I am a PhD student at the University of Technology Sydney (UTS), supervised by Prof. Chengqi Zhang and Dr Jing Jiang. Before joining UTS, I was a visiting scholar at the Southern University of Science and Technology (SUSTech), working with Dr Jing Jiang and Prof. Xuan Song. I received my Master’s Degree and Bachelor’s Degree from the School of Data and Computer Science, Sun Yat-sen University (SYSU) in 2020 and 2017 respectively, under the supervision of Prof. Chang-Dong Wang.
My current research focuses on causal reinforcement learning (RL), an emerging research field that incorporates prior knowledge and assumptions about causal relationships into the RL framework, empowering agents to better comprehend the world. By harnessing causal relationships, agents gain insights into complex environments and tasks, facilitating informed decision-making. Ultimately, the goal of my research is to advance the progress of next-generation AI agents toward human-level intelligence with robustness, fairness, and interpretability. If you are also passionate about this field and are interested in potential collaborations or discussing research ideas, please feel free to reach out to me！ 😉
I am currently seeking postdoctoral positions or roles as a research scientist/engineer in related fields. If you have any opportunities, please do not hesitate to contact me. Thank you!
- I’m grateful to receive the Student Best Paper Award from the Australian Artificial Intelligence Institute.
- Our tutorial proposal on causal reinforcement learning is accepted by IJCNN 2024. See you in Yokohama, Japan!
- Our survey paper on causal reinforcement learning is accepted by Transactions on Machine Learning Research!
- Our paper on offline RL is accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (CORE A*, IF=24.314)!
- We just present a tutorial on causal reinforcement learning at ADMA 2023 in Shenyang, China. Please check our presentation here.
- Our survey paper on causal reinforcement learning is now available on arxiv.
- One new paper on offline RL is on arxiv now.
- One paper on offline RL has been accepted by ICLR 2022 (CORE A*, Spotlight).
- One paper on session-based recommender systems has been accepted by TNNLS (CORE A*).
- One paper on deep learning-based recommender systems has been accepted by AAAI 2019 (CORE A*, Oral).
- Our paper on serendipitous recommendation was accepted by TCYB (CORE A).