About
Zhiqiang He / 何志强
I am a Ph.D. researcher in reinforcement learning at the University of Electro-Communications, Tokyo. Before UEC I was a Reinforcement Learning Engineer at InspirAI, an RL research intern at Baidu, and earned my M.S. from Northeastern University and B.S. from East China Jiaotong University.
Outside of papers I write about RL on Zhihu (10K followers) and maintain code at github.com/tinyzqh.
Education
-
2024 — present
Ph.D. in Information Science
University of Electro-Communications (UEC) · Tokyo, Japan
Advised by Prof. Zhi Liu.
-
2019 — 2022
M.S. in Control Science and Engineering
Northeastern University (NEU) · Shenyang, China
Advised by Prof. Jiao Wang.
-
2015 — 2019
B.S. in Automation
East China Jiaotong University (ECJTU) · Nanchang, China
Outstanding Graduate (Top 1%)
Experience
-
2022 — 2023
Reinforcement Learning Algorithms Engineer
InspirAI · Hangzhou, China
Built a general-purpose card-game AI SDK across Sanguosha, Hearthstone, Landlord (Dou Dizhu), and GuanDan. The Landlord agent reached super-human level, defeating top-ranked professional players; the GuanDan deployment delivered +6% win rate over baseline. Top-Performing Team Prize.
-
2021
Reinforcement Learning Research Intern
Baidu · Beijing, China
Proposed and shipped EDA-MAPPO (Expert-Data-Assisted MAPPO) into a client production environment. Super Special Offer.
Awards
- JST Next-Generation Researcher · ¥2.2M / year, 2025-2027
- Outstanding Graduate (Top 1%), East China Jiaotong University, 2019
- Honorable Mention, Mathematical Contest in Modeling (MCM), 2018
- Third Prize, 15th Challenge Cup, Jiangxi Division, 2017
Service
- Peer reviewer — ACM Multimedia
- Peer reviewer — IEEE Transactions on Network Science and Engineering
- Peer reviewer — IEEE Internet of Things Journal
- Peer reviewer — IEEE Open Journal of the Computer Society