Bandit problems and the exploration/exploitation tradeoff

IEEE Transactions on Evolutionary Computation

Volumn 2, Issue 1, 1998, Pages 2-22

  Macready, William G ^a   Wolpert, David H ^b  

^a Bios Group   (United States)

^b NASA AMES RESEARCH CENTER   (United States)

Author keywords

Bandit problems; Expected losses; Genetic algorithms; Greedy strategies

Indexed keywords

COMPUTER SIMULATION; ERROR CORRECTION; GENETIC ALGORITHMS; MATHEMATICAL MODELS; OPTIMIZATION; PROBLEM SOLVING;

BAYESIAN METHOD; GAUSSIAN BANDIT PROBLEM;

COMPUTATIONAL METHODS;

EID: 0032035573     PISSN: 1089778X     EISSN: None     Source Type: Journal    
DOI: 10.1109/4235.728210     Document Type: Article

References (15)

1. D. A. Berry and B. Fristedt, Bandit Problems, Sequential Allocation of Experiments. London, U.K.: Chapman and Hall, 1985.
2. D. P. Bertsekas, Dynamic Programming: Deterministic and Stochastic Models. Englewood Cliffs, NJ: Prentice-Hall, 1987.
3. D. Feldman, Contributions to the two-armed bandit problem, Ann. Math. Statist., vol. 33, pp. 847-856, 1962.
4. D. B. Fogel, Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. Piscataway, NJ: IEEE Press, 1995.
5. J. Hardwick, C. Page, and Q. F. Stout, Sequentially deciding between two experiments for estimating a common success probability, J. Amer. Statist. Assoc., 1998, to be published.
6. J. H. Holland, Genetic algorithms and the optimal allocation of trials, SIAM J. Comput., vol. 2, pp. 88-105, 1973.
7. _, Adaptation in Natural and Artificial Systems. Ann Arbor, MI: Univ. of Michigan Press, 1975.
8. O. E. Perçus and J. K. Perçus, Modified Bayes technique in sequential clinical trials, Comput. Biol. Med., vol. 14, pp. 127-134, 1984.
9. A. J. Petkau, Sequential medical trials for comparing an experimental with a standard treatment, J. Amer. Statist. Assoc., vol. 73, pp. 328-338, 1978.
10. R. Rohwer and H. Zhu, A Bayesian formulation of search, control and exploration/exploitation trade-off, unpublished.
11. G. Rudolph, Reflections on bandit problems and selection methods in uncertain environments, in Proc. 7th Int. Conf. Genetic Algorithms, T. Back, Ed., San Francisco, CA, 1997, pp. 166-173.
12. W. R. Thompson, On the likelihood that one unknown probability exceeds another in view of the evidence of two samples, Biometrika, vol. 25, pp. 285-294, 1933.
13. _, On the theory of apportionment, Amer. J. Math., vol. 57, pp. 450-457, 1935.
14. W. K. Viscusi, Job hazards and worker quit rates: An analysis of adaptive worker behavior, Int. Econom. Rev., vol. 20, pp. 29-58, 1979.
15. D. H. Wolpert and W. G. Macready, No free lunch theorems for optimization, IEEE Trans. Evol. Comput., vol. 1, pp. 67-83, 1997.