Equitable Restless Multi-Armed Bandits: A General Framework Inspired By Digital Health
Jackson A. Killian, Manish Jain, Yugang Jia, Jonathan Amar, Erich, Huang, Milind Tambe

TL;DR
This paper introduces a framework for equitable decision-making in restless multi-armed bandits, addressing fairness in high-stakes digital health applications with algorithms that improve equity without sacrificing utility.
Contribution
It pioneers the study of equitable objectives in RMABs, developing novel algorithms for fairness aligned with public health and digital health applications.
Findings
Algorithms significantly improve fairness across groups.
Approaches maintain high utility levels.
Effective in digital health simulation models.
Abstract
Restless multi-armed bandits (RMABs) are a popular framework for algorithmic decision making in sequential settings with limited resources. RMABs are increasingly being used for sensitive decisions such as in public health, treatment scheduling, anti-poaching, and -- the motivation for this work -- digital health. For such high stakes settings, decisions must both improve outcomes and prevent disparities between groups (e.g., ensure health equity). We study equitable objectives for RMABs (ERMABs) for the first time. We consider two equity-aligned objectives from the fairness literature, minimax reward and max Nash welfare. We develop efficient algorithms for solving each -- a water filling algorithm for the former, and a greedy algorithm with theoretically motivated nuance to balance disparate group sizes for the latter. Finally, we demonstrate across three simulation domains, including…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Bandit Algorithms Research
