LIU, Guiliang

Assistant Professor

Education Background

Ph.D. in Computer Science, Simon Fraser University, 2020
B.S. in Computer Science & Engineering, South China University of Technology, 2016

 

Research Field
Safe Reinforcement Learning, Inverse Reinforcement Learning and Embodied AI
Personal Website
Email
liuguiliang@cuhk.edu.cn
Office
Room 611, Teaching Complex C
Biography

Dr. Guiliang Liu is currently working as an Assistant Professor at the School of Data Science at The Chinese University of Hong Kong, Shenzhen. He obtained his undergraduate degree from South China University of Technology. He then earned his Ph.D. in Computer Science from Simon Fraser University in Canada and completed postdoctoral research at the University of Waterloo and the Vector Institute in Canada.

Dr. Liu's research primarily focuses on reinforcement learning and embodied intelligent decision-making. In the field of safe reinforcement learning, he leverages inverse constraint inference methods to enhance the safety of reinforcement learning systems. Additionally, he specializes in embodied robotic manipulation skills, developing efficient data engines to improve robotic operation in complex tasks, and designing robust control algorithms to ensure the safety and stability of humanoid robots in challenging environments. His research collaborator includes Baidu Research, Huawei Noah’s Ark Lab and DexForce Research.

Since 2022, Dr. Liu has published over 30 papers in top-tier international machine learning conferences and journals, including NeurIPS, ICML, and ICLR. Furthermore, he leads several provincial and municipal-level general projects and serves as co-principal investigator of a major program.

Academic Publications

1. Guiliang Liu, Ashutosh Adhikari, Amir-massoud Farahmand, Pascal Poupart. Learning Object-Oriented Dynamics for Planning from Text. International Conference on Learning Representations (ICLR) 2022

2. Yudong Luo, Guiliang Liu, Haonan Duan, Oliver Schulte, Pascal Poupart. Distributional Reinforcement Learning with Monotonic Splines. International Conference on Learning Representations (ICLR) 2022

3. Guiliang Liu, Xiangyu Sun, Oliver Schulte, Pascal Poupart. Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning. Advances in Neural Information Processing Systems (NeurIPS) 2021.

4. Guiliang Liu, Oliver Schulte, Pascal Poupart, Mike Rudd, Mehrsan Javan. Learning Agent Representations for Ice Hockey. Advances in Neural Information Processing Systems (NeurIPS) 2020.

5. Guiliang Liu, Xu Li, Jiakang Wang, Mingming Sun, Ping Li. Extracting Knowledge from Web Text with Monte Carlo Tree Search. The ACM Web Conference (WWW) 2020.

6. Xiangyu Sun, Jack Davis, Oliver Schulte, Guiliang Liu. Cracking the Black Box: Distilling Deep Sports Analytics. SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2020.