Towards Human-AI Cooperation on Sequential Decision Making Problems

Abstract

The tools we use have a great impact on our productivity. It is imperative that tools are designed with the user’s objectives in mind. From self-driving cars to tackling misinformation, from machine translation to breast cancer diagnosis, we are relying more and more on tools with artificial intelligence (AI) powered by machine learning models. This thesis focuses on developing machine learning models that are maximally useful to humans. Our primary goal is to improve the productivity of human-AI cooperation on important decision making problems by understanding how human and AI interact. In the traditional approach to machine learning, humans are treated as either rivals or teachers. However, machine learning can make up for some of the shortcomings of humans. Treating humans as collaborators opens up several new directions of research. In the first part of the thesis, we use flashcard learning as a testbed and study how human productivity can benefit from passively consuming information generated by machine learning models. In the second part, we consider humans as active decision makers, and investigate how explanations of machine learning predictions can improve the performance of human-AI teams on sequential decision making problems. Finally, we study the limitations of natural language explanations for model predictions, as well as novel methods to improve them.