1. Agrawal, R., D. Teneketzis and V. Anantharam. (1989a). Asymptotically efficient adaptive allocation schemes for controlled I.I.D. processes: Finite parameter space. IEEE Trans. Automat. Contr. 34, 258–267.
2. Agrawal, R., D. Teneketzis and V. Anantharam. (1989b). Asymptotically efficient adaptive allocation schemes for controlled Markov chains: Finite parameter space. IEEE Trans. Automat. Contr. 34, 1249–1259.
3. Anantharam, V., P. Varaiya and J. Walrand. (1987). Asymptotically efficient allocation rules for multiarmed bandit problems with multiple plays. Part II: Markovian rewards. IEEE Trans. Automat. Contr.32, 975–982.
4. Banks, J. S. and R.K. Sundaram. (1992). Denumerable-armed bandits. Econometrica60, 1071–1096.
5. Banks, J. S. and R.K. Sundaram. (1994). Switching costs and the Gittins index. Econometrica62, 687–694.