Curriculum Vitae

Algorithm Intern

Booster Robotics

Tested and improved the localization module. Deployed humanoid robots and tuned their parameters. Organized the mjlab motion-control repository and added online simulation-based evaluation and performance metrics for reinforcement learning.

Researcher

Intelligent Systems, Utrecht University

Developed theories and algorithms for learning communication in multi-agent reinforcement learning in stochastic, continuous, and multi-task environments. Served as a teaching assistant and independently supervised students on thesis projects. Received funding support from Applied Data Science at Utrecht University.

Research Associate

National University of Singapore

Developed an online multi-player collaborative decision-making platform based on oTree, enabling real-time interaction between humans and reinforcement learning agents.

Research Assistant

The Chinese University of Hong Kong

Developed knowledge-sharing algorithms for multi-agent reinforcement learning, and tested and evaluated them in the HFO soccer environment.

Ph.D. in Computer Science

Intelligent Systems, Utrecht University

Thesis: Learning with Communication in Multi-agent Deep Reinforcement Learning

Supervisors: Prof. dr. Mehdi Dastani; Dr. Shihan Wang

Master in Software Engineering

South China University of Technology

Thesis: A Teacher-Student Framework for Knowledge Sharing in Multi-agent Reinforcement Learning

Supervisors: Prof. Yi Cai; Prof. Ho-fung Leung

B.E. in Electronic Commerce

Guangxi University

Class rank: 1st

Thesis: Sentiment Analysis in Social Media Texts

Supervisor: Prof. Jinchuang Zhao