
About
Jiahao Ling is a researcher whose work lies at the intersection of reinforcement learning, multi-agent systems, and human-robot interaction. His key contributions focus on making robot learning more efficient and intuitive. In his most cited work, "Adaptive reinforcement learning in box-pushing robots" (2014, 8 citations), Ling proposed an adaptive state aggregation Q-Learning method that enhances learning efficiency through multi-agent cooperation, applying it to humanoid robots performing collaborative box-pushing tasks by partitioning the state space with decision trees. This work addresses fundamental challenges in scaling reinforcement learning to real-world robotic applications. Ling also explored novel approaches to human-guided robot learning in "Reward shaping for reinforcement learning by emotion expressions" (2014, 2 citations), where he developed a system enabling non-experts to teach robots through emotional expressions. Using interval fuzzy type-2 algorithms to recognize facial expressions from web camera input, this work translates human emotional cues into reward signals, making robot training more accessible. Though his citation counts are modest, Ling's research demonstrates creative thinking about how robots can learn from both structured algorithms and natural human communication, contributing to the development of more adaptable and user-friendly robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Adaptive reinforcement learning in box-pushing robots8 citations · 2014
- 2Reward shaping for reinforcement learning by emotion expressions2 citations · 2014