If you made any changes in Pure these will be visible here soon.

Personal profile


Learning and sharing information are essential intelligent conducts in human civilization. Individuals not only learn by themselves but also through collaborative behaviours. Communication, cooperation, and information exchange are interactive components to achieve effective and efficient learning. From the standpoint of Artificial Intelligence (AI), the process can be described as multi-agent learning where several autonomous agents simultaneously learn and conduct different activities. Autonomous sequential decision-making is one of the most pressing research areas in today’s machine learning field. With great advancement in computer performance, recent studies in Reinforcement Learning (RL) have shown progress to improve machines’ learning abilities. Yet, contemporary methods suffer from inherited challenges of single-agent learning, including the tradeoff between exploration and exploitation need for coordination, precise specification of learning goal, and the 'curse of dimensionality'.

The goal of the project is to develop a deep reinforcement learning approach with the right communication mechanism and effective learning capability to enable the best cooperative performance for multi-agent systems. The project is under the supervision of Professor Xiaojun Zeng, one of the pioneers in the Machine Learning area. 


Education/Academic qualification

Master in Science, Applied Computational Science and Engineering with Distinction, Imperial College London

2 Oct 20212 Oct 2022

Award Date: 1 Dec 2022

Bachelor of Science, BSc(Hons) Computer Science with Business and Management, The University of Manchester

18 Sep 201711 Jun 2021

Award Date: 23 Jul 2021

Areas of expertise

  • Q Science (General)
  • Computer Science