
Yali Du
Assistant Professor @ King´s College London
reinforcement learning
language models
machine learning
human-robot interaction
deep learning.
game playing
multi-agent systems
human-in-the-loop machine learning
cooperative games
social dilemma
reinforcement learning algorithms
marl
safe reinforcement learning
learning from human preferences
human-agent collaboration
5
presentations
13
number of views
SHORT BIO
Yali Du is a Lecturer at King’s College London and she leads the Cooperative AI Lab. Her research aim is to enable machines to exhibit trusted behaviour in complex decision making tasks. Her research interest lies in reinforcement learning and multi-agent systems and topics include multi-agent cooperation and coordination, reinforcement Learning and generalisation, evaluation of human and AI players, and applications in game AI, data science. Her research output has been widely published in prestigious venues including ICML, NeurIPS, ICLR, AAMAS, etc. Personal website: https://yalidu.github.io/
Presentations

Human-Guided Moral Decision Making in Text-Based Games
Zijing Shi and 4 other authors

STAS: Spatial-Temporal Return Decomposition for Multi-Agent Reinforcement Learning
Sirui Chen and 3 other authors

TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient
Xingzhou Lou and 4 other authors

Cooperative Multi-Agent Learning in a Complex World: Challenges and Solutions
Yali Du

How to train your agent: Active Learning from Human Preferences and Justifications in Safety-critical Environments
Ilias Kazantzidis and 3 other authors