Overview

My research centers on integrating emerging reinforcement learning technologies into intelligent transportation systems, with a particular focus on enhancing traffic safety through advanced adaptive traffic signal control.

Research Areas

Reinforcement Learning for Traffic Safety

Developing RL-based methods for traffic signal control that explicitly account for collision risk and safety constraints, moving beyond throughput-only optimization toward collision-free intersection management.

Applied AI in Finance

Exploring reinforcement learning frameworks for portfolio management and financial prediction, including margin trading strategies and risk-aware generative models for stock analysis.

Large Language Models & Robotics

Investigating the applications of large language models in embodied AI and robotic systems, exploring how language understanding can improve task planning and human-robot interaction.


Current Projects

  • PairUpLight — Multi-agent RL for coordinated multi-intersection traffic signal control
  • RAGIC — Risk-aware generative framework for stock interval construction
  • SafeLight — RL method toward collision-free traffic signal control

For a complete list of publications, visit the Publications page or my Google Scholar profile.