People

Principal supervisor


Xin Li. Xin is currently an Associate Professor in the School of Computer Science at Beijing Institute of Technology, China. She received the B.Sc. and M.Sc. degrees in Computer Science from Jilin University China, and the Ph.D. degree in Computer Science at Hong Kong Baptist University. Her research focuses on the development of algorithms for (deep) reinforcement learning, network representation learning, with application to Single/Multi-player Games, Robotics, Network Alignment and Recommender Systems. [Website]

Ph.D. students


Hongyu Zang. Hongyu is currently a first-year Ph.D. student in Computer Science at Beijing Institute of Technology. He received his B.Sc. degree in Computer Science from Beijing Forestry University. Hongyu's research focuses on Reinforcement Learning combining with Bayesian modeling, approximate inference and information bottleneck. His work aims to develop statistical models for analysing the reliability of Reinforcement Learning algorithms and use the information theory to explain the performance of RL algorithms.

M.S. and undergraduate students


Sen Chen. Sen is a second-year M.S. student in the Department of BIT computer Science. He focuses on partially observable reinforcement learning. He is also interested in agents building models of the environment in a human intelligent way, such as object recognition, concept learning and commonsense reasoning in the environment.

Jie Huang. Jie is a second-year M.S. student in computer science at Beijing Institute of Technology and a bachelor's degree in computer science from Beijing Institute of Technology. His research focuses on imitation learning and inverse reinforcement learning. His work aims to apply imitation learning and inverse reinforcement learning algorithms to robot control fields.

Li Zhang. Li is a third-year M.S. student in Computer Science at Beijing Instite of Technology, from which he also recevived his B.Sc. degree. Li's research interest includes model-free learning, model-based planning, their combination in both of reinforcement learning and imitation learning, partially observability, hierarchical DRL and multi-agent DRL. His work aims to build powerful, interpretable, verifiable, efficient, stable and reliable DRL methods, making DRL more pratical.

Shuqi Yang. Shuqi is a first-year M.S. student at the School of Computer Science, Beijing Institute of Technology. He received his Bachelor's degree in Computer Science and Technology at Zhengzhou University. His research focuses on partially observable deep reinforcement learning.

Group alumni


Xinwen Wang. Xinwen worked on (deep) reinforcement learning under partially observable environment. He will soon join Microsoft(China) after 6 months internship.

Pengfei Zhu. Former M.Sc. student, now working at Alibaba.

Guanghui Miao. Former M.Sc. student, now working at Xiaohongshu.

Collaborators


We are proud to have collaborative work with esteemed researchers in ML/RL fields.

William K. Cheung. Associate Professor and Head in the Computer Science Department, Hong Kong Baptist University, Hong Kong, China. [Website]

Pascal Poupart. Professor & Canada CIFAR AI Chair at the Vector Institute Artificial Intelligence, Machine Learning, Health Informatics Waterloo AI Institute David R. Cheriton School of Computer Science University of Waterloo, Canada. [Website]

Ivor W. Tsang. ARC Future Fellow, Professor of Artificial Intelligence, University of Technology Sydney(UTS), Australia. [Website]

Mingzhong Wang. Lecturer in ICT (Faculty of Arts and Business),University of the Sunshine Coast, Australia. [Website]

Our DRL group is also working with renowned company’s AI group towards more real-world applications, e.g., 育碧 Ubisoft(China), 达闼 CloudMinds(Shenzhen).