Algorithms for Fairness in Sequential Decision Making
This addresses fairness in sequential decision-making for domains like loans, but it is incremental as it adapts existing fairness concepts to MDPs.
The paper tackles the problem that fairness constraints can worsen unfairness when feedback effects are ignored, by modeling feedback as Markov decision processes and proposing algorithms for fair policies, demonstrating the need for dynamic accounting through loan applicant simulations.
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.