# Human-AI Learning Performance in Multi-Armed Bandits

## TL;DR

This study investigates how human-AI teams perform in multi-armed bandit tasks, revealing complex interactions where agent performance and human strategies influence overall effectiveness, with potential for improved decision-making.

## Contribution

The paper introduces an analysis of human-AI collaboration in multi-armed bandits, highlighting how agent performance impacts team outcomes and the importance of matching strategies.

## Key findings

- Team performance can surpass individual human or agent performance.
- Agent performance does not always predict team success.
- Matching human strategies with agents enhances decision-making.

## Abstract

People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at learning such tasks. Thus, there is an opportunity for AI agents to assist people in learning these tasks more effectively. In this work, we use a multi-armed bandit as a controlled setting in which to explore this direction. We pair humans with a selection of agents and observe how well each human-agent team performs. We find that team performance can beat both human and agent performance in isolation. Interestingly, we also find that an agent's performance in isolation does not necessarily correlate with the human-agent team's performance. A drop in agent performance can lead to a disproportionately large drop in team performance, or in some settings can even improve team performance. Pairing a human with an agent that performs slightly better than them can make them perform much better, while pairing them with an agent that performs the same can make them them perform much worse. Further, our results suggest that people have different exploration strategies and might perform better with agents that match their strategy. Overall, optimizing human-agent team performance requires going beyond optimizing agent performance, to understanding how the agent's suggestions will influence human decision-making.