Fairness in Reinforcement Learning

Paul Weng

Fairness in Reinforcement Learning

Machine Learning 2019-07-25 v1 Artificial Intelligence Machine Learning

Authors: Paul Weng

Abstract

Decision support systems (e.g., for ecological conservation) and autonomous systems (e.g., adaptive controllers in smart cities) start to be deployed in real applications. Although their operations often impact many users or stakeholders, no fairness consideration is generally taken into account in their design, which could lead to completely unfair outcomes for some users or stakeholders. To tackle this issue, we advocate for the use of social welfare functions that encode fairness and present this general novel problem in the context of (deep) reinforcement learning, although it could possibly be extended to other machine learning tasks.

Keywords

fairness in machine learning social welfare reinforcement learning

Cite

@article{arxiv.1907.10323,
  title  = {Fairness in Reinforcement Learning},
  author = {Paul Weng},
  journal= {arXiv preprint arXiv:1907.10323},
  year   = {2019}
}

Comments

Presented at the AI for Social Good Workshop at IJCAI 2019

Related papers

View all related →