Hi, welcome to my personal website! I am currently a second-year M.Phil. student in Robotics and Autonomous Systems at the Hong Kong University of Science and Technology (Guangzhou) under the supervision of Prof. Jun MA. I hold a Bachelor’s degree in Electronic and Information Engineering from Harbin Institute of Technology (Shenzhen).

I am currently seeking PhD opportunities that align with my research interests in 2025, with the goal of continuing my studies and making meaningful contributions to the field.

Research Interests

• Multi-Agent Reinforcement Learning
• Multi-Agent Collaboration and Game
• Decision-Making in Dynamic and Uncertain Environments
• Safe Decision-Making Algorithms for Autonomous Vehicles
• Large Language Models (LLMs) for Robotic Systems

My research focuses on multi-agent reinforcement learning and decision-making in complex, dynamic, and uncertain environments. In addition to technical research, I am highly interested in the potential of combining large language models (LLMs) with robotic systems, especially in enhancing semantic understanding and decision-making in real-world environments. My recent work involves leveraging semantic information to guide agents in navigation and exploration, while using reinforcement learning to improve the robustness and efficiency of decision-making algorithms.

Contact

I am open to collaborating with people to explore the possibilities of reinforcement learning and sequential decision making in various fields. If you find my work interesting, please feel free to contact me via email: zhou.xiao.hit@gmail.com.

News

• [2024.09] 🎉🎉 Our paper “Game-Theoretic Driver Modeling and Decision-Making for Autonomous Driving with Temporal-Spatial Attention-Based Deep Q-Learning” has been accepted by IEEE TRANSACTIONS ON INTELLIGENT VEHICLES!
• [2024.07] 🎉🎉 I attended the EPFL-ETHZ MARL Summer School at Lausanne, Switzerland!
• [2024.07] 🎉🎉 Our paper “Integrated Intention Prediction and Decision-Making with Spectrum Attention Net and Proximal Policy Optimization” has been accepted by ITSC 2024!
• [2024.06] 🎉🎉 Our paper “Reward-Driven Automated Curriculum Learning for Interaction-Aware Self-Driving at Unsignalized Intersections” has been accepted by IROS 2024!