Fairness in Reinforcement Learning with Bisimulation Metrics

2024/12/22 by Sahand Rezaei-Shoshtari, Rezaei-Shoshtari, Sahand, Hanna Yurchyk +7
Computer Science · Neuroscience · Social Sciences · #Computers and Society (cs.CY) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Behavioral Psychology Studies #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.2412.17123

openalex publication_date 2024/12/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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

• Reinforcement Learning with Stepwise Fairness Constraints
• What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning
• Survey on Fair Reinforcement Learning: Theory and Practice
• Group Fairness in Multi-Task Reinforcement Learning
• Fairness in Reinforcement Learning: A Survey