Human-Modeling in Sequential Decision-Making: An Analysis through the Lens of Human-Aware AI

TL;DR

This paper analyzes human-aware AI systems in sequential decision-making, proposing a framework to categorize interactions, reviewing recent literature, and highlighting overlooked research areas and validation practices.

Contribution

It introduces a conceptual framework for understanding human-aware AI, reviews recent work in the field, and identifies gaps in social science integration and user validation.

Findings

Most works focus on modeling humans in decision-making

Limited explicit use of social science results in current research

Few studies perform user-studies to validate human-aware AI systems

Abstract

"Human-aware" has become a popular keyword used to describe a particular class of AI systems that are designed to work and interact with humans. While there exists a surprising level of consistency among the works that use the label human-aware, the term itself mostly remains poorly understood. In this work, we retroactively try to provide an account of what constitutes a human-aware AI system. We see that human-aware AI is a design oriented paradigm, one that focuses on the need for modeling the humans it may interact with. Additionally, we see that this paradigm offers us intuitive dimensions to understand and categorize the kinds of interactions these systems might have with humans. We show the pedagogical value of these dimensions by using them as a tool to understand and review the current landscape of work related to human-AI systems that purport some form of human modeling. To fit the scope of a workshop paper, we specifically narrowed our review to papers that deal with sequential decision-making and were published in a major AI conference in the last three years. Our analysis helps identify the space of potential research problems that are currently being overlooked. We perform additional analysis on the degree to which these works make explicit reference to results from social science and whether they actually perform user-studies to validate their systems. We also provide an accounting of the various AI methods used by these works.