Imitation learning for combinatorial optimization and contact tracing

Thesis

The field of Imitation Learning (IL) has seen significant progress in recent years as researchers have applied this machine learning technique to various domains such as robotics, self-driving cars, healthcare, and game playing. Each domain has contributed to the advancement of the field by developing and applying new methods to solve the unique problems specific to their domain. In this thesis, we focus on IL in two domains that pose their own unique challenges.

The first applicat...

Expand abstract

Authors: Gupta, P

• DOI: 10.5287/ora-5rq49ema0
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: combinatorial optimisation; deep learning; deep learning in public health; graph neural networks (GNNs); COVID-19 digital contact tracing; mixed-integer linear programming (MILP); contact tracing; imitation learning; artificial intelligence; proactive contact tracing (PCT); linear programming; agent-based modeling (ABM)
• Subjects: Contact tracing (Epidemiology); Deep learning (Machine learning); Artificial intelligence; Integer programming; Mathematical optimisation