1. Asymptotically efficient adaptive allocation rules for the multiarmed bandit problem with switching costs;Agrawal;IEEE Transactions on Automatic Control,1988
2. Denumerable-narmed bandits;Banks;Econometrica,1992
3. Switching costs and the Gittins index;Banks;Econometrica,1994
4. A Bernoulli two-armed bandit;Berry;Annals of Mathematical Statistics,1972
5. Brezzi, M., Lai, T.L., 1999. Optimal stopping for Brownian motion in bandit problems and sequential analysis, Working Paper, Department of Statistics, Stanford University.