Optimizing delegation between human and AI collaborative agents

TL;DR

This paper presents a framework for training a delegating manager in human-AI hybrid teams, enabling optimal delegation decisions despite agents operating under different environmental models, leading to improved team performance.

Contribution

It introduces a novel manager model that learns delegation policies from team performance observations without assuming identical agent dynamics.

Findings

Manager outperforms alternative delegation methods

Effective in teams with agents having different environment models

Learned policies adapt to diverse agent behaviors

Abstract

In the context of humans operating with artificial or autonomous agents in a hybrid team, it is essential to accurately identify when to authorize those team members to perform actions. Given past examples where humans and autonomous systems can either succeed or fail at tasks, we seek to train a delegating manager agent to make delegation decisions with respect to these potential performance deficiencies. Additionally, we cannot always expect the various agents to operate within the same underlying model of the environment. It is possible to encounter cases where the actions and transitions would vary between agents. Therefore, our framework provides a manager model which learns through observations of team performance without restricting agents to matching dynamics. Our results show our manager learns to perform delegation decisions with teams of agents operating under differing representations of the environment, significantly outperforming alternative methods to manage the team.