Nearby in the stack

Reinforcement Learning with Stepwise Fairness Constraints · arXivDesk

2211.03994Nov 8, 2022Fairness, Reinforcement Learning

Reinforcement Learning with Stepwise Fairness Constraints

Zhun Deng, He Sun, Zhiwei Steven Wu, Linjun Zhang, David C. Parkes

Machine Learning Artificial Intelligence Computers and Society

Abstract

AI methods are used in societally important settings, ranging from credit to employment to housing, and it is crucial to provide fairness in regard to algorithmic decision making. Moreover, many settings are dynamic, with populations responding to sequential decision policies. We introduce the study of reinforcement learning (RL) with stepwise fairness constraints, requiring group fairness at each time step. Our focus is on tabular episodic RL, and we provide learning algorithms with strong theoretical guarantees in regard to policy optimality and fairness violation. Our framework provides useful tools to study the impact of fairness constraints in sequential settings and brings up new challenges in RL.

Briefing

What this paper is actually doing

This is a heuristic sketch from the abstract. Sign in for a live briefing.

GraduateNovelty 3/5

Researchers working in cs.LG and adjacent areas.

Claims

The paper addresses: Reinforcement Learning with Stepwise Fairness Constraints.
AI methods are used in societally important settings, ranging from credit to employment to housing, and it is crucial to provide fairness in regard to algorithmic decision making.