Algorithms for Fairness in Sequential Decision Making

Min Wen; Osbert Bastani; Ufuk Topcu

AISTATS 2021poster88 citations

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.

BibTeX

@InProceedings{pmlr-v130-wen21a,
  title = 	 { Algorithms for Fairness in Sequential Decision Making },
  author =       {Wen, Min and Bastani, Osbert and Topcu, Ufuk},
  booktitle = 	 {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {1144--1152},
  year = 	 {2021},
  editor = 	 {Banerjee, Arindam and Fukumizu, Kenji},
  volume = 	 {130},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--15 Apr},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v130/wen21a/wen21a.pdf},
  url = 	 {https://proceedings.mlr.press/v130/wen21a.html},
  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. }
}