Jia Zhang 张佳
Email:
jialrs.z[at]gmail[dot]com
zhangjia[at]microsoft[dot]com
Office:
12114, 12F
Microsoft Research Asia
Tower 2, No.5 Danling Street
Haidian District, Beijing, China
I am now a senior researcher of the Machine Learning Group of Microsoft Research Asia (MSRA) and working on intellegence decison (large scale multiple agent reinforcement learning (MARL), graph knowledge learning, quantum computing etc.). Before join MSRA, I get my Ph.D. degree of Computer Science at the Institute of Computing Technology, CAS, and I have worked on online algorithm and mechanism design under the guidance of Prof. Xiaoming Sun in the Algorithm & Complexity Group. Before joining ICT, I got my bachelor from the "Wang Daheng Class" at Changchun University of Science and Technology.
Note: click the title to see the abstract
Multi-Agent Resource Optimization Platform (MARO)
| 2019.05 - Now | Co-Leader. MARO is an instance of Reinforcement learning as a Service (RaaS) for real-world resource optimization. It can be applied to many important industrial domains, such as container inventory management in logistics, bike repositioning in transportation, virtual machine provisioning in data centers, and asset management in finance. Besides Reinforcement Learning (RL), it also supports other planning/decision mechanisms, such as Operations Research. More details can be found in the GitHub Repo. |
Dynamic Route Pricing with SF Tech
| 2020.05 - 2020.10 | Project Leader. With the help of the graph neural network and optimization technology, we dynamically determine the price for the real-time land transportation orders. The goal is to minimize costs and increase automatic turnover rates. |
Supply and Demand Forecasting in Ocean Transportation Netowrk with OOCL
| 2020.01 - 2020.09 | Project Leader. By using the route and freight relationship in the shipping network, we are aim to forecast the the long-term supply and demand situation of each port. |
Multi-Agent Based Eempty Container Reposition System in Ocean Transportation Network with OOCL
| 2018.03 - 2019.08 | Project Leader. A multi-agent reinforcement learning system is designed to solve the reposition problem of empty containers in the extremely complex ocean transportation system. |
Education and Experience:
| 2017.07 - present | Senior Researcher, Machine Learning Group, Microsoft Research Asia |
| 2012.09 - 2017.06 | Ph.D. Candidate, Institute of Computing Technology, Chinese Academy of Sciences (CAS) Advisor: Xiaoming Sun |
| 2015.10 - 2016-04 | Research Intern, Machine Learning Group, Microsoft Research Asia Mentor: Tao Qin |
| 2008.09 - 2012.07 | Bachelor, School of Computer Science and Technology, Changchun University of Science and Technology |
| 2005.09 - 2008.07 | Shijiazhuang Foreign Language School |
Selected Honors:
| 2015&2014&2013 | Outstanding Student of University of Chinese Academy of Sciences (5%) |
| 2013 | National Scholarship for Postgraduate Students (2%) |
| 2013 | First Prize of the 10st National Postgraduate Mathematic Contest in Modeling (2.6% among 3884 teams) |
| 2012 | Outstanding Graduates of Changchun University of Science and Technology (5%) |
| 2010 | Second Prize of ACM/ICPC Contest in Jilin Province (rank 11) |
Social Activities:
| 2013 - 2014 | Present of Student Branch of Chinese Computer Federation (CCF) in Institute of Computing Technology |
| 2012 - 2013 | Vice Minister of the Ministry of Academic in student union of Institute of Computing Technology |
