Junqi Lu

☕️

陆俊骐 Lu Jun Qi

Undergraduate Student / Researcher

About Me

I hold a B.S. in Mathematics and am currently pursuing a second Bachelor’s degree in Computer Science at the Beijing Institute of Technology. This dual academic background equips me with a rigorous mathematical foundation and strong computational engineering skills.

My research interests lie at the intersection of Sequential Decision Making under Uncertainty, Operations Research, and Deep Reinforcement Learning (DRL). I am passionate about bridging theoretical mathematical modeling with efficient algorithmic design. My current work focuses on two main areas:

Reliability Engineering & Stochastic Control: Developing adaptive control frameworks and sequential decision-making strategies for mission-critical systems to safely balance operational risk and long-term efficiency.
Deep Reinforcement Learning & Representation Learning: Enhancing the robustness, generalization, and sample efficiency of DRL algorithms in highly stochastic and complex environments.

I am driven to create methodologies that are both theoretically sound and practically impactful. I am actively seeking graduate opportunities (Master’s or Ph.D.) starting in Fall 2026 and always welcome opportunities for academic collaboration.

Download CV

Interests

Reinforcement Learning
Reliability Engineering
Representation Learning
Mathematical Modeling

Education

B.E. in Computer Science and Technology
Beijing Institute of Technology
B.S. in Mathematics and Applied Mathematics
Beijing Institute of Technology

My Research

My research work centers on applying Markov Decision Processes (MDP) and Deep Reinforcement Learning (DRL) to complex decision-making and algorithmic improvement.

As a research assistant in Professor Li Xin’s Reinforcement Learning Group, I focus on developing advanced DRL algorithms, including improving model efficiency and generalization through Bisimulation Metrics and robust state representation learning.

In collaboration with Professor Qingan Qiu, I address reliability-based engineering decision-making under uncertainty. This work has resulted in a first-author publication, with ongoing efforts focused on extending the MDP framework using RL.

I am passionate about advancing methods that are both theoretically sound and practically applicable to real-world problems. I welcome opportunities for academic collaboration. 🤝

Featured Publications

Task Termination