Avoiding starvation of arms in restless multi-armed bandit

• Main Authors: LI, Dexun, VARAKANTHAM, Pradeep
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Automated calls; Community OR; Fairness; Optimizing performance; Patient health; Restless multi-armed bandit; Softmax; Uncertainty; Whittle indexs; Workers'; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8593; https://ink.library.smu.edu.sg/context/sis_research/article/9596/viewcontent/Avoiding_Starvation_of_Arms_in_Restless_Multi_Armed_Bandits.pdf
• Institution: Singapore Management University

Restless multi-armed bandits (RMAB) is a popular framework for optimizing performance with limited resources under uncertainty. It is an extremely useful model for monitoring beneficiaries (arms) and executing timely interventions using health workers (limited resources) to ensure optimal benefit in public health settings. For instance, RMAB has been used to track patients' health and monitor their adherence in tuberculosis settings, ensure pregnant mothers listen to automated calls about good pregnancy practices, etc. Due to the limited resources, typically certain individuals, communities, or regions are starved of interventions, which can potentially have a significant negative impact on the individual/community in the long term. To that end, we first define a soft fairness objective which entails an algorithm never probabilistically favors one arm over another if the long-term cumulative reward of choosing the latter arm is higher. Then we provide a scalable approach to ensure long-term optimality while satisfying the proposed fairness constraints in RMAB. Our method, referred to as SoftFair, can balance the tradeoff between the goal of having resources uniformly distributed and maximizing cumulative rewards. SoftFair also provides theoretical performance guarantees and is asymptotically optimal. Finally, we demonstrate the utility of our approaches on simulated benchmarks and show that the soft fairness objective can be handled without a significant sacrifice on the optimal value.