Algorithms for Fairness in Sequential Decision Making

Abstract

It has recently been shown that if feedback effects of decisions are ignored, then imposing fairness constraints such as demographic parity or equality of opportunity can actually exacerbate unfairness. We propose to address this challenge by modeling feedback effects as Markov decision processes (MDPs). First, we propose analogs of fairness properties for the MDP setting. Second, we propose algorithms for learning fair decision-making policies for MDPs. Finally, we demonstrate the need to account for dynamical effects using simulations on a loan applicant MDP.

Cited by in corpus (6)

• Fairness in Forecasting of Observations of Linear Dynamical Systems
• Recommendation Fairness: From Static to Dynamic
• Achievement and Fragility of Long-term Equitability
• Fairness Through Counterfactual Utilities
• Algorithm Fairness in AI for Medicine and Healthcare
• Stacking interventions for equitable outcomes