About me
Seeking Opportunities
I am actively seeking postdoctoral positions and am available to start at any time.
I am currently doing a PhD in Computer Science at the University of Manchester, supervised by Prof. Xiao-Jun Zeng and co-supervised by Dr. Ke Chen. I graduated from Wuhan University with an MSc in Management Science and Engineering in 2022 and from Wuhan University of Technology with a BSc in Management Information Systems in 2019.
My research focuses on multi-agent reinforcement learning as a computational framework for understanding how cooperation, reputation, and normative behaviour emerge and stabilise in decentralised multi-agent systems. During my master’s studies, I investigated how social exclusion and expulsion mechanisms shape cooperative dynamics in social dilemmas, grounding my work in evolutionary game theory and networked interactions.
Building on this foundation, my doctoral research examines how cooperative facilitation mechanisms, such as selective interaction and emergent reputation, operate under different learning paradigms, with a particular emphasis on comparing social learning and reinforcement learning frameworks. Through this work, I aim to develop learning-based, bottom-up models in which cooperative and normative behaviours arise from agent interaction rather than being imposed externally, thereby promoting robust cooperative collective intelligence.
News
[July 2025] I am currently doing a research visit at the Universiy of Amsterdam, hosted by Fernando P. Santos and funded by the ELIAS Mobility Program.
[May 2025] I was awarded the Carole Goble Medal for Outstanding Doctoral Paper in Computer Science at The University of Manchester.
[March 2025] Our journal paper, “Feature-driven Hybrid Attention Learning for Accurate Water Quality Prediction”, has been accepted in Expert Systems with Applications, where I contributed as the third author.
[Dec 2024] Our conference paper, “Bottom-Up Reputation Promotes Cooperation with Multi-Agent Reinforcement Learning,” where I am the first author, as been accepted as a full paper at AMMAS 2025.