Zhiqiang He

Reinforcement Learning & Systems Intelligence

Personal academic homepage (future lab-ready layout)

Zhiqiang He (何志强)

I am a Ph.D. student at the University of Electro-Communications (UEC), Tokyo, advised by Prof. Zhi Liu. My research focuses on reinforcement learning and its applications across real-world decision-making problems. Previously, I earned an M.S. from Northeastern University under the supervision of Prof. Jiao Wang.

I interned as a Research Engineer at Baidu Beijing from June to September 2021 (Received Super Special Offer), followed by a role as a Reinforcement Learning Algorithms Engineer at InspirAI from June 2022 to May 2023 (Received Top-Performing Team Prize).

Email  /  CV  /  Google Scholar  /  Github  /  Zhihu  / 

Research Interests

I am broadly interested in reinforcement learning and sequential decision making, especially towards more general and reliable AI agents. A long-term goal of my research is to use AI to do scientific research itself, enabling agents that can discover, test, and refine hypotheses and ultimately reshape how we do science.

• Data-efficient reinforcement learning under limited samples
• Stable and robust training for long-horizon control
• Large-scale RL and deployment in real systems
• Continual / sustainable learning under non-stationary environments

So far, many of my works use concrete application scenarios (e.g., communication networks, traffic systems, multimedia) as research testbeds for these RL questions. Going forward, I plan to gradually move from \"RL for complex control\" to AI for scientific discovery, starting from well-defined controlled systems and then expanding to broader scientific domains.

Academic Activities & Awards

Served as a peer reviewer for IEEE Transactions on Network Science and Engineering; IEEE Internet of Things Journal; IEEE Open Journal of the Computer Society.

Awards: JST (Japan Science and Technology Agency) Next-Generation Researcher (2.2 million yen per year, 2025) ; Outstanding Graduate (Top 1%, 2019) ;

Publication / Preprint

For the full list of my publications, please visit the Publications page.

Collaboration

I am always happy to discuss ideas and potential collaborations on reinforcement learning, especially topics related to data efficiency, stability, large-scale deployment, and continual learning.

If you are interested in working together (e.g., on a joint paper / project), feel free to email me with a brief introduction, your background, and what kind of problems you would like to work on.

News

• 2026: Paper accepted to IEEE Transactions on Multimedia on plasticity-aware mixture of experts for adaptive video streaming.
• 2025: Recognized as JST Next-Generation Researcher.
• 2025: Several works on world models, multi-agent RL for traffic, and DRL-based UAV communications accepted to leading journals.
• 2019: Selected as Outstanding Graduate (Top 1%).

Teaching & Service

I am committed to contributing to the research community and mentoring young researchers.

Journal Reviewing: IEEE Transactions on Network Science and Engineering; IEEE Internet of Things Journal; IEEE Open Journal of the Computer Society.

Mentoring: I regularly mentor junior students and collaborators on topics related to reinforcement learning and its applications.

Contact

The best way to reach me is by email: tinyzqh@gmail.com.

Address: University of Electro-Communications (UEC), Tokyo, Japan.

Thanks Jon Barron for his website template.