Fairness in Reinforcement Learning: A Survey

TL;DR

This survey reviews recent advances in fairness in reinforcement learning, highlighting definitions, methodologies, applications, and gaps to guide future research in responsible AI deployment.

Contribution

It provides a comprehensive overview of fairness concepts, methods, and applications in RL, identifying key gaps and future directions for operationalizing fair RL.

Findings

Various fairness definitions in RL are discussed.

Methodologies for implementing fairness in single- and multi-agent RL are summarized.

Identifies gaps such as fairness in RLHF and real-world deployment challenges.

Abstract

While our understanding of fairness in machine learning has significantly progressed, our understanding of fairness in reinforcement learning (RL) remains nascent. Most of the attention has been on fairness in one-shot classification tasks; however, real-world, RL-enabled systems (e.g., autonomous vehicles) are much more complicated in that agents operate in dynamic environments over a long period of time. To ensure the responsible development and deployment of these systems, we must better understand fairness in RL. In this paper, we survey the literature to provide the most up-to-date snapshot of the frontiers of fairness in RL. We start by reviewing where fairness considerations can arise in RL, then discuss the various definitions of fairness in RL that have been put forth thus far. We continue to highlight the methodologies researchers used to implement fairness in single- and multi-agent RL systems before showcasing the distinct application domains that fair RL has been investigated in. Finally, we critically examine gaps in the literature, such as understanding fairness in the context of RLHF, that still need to be addressed in future work to truly operationalize fair RL in real-world systems.