Related papers: Fairness in Reinforcement Learning with Bisimulation Metrics

Fairness in Reinforcement Learning with Bisimulation Metrics

URL: http://arxiv.org/abs/2412.17123v2
Date: Tue, 31 Dec 2024 14:55:25 GMT
Title: Fairness in Reinforcement Learning with Bisimulation Metrics
Authors: Sahand Rezaei-Shoshtari, Hanna Yurchyk, Scott Fujimoto, Doina Precup, David Meger,
Abstract summary: By maximizing their reward without consideration of fairness, AI agents can introduce disparities in their treatment of groups or individuals. We propose a novel approach that leverages bisimulation metrics to learn reward functions and observation dynamics.
Score: 45.674943127750595
License:
Abstract: Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environments. By maximizing their reward without consideration of fairness, AI agents can introduce disparities in their treatment of groups or individuals. In this paper, we establish the connection between bisimulation metrics and group fairness in reinforcement learning. We propose a novel approach that leverages bisimulation metrics to learn reward functions and observation dynamics, ensuring that learners treat groups fairly while reflecting the original problem. We demonstrate the effectiveness of our method in addressing disparities in sequential decision making problems through empirical evaluation on a standard fairness benchmark consisting of lending and college admission scenarios.

Related papers

Striking a Balance in Fairness for Dynamic Systems Through Reinforcement Learning [6.814499629376316]
We study fairness in dynamic systems where sequential decisions are made. We propose an algorithmic framework to integrate various fairness considerations with reinforcement learning. Three case studies show that our method can strike a balance between traditional fairness notions, long-term fairness, and utility.
arXiv Detail & Related papers (2024-01-12T01:29:26Z)
Equal Confusion Fairness: Measuring Group-Based Disparities in Automated Decision Systems [5.076419064097733]
This paper proposes a new equal confusion fairness test to check an automated decision system for fairness and a new confusion parity error to quantify the extent of any unfairness. Overall, the methods and metrics provided here may assess automated decision systems' fairness as part of a more extensive accountability assessment.
arXiv Detail & Related papers (2023-07-02T04:44:19Z)
Counterpart Fairness -- Addressing Systematic between-group Differences in Fairness Evaluation [17.495053606192375]
When using machine learning to aid decision-making, it is critical to ensure that an algorithmic decision is fair and does not discriminate against specific individuals/groups. Existing group fairness methods aim to ensure equal outcomes across groups delineated by protected variables like race or gender. In cases where systematic differences between groups play a significant role in outcomes, these methods may overlook the influence of non-protected variables.
arXiv Detail & Related papers (2023-05-29T15:41:12Z)
Fairness in Matching under Uncertainty [78.39459690570531]
algorithmic two-sided marketplaces have drawn attention to the issue of fairness in such settings. We axiomatize a notion of individual fairness in the two-sided marketplace setting which respects the uncertainty in the merits. We design a linear programming framework to find fair utility-maximizing distributions over allocations.
arXiv Detail & Related papers (2023-02-08T00:30:32Z)
Increasing Fairness via Combination with Learning Guarantees [8.314000998551865]
We propose a fairness quality measure named discriminative risk to reflect both individual and group fairness aspects. We also propose first- and second-order oracle bounds to show that fairness can be boosted via ensemble combination with theoretical learning guarantees.
arXiv Detail & Related papers (2023-01-25T20:31:06Z)
Reinforcement Learning with Stepwise Fairness Constraints [50.538878453547966]
We introduce the study of reinforcement learning with stepwise fairness constraints. We provide learning algorithms with strong theoretical guarantees in regard to policy optimality and fairness violation.
arXiv Detail & Related papers (2022-11-08T04:06:23Z)
Measuring and signing fairness as performance under multiple stakeholder distributions [39.54243229669015]
Best tools for measuring the fairness of learning systems are rigid fairness metrics encapsulated as mathematical one-liners. We propose to shift focus from shaping fairness metrics to curating the distributions of examples under which these are computed. We provide full implementation guidelines for stress testing, illustrate both the benefits and shortcomings of this framework.
arXiv Detail & Related papers (2022-07-20T15:10:02Z)
Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
arXiv Detail & Related papers (2021-09-17T13:45:46Z)
Can Active Learning Preemptively Mitigate Fairness Issues? [66.84854430781097]
dataset bias is one of the prevailing causes of unfairness in machine learning. We study whether models trained with uncertainty-based ALs are fairer in their decisions with respect to a protected class. We also explore the interaction of algorithmic fairness methods such as gradient reversal (GRAD) and BALD.
arXiv Detail & Related papers (2021-04-14T14:20:22Z)
Beyond Individual and Group Fairness [90.4666341812857]
We present a new data-driven model of fairness that is guided by the unfairness complaints received by the system. Our model supports multiple fairness criteria and takes into account their potential incompatibilities.
arXiv Detail & Related papers (2020-08-21T14:14:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.