We utilize and develop elements of the recent achievable region account of
Gittins indexation by Bertsimas and Nino-Mora to design index-based policie
s for discounted multi-armed bandits on parallel machines. The policies ana
lyzed have expected rewards which come within an O(alpha) quantity of optim
ality, where alpha > 0 is a discount rate. In the main, the policies make a
n initial once for all allocation of bandits to machines, with each machine
then handling its own workload optimally. This allocation must take carefu
l account of the index structure of the bandits. The corresponding limit po
licies are average-overtaking optimal.