Guiliang Liu

Recruitment

Ph.D. student recruitment: I am looking for self-motivated Ph.D. students with solid mathematical background and programming skill. Should you be interested, please send me an email with you CV, transcript, and publications. Potential research topics includes (but not limited to):

Inverse Constrained Reinforcement Learning (please refer to this paper).
Risk-Sensitive Reinforcement Learning.
Reinforcement Learning in Healthcare.

RA recruitment: I am looking for Research Assistants (RAs) starting anytime. Successful candidates should have promising academic record (e.g., high GPA). Financial support will be provided to strong candidates. Send me by email if you are interested. Please also attach your CV.

Research Interests

Reinforcement Learning (RL) and the related topics, including, Inverse Constrained RL, Model-based RL, Interpretable RL, Agent Evaluation and Embedding. I have also studied applications on Natural Language Process (NLP), Sports analytic and Autonomous Driving.

Selected Publications

Benchmarking Constraint Inference in Inverse Reinforcement Learning.
Guiliang Liu, Yudong Luo, Ashish Gaurav, Kasra Rezaee, Pascal Poupart.
International Conference on Learning Representations (ICLR) 2023.
[Paper (PDF)], [Slides], [Code],
Uncertainty-Aware Reinforcement Learning for Risk-Sensitive Player Evaluation in Sports Game.
Guiliang Liu, Yudong Luo, Oliver Schulte, Pascal Poupart.
Advances in Neural Information Processing Systems (Neurips) 2022.
[Paper (PDF)], [Slides],
Learning Object-Oriented Dynamics for Planning from Text.
Guiliang Liu, Ashutosh Adhikari, Amir-massoud Farahmand, Pascal Poupart.
International Conference on Learning Representations (ICLR) 2022.
[Paper (PDF)], [Slides], [Code],
Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning.
Guiliang Liu, Xiangyu Sun, Oliver Schulte, Pascal Poupart.
Advances in Neural Information Processing Systems (Neurips) 2021.
[Paper (PDF)], [Slides], [Code],
Learning Agent Representations for Ice Hockey.
Guiliang Liu, Oliver Schulte, Pascal Poupart, Mike Rudd, Mehrsan Javan.
Advances in Neural Information Processing Systems (Neurips) 2020.
[Paper (PDF)], [Slides], [Video], [Code ],

Contact

Email: liuguiliang[at]cuhk[dot]edu[dot]cn
Address: 319a DaoYuan, CUHK Shenzhen. Shenzhen, 518172
Linkedin: Guiliang (Galen) Liu