Papers

5

Total Citations

93

H-Index

5

About

Dr. Huiyun Li is a leading researcher in reinforcement learning (RL) and robotics, whose work has garnered over 90 citations. Her primary research areas focus on developing sample-efficient and stable RL algorithms for continuous control, multi-agent systems, and robotic path planning. Dr. Li’s major contributions include the creation of Continuous Dynamic Policy Programming (CDPP), which addresses learning stability and sample efficiency in continuous-action RL by leveraging relative entropy regularization—a method that has gained 24 citations since 2023. She also pioneered Multi-Agent Continuous Dynamic Policy Gradient (MACDPP) for effective multi-agent control, and Deep Ensemble RL with multiple DDPG algorithms to improve exploration efficiency. In robotics, Dr. Li’s work on combining Rapidly-exploring Random Trees with Dynamic Window Approach in ROS has been instrumental in bridging path planning and velocity command generation, earning 20 citations. Her recent 2024 paper on Dropout-based Probabilistic Ensembles with Trajectory Sampling (DPETS) further advances model-based RL by integrating dropout uncertainty for robust control. Dr. Li’s research consistently pushes the boundaries of RL, making her a notable figure in the field.

Research Focus

Key Achievements

5
H-Index
5
Papers
93
Total Citations
19
Avg Citations/Paper
🏆 Most Cited Paper
Relative Entropy Regularized Sample-Efficient Reinforcement Learning With Continuous Actions
24 citations · 2023
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 10
🏛 Institutions: Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago