To address this shortcoming we propose a novel approach for decision-focused learning in RMAB that directly trains the predictive model to maximize the Whittle index solution quality.
Our second major contribution is evaluation of our RMAB system in collaboration with an NGO, via a real-world service quality improvement study.
Our contributions are as follows: (1) We derive conditions under which our problem satisfies indexability, a precondition that guarantees the existence and asymptotic optimality of the Whittle Index solution for RMABs.
no code implementations • 7 Mar 2021 • Siddharth Nishtala, Lovish Madaan, Aditya Mate, Harshavardhan Kamarthi, Anirudh Grama, Divy Thakkar, Dhyanesh Narayanan, Suresh Chaudhary, Neha Madhiwalla, Ramesh Padmanabhan, Aparna Hegde, Pradeep Varakantham, Balaraman Ravindran, Milind Tambe
India has a maternal mortality ratio of 113 and child mortality ratio of 2830 per 100, 000 live births.
Our main contributions are as follows: (i) Building on the Whittle index technique for RMABs, we derive conditions under which the Collapsing Bandits problem is indexable.
(ii) We exploit the optimality of threshold policies to build fast algorithms for computing the Whittle index, including a closed-form.
Stackelberg security games are a critical tool for maximizing the utility of limited defense resources to protect important targets from an intelligent adversary.