I am currently an Assistant Professor (UK Lecturer) at King’s College London. I lead the Cooperative AI Lab. My research interests lie in reinforcement learning and multi-agent cooperation, with a focus on topics such as generalization, zero-shot coordination, evaluation of human and AI players, and social agency (e.g., human-involved learning, safety, and ethics), among others.
Funded PhD position: We have a fully funded position on reinforcement learning and multi-agent learning (start date flexible). Full scholarship for local students (also applicable for international students). Applying or enquiry with your CV to: yali.du(at)kcl.ac.uk
I will be speaking at the following events:
- 16-19 Jul 2023 - Cooperative AI Summer school on human-in-the-loop RL
- 2nd Jun 2023 - Berkeley MARL seminar, UC Berkeley on human-in-the-loop RL, host by Eugene Vinitsky.
- 24th May 2023 - Computer Science Colloquium at Dept. of Computer Science, University of Warwick.
- 23th May 2023 - School of Computing, Australian National University, host by Dr. Liang Zheng. I will give a guest lecture on “Introdoction to Reinforcement Learning”
- 17th May 2023 - Invited Talk @ Fidelity AI Center, Fidelity Investments, on RL with human values.
8th May 2023 - Tutorial on “machine learning optimisation” in Oxford Machine Learning Summer School. Please find out more here! 19-21 Feb - Rising Star in AI symposium at KAUST, Thuwal, Saudi Arabia. 10 Feb 2023 - Selected to speak for AAAI New Faculty Highlights Program. 7 Feb 2023 - Tutorial on “Cooperative multi-agent learning” at AAAI 2023. Please find out more here.
(For recent news, please visit here)
- 28 Dec 2022 - I am appointed as the an Associate Editor for IEEE Transactions on AI editorial board. Look forward to serving the journal!
- 12 Dec 2022 - I give a tutorial on “Cooperative multi-agent learning: a review of progress and challenges” at ACML 12-14 Dec, 2022 together with Dr. Joel Z. Leibo from DeepMind. More details to be released.
- 1 Sep 2022 - we are organizing the 1st International Workshop on Safe Reinforcement Learning Theory and its Applications. Registration Deadline: Sep 1, 2022
- 17 Aug 2022 - I am giving a talk on “Decision Structure in Decentralized Multi-Agent Learning” at International Joint Conference on Theoretical Computer Science – Frontier of Algorithmic Wisdom (IJTCS-FAW) 2022.
- 30 Jun 2022 - One paper on “Scalable model-based policy optimization for decentralized networked systems” has been accepted by 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
- 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!
Email: yali.du AT kcl.ac.uk
Address: Bush House, 30 Aldwych, WC2B 4BG