FAIRO: Fairness-aware Adaptation in Sequential-Decision Making for Human-in-the-Loop Systems

TL;DR

FAIRO is a novel algorithm designed to enhance fairness in sequential decision-making systems within Human-in-the-Loop environments by accounting for human variability and preferences over time, balancing fairness and utility.

Contribution

The paper introduces FAIRO, a new fairness-aware algorithm that decomposes complex fairness tasks into adaptive sub-tasks using reinforcement learning, applicable across multiple HITL applications.

Findings

FAIRO improves fairness by an average of 35.36% across tested applications.

It effectively balances fairness and utility based on application needs.

Demonstrates generalizability and effectiveness in diverse HITL scenarios.

Abstract

Achieving fairness in sequential-decision making systems within Human-in-the-Loop (HITL) environments is a critical concern, especially when multiple humans with different behavior and expectations are affected by the same adaptation decisions in the system. This human variability factor adds more complexity since policies deemed fair at one point in time may become discriminatory over time due to variations in human preferences resulting from inter- and intra-human variability. This paper addresses the fairness problem from an equity lens, considering human behavior variability, and the changes in human preferences over time. We propose FAIRO, a novel algorithm for fairness-aware sequential-decision making in HITL adaptation, which incorporates these notions into the decision-making process. In particular, FAIRO decomposes this complex fairness task into adaptive sub-tasks based on individual human preferences through leveraging the Options reinforcement learning framework. We design FAIRO to generalize to three types of HITL application setups that have the shared adaptation decision problem. Furthermore, we recognize that fairness-aware policies can sometimes conflict with the application's utility. To address this challenge, we provide a fairness-utility tradeoff in FAIRO, allowing system designers to balance the objectives of fairness and utility based on specific application requirements. Extensive evaluations of FAIRO on the three HITL applications demonstrate its generalizability and effectiveness in promoting fairness while accounting for human variability. On average, FAIRO can improve fairness compared with other methods across all three applications by 35.36%.