Model-agnostic Fits for Understanding Information Seeking Patterns in Humans

TL;DR

This paper introduces a model-agnostic deep learning approach to accurately predict human information-seeking behavior in decision-making tasks, capturing individual differences without relying on specific task assumptions.

Contribution

It demonstrates that large-scale sampling can overcome limited data per individual and that high-accuracy predictions are possible without task-specific assumptions.

Findings

High prediction accuracy of human behavior without task assumptions

Large-scale sampling captures individual differences effectively

Model-agnostic approach reduces reliance on inductive biases

Abstract

In decision making tasks under uncertainty, humans display characteristic biases in seeking, integrating, and acting upon information relevant to the task. Here, we reexamine data from previous carefully designed experiments, collected at scale, that measured and catalogued these biases in aggregate form. We design deep learning models that replicate these biases in aggregate, while also capturing individual variation in behavior. A key finding of our work is that paucity of data collected from each individual subject can be overcome by sampling large numbers of subjects from the population, while still capturing individual differences. In addition, we can predict human behavior with high accuracy without making any assumptions about task goals, reward structure, or individual biases, thus providing a model-agnostic fit to human behavior in the task. Such an approach can sidestep potential limitations in modeler-specified inductive biases, and has implications for computational modeling of human cognitive function in general, and of human-AI interfaces in particular.