About Me

I am currently an Assistant Professor (UK Lecturer) at King’s College London and a member of Distributed Artificial Intelligence Group. Prior to joining King’s, I was a postdoc researcher at Centre for AI, University College London working with Prof. Jun Wang. I received my PhD from University of Technology Sydney in 2019, advised by Prof. Dacheng Tao. My research interest lies in machine learning and reinforcement learning, especially in the topics of multi-agent learning, policy evaluation, social agents, and applications to Game AI and data science.

  • I am actively looking for PhD students and postdocs to work with me. Check Openings for funding opportunities and topics of interest. Please drop me an email with your CV and interest.
  • I am happy to host (remote) undergraduate / graduate visitors and supervise summer research projects. Please drop me an email with your CV and interest.
  • For Master’s and undergrad’s project at King’s, please contact me before putting me forward as the supervisor.

Recent News

  • 08 Mar 2022 - Invited to give a tutorial at Oxford Machine Learning Summer School. This is a three-hour tutorial on optimisation for machine learning. Welcome to join!
  • 21 Jan 2022 - Our paper on offline goal-conditioned reinforcement learning has been accepted by ICLR 2022.
  • 10 Dec 2022 - One paper got accepted by AAMAS 2022. We propose to coordinate agents’ behaviors based on directed acyclic graphs (DAGs).
  • 10 Nov 2021 - Invited to serve as Session Chair for Reinforcement Learning in Asian Conference on Machine Learning 2021
  • 16 Aug 2021 - Invited talk on RLChina summer school, check schedule.
  • 07 Aug 2021 - Invited to serve as Senior PC for AAAI 2022.
  • 10 Jul 2021 - Our paper on Reinforcement Learning for Vehicle Routing has been accepted by IEEE Transactions on Cybernetics.
  • 08 May 2021 - Two papers on multi-agent evaluation by alpha-rank and solving general sum stochastic games are accepted by ICML 2021.
  • 29 Apr 2021 - Our paper on reinforcement learning for causal discovery has been accepted by IJCAI-21.
  • 16 Jan 2021 - Our paper on reinforcement learning for multi-aspect recommendation has been accepted by The Web Conference.
  • 18 Dec 2020 - One paper on learning correlated communication topology for MARL has been accepted by AAMAS 2021 (London Online) as oral presentation.
  • 09 Dec 2020 - Invited to serve as the reviewer for ICML 2021.
  • 26 Sep 2020 - One paper on RL for text-based games is accepted by NeurIPS 2020.
  • 17 Aug 2020 - Invited to serve as the PC for AAAI 2020.
  • 4 Apr 2020 - Invited talk at Youth Forum in Center on Frontiers of Computing, Peking University. Details can be found here.
  • Mar 2020 - Invited to serve as the Reviewer for NeurIPS and IROS 2020.
  • Dec 2019 - Invited to serve as the PC of IJCAI, ICML 2020.


Email: yali.dux AT gmail.com
Address: Bush House, 30 Aldwych, WC2B 4BG