![]() |
朱正茂 |
Currently I am a first year PhD student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, which is led by professor Zhi-Hua Zhou.
I received my B.Sc. degree in School of Mathematical Sciences in June 2018 from Zhejiang University. In September 2018 and 2020, I was admitted to study for a M.Sc. degree and Ph.D. degree in Nanjing University under the supervision of associate Prof. Yang Yu without entrance examination, respectively.
My research interests lie in Reinforcement Learning, especially the state abstraction in Reinforcement Learning. The complex dynamics and high-dimensional observations are big challenges in applying Reinforcement Learning into real-world. State Abstraction is a promising approach to solve these challenges. During past years, I worked on several interesting topics including data-efficient state abstraction, predictive learning, predicting uncertain dynamics and exploration in model-based learning. In the future, I would like to study deeply in building more universal state abstraction with causal inference.
Introduction to Reinforcement Learning(with Prof. Yang Yu; for graduate students), Fall, 2020
KDD 2020 Cup Track 4: Reinforcement Learning Competition – Learning to Dispatch and Reposition on a Mobility-on-Demand Platform , 2nd place, 2020.7
First-Class Academic Scholarship, Nanjing University, Nanjing, 2018, 2019
Second-Class Academic Scholarship, Zhejiang University, Hangzhou, 2014, 2016
Email:
zhuzm {AT} lamda.nju.edu.cn, siqili1230 {AT} gmail.com
Laboratory:
Computer Science Building, Xianlin Campus of Nanjing University
Address:
Hong Qian, National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(南京市栖霞区仙林大道163号, 南京大学仙林校区603信箱, 软件新技术国家重点实验室, 210023.)