A class of bandit problems yielding myopic optimal strategies
Authors:
- Jeffrey S. BanksJBJeffrey S. Banks
- Rangarajan K. SundaramRSRangarajan K. Sundaram
- 1 September 1992
- journal article
- Published by Cambridge University Press (CUP) in Journal of Applied Probability
- Vol. 29 (3) , 625-632
Abstract
We consider the class of bandit problems in which each of the n ≧ 2 independent arms generates rewards according to one of the same two reward distributions, and discounting is geometric over an infinite horizon. We show that the dynamic allocation index of Gittins and Jones (1974) in this context is strictly increasing in the probability that an arm is the better of the two distributions. It follows as an immediate consequence that myopic strategies are the uniquely optimal strategies in this class of bandit problems, regardless of the value of the discount parameter or the shape of the reward distributions. Some implications of this result for bandits with Bernoulli reward distributions are given.Keywords
This publication has 5 references indexed in Scilit:
- Some results on two-armed bandits when both projects varyJournal of Applied Probability, 1989
- Optimality of myopic stopping times for geometric discountingJournal of Applied Probability, 1988
- Bandit problems1985
- On the Many-armed Bandit ProblemThe Annals of Probability, 1978
- Contributions to the "Two-Armed Bandit" ProblemThe Annals of Mathematical Statistics, 1962