☕️About Me
I am a master’s student in mathematics at the University of Luxembourg, with a background in mathematics and computer science at Beijing Institute of Technology.
My research focuses on sequential decision-making under uncertainty, particularly reinforcement learning, state representation learning, and stochastic optimization. I am interested in how agents can learn useful representations and make reliable decisions in stochastic environments.
My published work in Computers & Industrial Engineering studies Bayesian learning and optimal task termination with uncertain system lifetimes and task durations. My current research explores state similarity and optimization methods for representation learning in reinforcement learning.
I welcome research collaborations and opportunities to develop these interests through a master’s research project or research internship.
- Reinforcement Learning
- Reliability Engineering
- Representation Learning
- Mathematical Modeling
Master of Mathematics
University of Luxembourg
B.E. in Computer Science and Technology
Beijing Institute of Technology
B.S. in Mathematics and Applied Mathematics
Beijing Institute of Technology
Reinforcement learning and state representations
I study state similarity and bisimulation-based representation learning, with an interest in robustness to stochastic transitions and task-irrelevant observations.
Stochastic optimization for learning
I explore how sampling and optimization objectives affect representation learning, including auxiliary estimators and primal-dual formulations.
Bayesian decisions and reliability
My published research combines Bayesian inference from complete and censored observations with Markov decision processes to optimize task termination. I am interested in connections to risk-aware decision-making and learning-based control.