Towards Soft Fairness in Restless Multi-Armed Bandits
Dexun Li, Pradeep Varakantham

TL;DR
This paper introduces SoftFair, a novel approach for incorporating soft fairness constraints into restless multi-armed bandits, ensuring equitable resource allocation without significant loss in reward.
Contribution
It proposes a soft fairness constraint for RMABs and develops a softmax-based value iteration algorithm that guarantees asymptotic optimality and fairness.
Findings
SoftFair effectively enforces fairness in simulated benchmarks.
The approach achieves near-optimal rewards while maintaining fairness.
Theoretical guarantees support the method's asymptotic optimality.
Abstract
Restless multi-armed bandits (RMAB) is a framework for allocating limited resources under uncertainty. It is an extremely useful model for monitoring beneficiaries and executing timely interventions to ensure maximum benefit in public health settings (e.g., ensuring patients take medicines in tuberculosis settings, ensuring pregnant mothers listen to automated calls about good pregnancy practices). Due to the limited resources, typically certain communities or regions are starved of interventions that can have follow-on effects. To avoid starvation in the executed interventions across individuals/regions/communities, we first provide a soft fairness constraint and then provide an approach to enforce the soft fairness constraint in RMABs. The soft fairness constraint requires that an algorithm never probabilistically favor one arm over another if the long-term cumulative reward of…
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Bandit Algorithms Research
MethodsSoftmax
