A/ProfJing Jiang

Her research advances collaborative learning and decision-making across the following interconnected areas:

• Federated and collaborative learning: Learning from decentralised data and experience through effective knowledge sharing.

• Reinforcement learning and sequential decision-making: Learning adaptive policies for decision-making under uncertainty and optimising long-term outcomes.

• Federated reinforcement learning: Enabling agents to learn policies collaboratively while adapting to heterogeneous environments and individual objectives.

• Personalised AI and heterogeneous learning: Adapting shared knowledge to individual users, agents, tasks, and environments.

• Lifelong learning and meta-learning: Enabling continual adaptation, knowledge transfer, and efficient learning of new tasks.

• Machine learning applications: Developing personalised recommender systems and other intelligent applications that support long-term user benefit and wellbeing.