Indexability and whittle index for restless bandit problems involving reset processes
Keqin Liu, Richard Weber, Qing Qi Zhao · 2011
We consider a class of restless multi-armed bandit (RMAB) problems, in which the active action resets the stochastic evolution of the system. We obtain the Whittle index in closed-form, showing that it induces a policy that is equivalent to the myopic policy, and that it is optimal for stochastically identical arms. These results find applications in opportunistic spectrum access and supervisory control systems such as anomaly detection and control.