Bandit problems with infinitely many arms

Annals of Statistics

Volumn 25, Issue 5, 1997, Pages 2103-2116

  Berry, Donald A ^a   Chen, Robert W ^c   Zame, Alan ^c   Heath, David C ^b   Shepp, Larry A ^d  

^a DUKE UNIVERSITY   (United States)

^b Department of Obstetrics Gynecology   (United States)

^c UNIVERSITY OF MIAMI   (United States)

^d RUTGERS UNIVERSITY   (United States)

Author keywords

Bandit problems; Dynamic allocation of bernoulli processes; Sequential experimentation; Staying with a winner; Switching with a loser

Indexed keywords

EID: 0031534756     PISSN: 00905364     EISSN: None     Source Type: Journal    
DOI: 10.1214/aos/1069362389     Document Type: Article

References (10)

1. BANKS, J. S. and SUNDARAM, R. K. (1992). Denumerable-armed bandits. Econometrica 60 1071-1096.
2. BERRY, D. A. and FRISTEDT, B. (1985). Bandit Problems: Sequential Allocations of Experiments. Chapman and Hall, London.
3. FELLER, W. (1971). An Introduction to Probability Theory and Its Applications, 2nd ed. Wiley, New York.
4. GITTINS, J. C. (1989). Multi-armed Bandit Allocation Indices. Wiley, New York.
5. HERSCHKORN, S. J., PEKOZ, E. and ROSS, S. M. (1995). Policies without memory for the infinite-armed Bernoulli bandit under the average-reward criterion. Probab. Engrg. Inform. Sci. 10 21-28.
6. JOVANOVIC, B. (1979). Job-search and the theory of turnover. Journal of Political Economy 87 972-990.
7. ROBBINS, H. (1952). Some aspects of the sequential design of experiments. Bull. Amer. Math. Soc. 58 527-536.
8. WHITTLE, P. (1982, 1983). Optimization over Time 1, 2. Wiley, New York.
9. WILDE, L. (1979). An information-theoretic approach to job quits. In Studies in the Economics of Search (S. Lippman and J. McCall, eds.) 35-52. North-Holland, Amsterdam.
10. VISCUSI, W. (1979). Job-hazards and worker quit rates: an analysis of adaptive worker behavior. Internat. Econ. Rev. 20 29-58.