Scholar
Zhongwen Xu
Google Scholar ID: T4xuHn8AAAAJ
Tencent
Citations & Impact
Citations
2,723
H-index
23
i10-index
32
Publications
20
Co-authors
22
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including 'Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and Planning' and 'Single-stream Policy Optimization'. Participated in various projects, such as 'Agents Play Thousands of 3D Video Games'.
Research Experience
- Spent time at Carnegie Mellon University, the National University of Singapore, Google Brain, and DeepMind during early research career.
Education
- Received a Bachelor's degree from Zhejiang University in 2013, supervised by Prof. Yueting Zhuang and Prof. Fei Wu. Earned a Ph.D. from the University of Technology Sydney (UTS), advised by Prof. Yi Yang.
Background
- Principal Scientist at Tencent, focusing on Deep Reinforcement Learning and Large Language Models, especially in reasoning and planning. Previously, a Principal Scientist at Sea AI Lab, an Adjunct Assistant Professor at the National University of Singapore, and a Senior Research Scientist at DeepMind.
