On ergodic two-armed bandits

Annals of Applied Probability

Volumn 22, Issue 2, 2012, Pages 457-476

  Tarrès, Pierre ^a,c   Vandekerkhove, Pierre ^b  

^a UNIVERSITÉ DE TOULOUSE   (France)

^b UFR des Sciences et Technologie   (France)

^c UNIVERSITY OF OXFORD   (United Kingdom)

Author keywords

Convergence; Ergodicity; Stochastic algorithms; Two armed bandit

Indexed keywords

EID: 84879806196     PISSN: 10505164     EISSN: None     Source Type: Journal    
DOI: 10.1214/10-AAP751     Document Type: Article

References (15)

1. BENAÏM, M. and BEN AROUS, G. (2003). A two armed type bandit problem. Internat. J. Game Theory 32 3-16. (Pubitemid 37550818)
2. DACUNHA-CASTELLE, D. and DUFLO, M. (1986). Probability and Statistics. Vol. II. Springer, New York. MR0837655
3. DUFLO, M. (1996). Algorithmes Stochastiques. Mathématiques and Applications (Berlin) [Mathematics and Applications] 23. Springer, Berlin. MR1612815
4. LAMBERTON, D. and PAGÈS, G. (2008). How fast is the bandit? Stoch. Anal. Appl. 26 603- 623. MR2401408
5. LAMBERTON, D. and PAGÈS, G. (2008). A penalized bandit algorithm. Electron. J. Probab. 13 341-373. MR2386736
6. LAMBERTON, D., PAGÈS, G. and TARRÈS, P. (2004). When can the two-armed bandit algorithm be trusted? Ann. Appl. Probab. 14 1424-1454. MR2071429 (Pubitemid 41449224)
7. LARUELLE, S. and PAGÈS, G. (2010). Stochastic approximation with averaging innovation. Preprint.
8. MIAO, Y. and YANG, G. (2008). The law of the iterated logarithm for additive functionals of Markov chains. Statist. Probab. Lett. 78 265-270. MR2387547
9. NARENDRA, K. S. and THATHACHAR, M. A. L. (1974). Learning automata - a survey. IEEE Trans. Systems Man Cybernet. SMC-4 323-334. MR0469583
10. NARENDRA, K. S. and THATHACHAR, M. A. L. (1989). Learning Automata - An Introduction. Prentice Hall, Englewood Cliffs, NJ.
11. NIANG, M. (1999). Algorithme de Narendra et application à l'allocation d'actifs. Rapport de stage de DEA, Olympia Capital Management et Univ. Marne-la-vallée (France).
12. NORMAN, M. F. (1968). On the linear model with two absorbing barriers. J. Math. Psych. 5 225-241. MR0226954
13. PAGÈS, G. (2005). A two-armed bandit type problem revisited. ESAIM Probab. Stat. 9 277-282 (electronic). MR2174870
14. SHAPIRO, I. J. and NARENDRA, K. S. (1969). Use of stochastic automata for parameter selfoptimization with multi-modal perfomance criteria. IEEE Trans. Syst. Sci. Cybern. SSC-5 352-360.
15. TARRÈS, P. (2001). Algorithmes stochastiques et marches aléatoires renforcées. Thèse de l'ENS Cachan (France).