PhD Dissertation Proposal by LI Dexun | Sequential Decision Learning for Social Good and Fairness

Sequential decision-making is one of the key research areas in artificial intelligence. Typically, a sequence of events is observed through a transformation that introduces uncertainty into the observations and based on these observations, the recognition process produces a hypothesis of the underlying events. This learning process is characterized by maximizing a scalar reward signal. However, many real-life problems are inherently constrained by limited resources. Besides, when the learning algorithms are used to inform decisions involving human beings (e.g., Security and justice, health intervention, etc), they may inherit the potential, pre-existing bias in the dataset and exhibit similar discrimination against protected attributes such as race and gender. 

In this proposal, we focus on sequential decision-making for social good. In particular, in the first line of work, we consider the restless multi-armed bandits setting, which is an apt model to represent decision-making problems in public health interventions. In the second line of work, we discuss the reinforcement learning setting where an agent interacts with the environment to find an optimal sequence of actions to perform a specific task.

Dexun Li is a Ph.D. candidate at SMU SCIS, supervised by Prof. Pradeep Varakantham. His research focuses on Multi-armed Bandits, Reinforcement Learning, and Optimization, aiming to build models with constraints of the world for decision-making in limited resources environments.