In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of int...
We define the k-path tree matroid, and use it to solve network design problems in which the required connectivity is arbitrary for a given pair of nodes, and 1 for the other pairs...
We consider the restless multi-armed bandit (RMAB) problem with unknown dynamics. In this problem, at each time, a player chooses K out of N (N > K) arms to play. The state of ...
Abstract—We consider the restless multi-armed bandit (RMAB) problem with unknown dynamics. At each time, a player chooses K out of N (N > K) arms to play. The state of each ar...