How fast is the bandit?

Stochastic Analysis and Applications

Volumn 26, Issue 3, 2008, Pages 603-623

  Lamberton, Damien ^a   Pagès, Gilles ^b,c  

^a UFR des Sciences et Technologie   (France)

^b University of Paris VII LPSM partially supported by ERC Starting Grant 680275 MALIG   (France)

^c SORBONNE UNIVERSITÉ   (France)

Author keywords

Asset allocation; Learning automata; Stochastic approximation; Two armed bandit algorithm

Indexed keywords

EID: 45749127104     PISSN: 07362994     EISSN: 15329356     Source Type: Journal    
DOI: 10.1080/07362990802007202     Document Type: Article

References (20)

1. Bai, Z.-D., and Hu, F. 2005. Asymptotics in randomized urn models. Annals of Applied Probability, 15:914-940.
2. Bouton, C. 1988. Approximation gaussienne d'algorithmes stochastiques à dynamique markovienne. Ann. Inst. Henri Poincaré, Probab. Stat. 24(1):131-155.
3. Brandière, O., and Duflo, M. 1996. Les algorithmes stochastiques contournent-ils les pièges? Ann. Inst. H. Poincaré Probab. Statist. 32:395-427.
4. Duflo, M. 1997. Random Iterative Models, trans. by Stephen S. Wilson; rev. by M. Duflo. Applications of Mathematics. Springer-Verlag, New York, Berlin, vol. 34.
5. Fort, J.C., and Pagès, G. 2002. Decreasing step stochastic algorithms: a.s. behavior of weighted empirical measures. Monte Carlo Methods and Applications 8(3):237-270.
6. Hall, P., and Heyde, C.C. 1980. Martingale Limit Theory and Its Application. Academic Press, New York, 308 p.
7. Kushner, H.J., and Yin, G.G. 2003. Stochastic approximation and recursive algorithms and applications. Applications of Mathematics, Stochastic Modelling and Applied Probability. 2nd ed. Springer-Verlag, New York, vol. 35.
8. Lamberton, D., Pagès, G., and Tarrès, P. 2004. When can the two-armed bandit algorithm be trusted?. Annals of Applied Probability, 14(3):1424-1454.
9. Lamberton, D., and Pagès, G. 2005. A penalized bandit algorithm. Electronic Journal of Probability 13:341-373.
10. Lazarev, V.A. 1992. Convergence of stochastic approximation procedures in the case of a regression equation with several roots, (transl. from) Problemy Pederachi Informatsii, vol. 28(1).
11. Narendra, K.S., and Thathachar, M.A.L. 1974. Learning Automata-A Survey. IEEE Trans. Systems, Man., Cybernetics S.M.C-4, pp. 323-334.
12. Narendra, K.S., and Thathachar, M.A.L. 1989. Learning Automata-An Introduction. Prentice Hall, Englewood Cliffs, NJ, 476. p
13. Neveu, J. 1975. Discrete-Parameter Martingales. North-Holland, New York.
14. Norman, M.F. 1968. On linear models with two absorbing barriers. Journal of Mathematical Psychology, 5:225-241.
15. Pelletier, M. 1998. Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing. Annals of Applied Probability 8(1):10-44.
16. Pemantle, R. 1990. Nonconvergence to unstable points in urn models and stochastic approximations. Annals of Probability 18(2):698-712.
17. Shapiro, I.J., and Narendra, K.S. 1969. Use of stochastic automata for parameter self-optimization with multi-modal perfomance criteria. IEEE Trans. Syst. Sci. Cybern. SSC-5:352-360.
18. Tarrès, P. 2000. Pièges répulsifs. C.R.A.S. Acad. Sc. de Paris, Série I 330:125-130.
19. Tarrès, P. 2001. Algorithmes Stochastiques et Marches Aléatoires Renforcées. Thèse de l'ENS Cachan (France).
20. Tarrès, P., and Vandekerkhove, P. 2006. On the ergodic two-armed bandit algorithm. University Paris-Est Marne-la-Vallée.