Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Eaton, Eric, Hussing, Marcel, Kearns, Michael, Roth, Aaron, Sengupta, Sikata Bela, Sorrell, Jessica
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913693809246208
author Eaton, Eric
Hussing, Marcel
Kearns, Michael
Roth, Aaron
Sengupta, Sikata Bela
Sorrell, Jessica
author_facet Eaton, Eric
Hussing, Marcel
Kearns, Michael
Roth, Aaron
Sengupta, Sikata Bela
Sorrell, Jessica
contents In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real-world settings, it is important to optimize over multiple objectives simultaneously. For example, when we are interested in fairness, states might have feature annotations corresponding to multiple (intersecting) demographic groups to whom reward accrues, and our goal might be to maximize the reward of the group receiving the minimal reward. In this work, we consider a multi-objective optimization problem in which each objective is defined by a state-based reweighting of a single scalar reward function. This generalizes the problem of maximizing the reward of the minimum reward group. We provide oracle-efficient algorithms to solve these multi-objective RL problems even when the number of objectives is exponentially large-for tabular MDPs, as well as for large MDPs when the group functions have additional structure. Finally, we experimentally validate our theoretical results and demonstrate applications on a preferential attachment graph MDP.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
Eaton, Eric
Hussing, Marcel
Kearns, Michael
Roth, Aaron
Sengupta, Sikata Bela
Sorrell, Jessica
Machine Learning
Computer Science and Game Theory
In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real-world settings, it is important to optimize over multiple objectives simultaneously. For example, when we are interested in fairness, states might have feature annotations corresponding to multiple (intersecting) demographic groups to whom reward accrues, and our goal might be to maximize the reward of the group receiving the minimal reward. In this work, we consider a multi-objective optimization problem in which each objective is defined by a state-based reweighting of a single scalar reward function. This generalizes the problem of maximizing the reward of the minimum reward group. We provide oracle-efficient algorithms to solve these multi-objective RL problems even when the number of objectives is exponentially large-for tabular MDPs, as well as for large MDPs when the group functions have additional structure. Finally, we experimentally validate our theoretical results and demonstrate applications on a preferential attachment graph MDP.
title Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
topic Machine Learning
Computer Science and Game Theory
url https://arxiv.org/abs/2502.11828