👋Hello! I am currently a first-year PhD student in University of Chinese Academy of Sciences, supervised by Prof. Yunduan Cui.
Prior to this, I received Master of Electronic and Information Engineering in Computer Technology from University of Chinese Academy of Sciences in 2025.
My research interests lie in the reinforcement learning and robot learning, especially in complex systems, like USV system, HVAC system, chemical production control etc.
In addition to academic, My areas of expertise include but are not limited to full-stack software and hardware development, cybersecurity maintenance, patent writing, commercial product design, and business plan writing. For more about me, visit my blog.
💪 Skills
- 💻 Programming skill: Go, Node.js(JavaScript), Vue/CSS, PHP, SQL(MySQL, PostgreSQL), Python(Django), Shell, Redis;
- ✒️ Academic skill: Pytorch, Tensorflow, Paddlepaddle, Latex;
- ⚙️ Software skills: SolidWorks, AutoCAD, Git.
📝 Featured Papers
✉️ Corresponding author.
Working Papers
-
Enhancing Stability of Probabilistic Model-based Reinforcement Learning by [Double-blind Peer Review]
Wenjun Huang, Xinrui Yue, Yidong Chen, Tianfu Sun and Yunduan Cui ✉️
Submitted to IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS, Major Revision) -
Multi-Goal Dexterous Hand Manipulation using Probabilistic Model-based Reinforcement Learning
Yingzhuo Jiang, Wenjun Huang, Rongdun Lin, Chenyang Miao, Tianfu Sun, Yunduan Cui ✉️
Submitted to IEEE Robotics & Automation Magazine (IEEE RAM) |[arXiv]
Published / Accepted Papers
-
Practical Reinforcement Learning using Time-efficient Model-based Policy Optimization
Wenjun Huang, Yunduan Cui ✉️ , Huiyun Li and Xinyu Wu
IEEE Transactions on Automation Science and Engineering (IEEE T-ASE, JCR Q1), 2025|[IEEE Xplore] -
Effective Probabilistic Neural Networks Model for Model-based Reinforcement Learning USV
Wenjun Huang, Yunduan Cui ✉️ , Huiyun Li and Xinyu Wu
IEEE Transactions on Automation Science and Engineering (IEEE T-ASE, JCR Q1), 2025|[IEEE Xplore] -
Practical Probabilistic Model-based Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling
Wenjun Huang, Yunduan Cui ✉️ , Huiyun Li and Xinyu Wu
IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2024|[Github]｜[IEEE Xplore]
🎖 Honors and Awards
- 2025.6 Outstanding Student Leader (Top 1%) at University of Chinese Academy of Sciences
- 2025.1 Director’s Innovation Award (Top 1%) at the Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences and The Chinese University of Hong Kong
- 2025.1 Best Student of the Year (Top 1%) at Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
- 2024.10 National Third Prize in CCF Technology Entrepreneurship Competition
📖 Educations
- 2025.09 – 2029.06, University of Chinese Academy of Sciences (UCAS), PhD of Pattern Recognition and Intelligent Systems.
- 2022.09 – 2025.06, University of Chinese Academy of Sciences (UCAS), Master of Electronic and Information Engineering, Computer Technology.
- 2018.09 – 2022.06, Harbin University of Commerce (HUC), Bachelor of Industrial Engineering.
🤝 Projects
- HVAC System Control in Collaboration with Ma’anshan Software Park (Leader);
- Industrial Process Control in Collaboration with SUPCON (Member);
- Dexterous Hand Control in Collaboration with ZHAOWEI (Member).
💻 Services
Reviewer
- IEEE Transactions on Automation Science and Enginnering (T-ASE)
- IEEE Robotics & Automation Magazine (RAM)
- IEEE International Conference on Robotics & Automation (ICRA)