About Me

  • I am an aspiring AI researcher with an entrepreneurial spirit. Please feel free to reach out for opportunities, collaboration or just a chat! (My Oxford email will be deactivated soon so please use my Gmail account)[Curriculum Vitae] [Google Scholar]
  • I was a MSc Student in the Computer Science Department at the University of Oxford, supervised by Professor Shimon Whiteson and Professor Jakob Foerster.
  • My research interests lie in the general area of machine learning, with specific focuses on reinforcement learning and deep learning, as well as their applications in sequential decision-making problems. Recently, I have been looking more into model-based reinforcement learning and multi-agent reinforcement learning.
  • In 2018, I joined the Reinforcement Learning and Artificial Intelligence (RLAI) Laboratory at the University of Alberta as a research visitor for a year, supervised by Professor Richard Sutton. It was a life-changing experience, especially in terms of my research philosophy.
  • I received my dual Bachelor’s degrees in information systems (BBA) and computer science (BEng) from the University of Hong Kong. My undergraduate research supervisors are Professor Michael Chau, Professor Jia Pan, Professor Ka Wai Kwok and Professor Albert Lam.

Recent News

  • January 15, 2024. One paper accepted to ICLR 2024.
  • February 6, 2023. I have joined the Robot Learning Lab at Dyson, focusing on developing sample-efficient RL methods for Robotics.
  • January 31, 2023. One paper accepted to ICLR 2023, my first first-author conference paper!
  • March 25, 2022. One paper ( Runner-up Best Paper ) accepted to ICLR-22 Workshop on Emergent Communication.
  • October 21, 2021. I was awarded the Hoare Prize for the best thesis from the Department of Computer Science, University of Oxford
  • I graduated from the University of Oxford with a MSc (Computer Science) degree, receiving a (distinction) for both coursework and thesis. My thesis topic is Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning , supervised by Christian Schroeder De Witt, Samuel Sokota, Jakob Foerster and Shimon Whiteson
  • August 28, 2020. One paper accepted to ICAPS-20 Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning. A nice little conclusion to my undergraduate studies.
  • January 15, 2020. One paper accepted to AAMAS 2020.
  • October 2, 2019. One paper accepted to NeurIPS-19 Workshop on Biological and Artificial Reinforcement Learning.
  • August 12, 2019. One paper accepted to MICCAI-19 Workshop on Artificial Intelligence in Radiation Therapy.
  • May 15, 2019. Our idea piece on Corrigibility won the ACM SIGAI Essay contest and will be published in the next AI Matters.

"We don't fight because there is hope. We fight so we can have hope" - Freedom Fighters