Designing Algorithmic Delegates: The Role of Indistinguishability in Human-AI Handoff

TL;DR

This paper explores how to design optimal AI delegates that consider human categorization of instances, revealing complex, computationally hard problems but also providing efficient solutions and practical insights through simulations.

Contribution

It introduces the problem of designing optimal algorithmic delegates with categorization, demonstrating its complexity and providing algorithms for key cases.

Findings

Optimal delegates can outperform standalone algorithms.

Designing optimal delegates is computationally hard in general.

Efficient algorithms exist for certain decomposable cases.

Abstract

As AI technologies improve, people are increasingly willing to delegate tasks to AI agents. In many cases, the human decision-maker chooses whether to delegate to an AI agent based on properties of the specific instance of the decision-making problem they are facing. Since humans typically lack full awareness of all the factors relevant to this choice for a given decision-making instance, they perform a kind of categorization by treating indistinguishable instances -- those that have the same observable features -- as the same. In this paper, we define the problem of designing the optimal algorithmic delegate in the presence of categories. This is an important dimension in the design of algorithms to work with humans, since we show that the optimal delegate can be an arbitrarily better teammate than the optimal standalone algorithmic agent. The solution to this optimal delegation problem is not obvious: we discover that this problem is fundamentally combinatorial, and illustrate the complex relationship between the optimal design and the properties of the decision-making task even in simple settings. Indeed, we show that finding the optimal delegate is computationally hard in general. However, we are able to find efficient algorithms for producing the optimal delegate in several broad cases of the problem, including when the optimal action may be decomposed into functions of features observed by the human and the algorithm. Finally, we run computational experiments to simulate a designer updating an algorithmic delegate over time to be optimized for when it is actually adopted by users, and show that while this process does not recover the optimal delegate in general, the resulting delegate often performs quite well.