On Ergodic Two-armed Bandits

  title={On Ergodic Two-armed Bandits},
  author={Pierre Tarres and Pierre Vandekerkhove},
A device has two arms with unknown deterministic payoffs, and the aim is to asymptotically identify the best one without spending too much time on the other. The Narendra algorithm offers a stochastic procedure to this end. We show under weak ergodic assumptions on these deterministic payoffs that the procedure eventually chooses the best arm (i.e. with greatest Cesaro limit) with probability one, for appropriate step sequences of the algorithm. In the case of i.i.d. payoffs, this implies a… CONTINUE READING

From This Paper

Topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 16 references

The law of the iterated logarithm for additive functionals of Markov chains

  • Y. Miao, G. Yang
  • Statist. Prob. Letters
  • 2008
Highly Influential
4 Excerpts

A Two Armed Type Bandit Problem

  • M. Benäım, G. Ben Arous
  • International Journal of Game Theory,
  • 2003
Highly Influential
7 Excerpts

On linear Models with Two Absorbing Barriers

  • M. F. Norman
  • J. of Mathematical Psychlogy,
  • 1968
Highly Influential
15 Excerpts

A two-armed bandit problem revisited

  • G. Pagès
  • 2005
Highly Influential
13 Excerpts

Algorithmes stochastiques et marches aléatoires renforcées, Thèse de l’ENS Cachan (France), novembre

  • P. Tarrès
  • 2001
Highly Influential
8 Excerpts

Algorithme de Narendra et application à l’allocation d’actifs

  • M. Niang
  • Rapport de stage de DEA, Olympia Capital…
  • 1999
Highly Influential
3 Excerpts

How fast is the two armed-bandit algorithm

  • D. Lamberton, G. Pagès
  • Stoch. Anal. Appl
  • 2008
2 Excerpts

Similar Papers

Loading similar papers…