When can the two-armed bandit algorithm be trusted?

Annals of Applied Probability

Volumn 14, Issue 3, 2004, Pages 1424-1454

  Lamberton, Damien ^a,d   Pagès, Gilles ^b   Tarrès, Pierre ^c,e  

^a UNIVERSITÉ GUSTAVE EIFFEL   (France)

^b SORBONNE UNIVERSITÉ   (France)

^c UNIVERSITÉ DE TOULOUSE   (France)

^d UFR des Sciences et Technologie   (France)

^e CNRS   (France)

Author keywords

Asset allocation; Learning automata; P lya urn; Stochastic approximation; Two armed bandit algorithm

Indexed keywords

EID: 26844528216     PISSN: 10505164     EISSN: 10505164     Source Type: Journal    
DOI: 10.1214/105051604000000350     Document Type: Article

References (17)

1. BALDI, P., MAZLIAK, L. and PRIOURET, P. (2000). Martingales et chaînes de Markov. Hermann, 2ē éd. Paris, or (2002). Martingales and Markov Chains. Chapman and Hall/CRC, London.
2. BENAǏM, M. and HIRSCH, M. W. (1996). Asymptotic pseudo-trajectories, chain recurrent flows and stochastic approximations. J. Dynam. Differential Equations 8 141-176.
3. BRANDIÈRE, O. and DUFLO, M. (1996). Les algorithmes stochastiques contournent-ils les pièges? Ann. Inst. H. Poincaré Probab. Statist. 32 395-427.
4. DACUNHA-CASTELLE, D. and DUFLO, M. (1983). Probabilités et Statistiques II. Problèmes à temps mobile. Masson, Paris, or (1986). Probability and Statistics II. Springer, New York.
5. DUFLO, M. (1996). Algorithmes Stochastiques. Springer, Berlin.
6. FORT, J. C. and PAG̀ES, G. (2002). Decreasing step stochastic algorithms: A.s. behaviour of weighted empirical measures. Monte Carlo Methods Appl. 8 221-320.
7. HALL, P. and HEYDE, C. C. (1980). Martingale Limit Theory and Its Application. Academic Press, New York.
8. KUSHNER, H. J. and CLARK, D. S. (1978). Stochastic Approximation for Constrained and Unconstrained Systems. Springer, New York.
9. LAZAREV, V. A. (1992). Convergence of stochastic approximation procedures in the case of a regression equation with several roots. Problemy Pederachi Infonnatsii 28.
10. NARENDRA, K. S. and THATHACHAR, M. A. L. (1974). Learning automata - a survey. IEEE Trans. Systems Man. Cybernetics S.M.C-4 323-334.
11. NARENDRA, K. S. and THATHACHAR, M. A. L. (1989). Learning Automata-An Introduction. Prentice-Hall, Englewood Cliffs, NJ.
12. NIANG, M. (1999). Algorithme de Narendra et application àl'allocation d'actifs. Rapport de stage de DEA, Olympia Capital Management et Univ. Marne-la-vallée, France.
13. NORMAN, M. F. (1968). On linear models with two absorbing barriers. J. Math. Psych. 5 225-241.
14. PEMANTLE, R. (1990). Nonconvergence to unstable points in urn models and stochastic approximations. Ann. Probab. 18 698-712.
15. 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. and Cybern. SSC-5 352-360.
16. TARRÈS, P. (2000). Pièges répulsifs. C. R. Acad. Sci. Paris Sér. 1330 125-130.
17. TARRÈS, P. (2001). Pièges des Algorithmes stochastiques et marches aléatoires renforcées par sommets. Thèse de l'ENS Cachan, France.