Global Rewards in Restless Multi-Armed Bandits
Restless multi-armed bandits (RMAB) extend multi-armed bandits so pulling an arm impacts
future states. Despite the success of RMABs, a key limiting assumption is the separability of …
future states. Despite the success of RMABs, a key limiting assumption is the separability of …
Contextual Restless Multi-Armed Bandits with Application to Demand Response Decision-Making
This paper introduces a novel multi-armed bandits framework, termed Contextual Restless
Bandits (CRB), for complex online decision-making. This CRB framework incorporates the …
Bandits (CRB), for complex online decision-making. This CRB framework incorporates the …