Fairness in Reinforcement Learning: A Survey
This work is a survey that synthesizes existing literature to help researchers and practitioners address fairness in dynamic, long-term RL systems like autonomous vehicles, but it is incremental as it does not introduce new methods or results.
The paper surveys the current state of fairness in reinforcement learning (RL), addressing the gap in understanding compared to one-shot classification tasks, and provides an overview of definitions, methodologies, and application domains to guide future research.
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.