Xiaoqing Fan

Hi, I am a second-year PhD student in Mathematics for Real-World Systems Centre for Doctoral Training. My research interests involve algorithms, machine learning (particularly reinforcement learning), dynamical systems and algorithmic game theory. I am under the supervision of Dr. Paolo Turrini and Prof. Thomas Hills.

Current Research Topic

I am currently researching the intersection of reinforcement learning and game theory, with a primary focus on designing algorithms to uncover the underlying learning processes and what drives the cooperation in social networks. Meanwhile, I am designing the experiments with the Department of Psychology and recruiting participants to structure an environment that fosters enhanced pro-social behaviour.

Publications

Fan, X., Leung, C.W. and Turrini, P., 2025. Co-learning of strategy and structure achieves full cooperation in complex networks with dynamical linking. International Joint Conference on Artificial Intelligence, 2025.

In this paper we show, for the first time, that a fully cooperative society can be sustained in games on networks by RL agents only, without relying on hard-wired decision-making heuristics or imitation dynamics.
We also confirm the fundamental role of timescales, the relative speed at which strategic and structural updates occur, highlighting the intricate interplay between network dynamics and decision-making in structured agent societies.

Projects

Multiple Object Tracking and Forecasting: Predicting Future Object Locations with Reinforcement Learning. Supervised by Dr. Victor Sanchez.

Drift and Bias in AI Triage Tools for GP Consultations. Supervised by Prof Magnus Richardson and in collaboration with Dr Youssef Taleb from Spectra Analytics.

Graph Transformation Method for Graph Convolutional Networks with Heterophily. Supervised by Professor Mauricio Barahona.

Research Activities

Talk & poster: Co-learning of strategy and structure achieves full cooperation in complex networks with dynamical linking, IJCAI, August 2025.

Talk: Self-learning Cooperation in Social Networks, MathSys PhD Meeting, Feb 2025.

Poster: Social dilemma in complex networks and with LLMs, Cooperative AI Summer School, July 2025/

Teaching

CS910 Foundation of Data Analytics 24/25 Term 1

CS909 Data Mining 24/25 Term 2

MA222 Metrics Spaces 23/24 Term 2

Supervisor for First-year Maths Students 23/24 Term 2