Yuanqiang Yu
Papers
2
Total Citations
8
H-Index
2
About
Yuanqiang Yu is a rising researcher in artificial intelligence, with a primary focus on deep reinforcement learning (RL) and multi-task learning. His work addresses a critical bottleneck in modern AI: how to train agents that can efficiently master multiple tasks without suffering from inter-task interference. In his highly cited 2023 paper, "Accelerating deep reinforcement learning via knowledge-guided policy network," Yu introduced a novel framework that leverages prior knowledge to guide policy network design, significantly speeding up training convergence. This work has already garnered 5 citations, signaling its early impact. Complementing this, his paper "T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler" tackles the challenge of negative interference in multi-task RL by proposing a dynamic feature selection and scheduling mechanism. With 3 citations, this work demonstrates Yu’s ability to develop practical solutions for complex, real-world RL problems. Through these contributions, Yuanqiang Yu is establishing himself as a thoughtful innovator in making reinforcement learning more scalable, efficient, and applicable to diverse task domains.
Research Focus
Key Achievements
Top Papers
- 1
- 2