When can the two-armed bandit algorithm be trusted?

Abstract

We investigate the asymptotic behavior of one version of the so-called two-armed bandit algorithm. It is an example of stochastic approximation procedure whose associated ODE has both a repulsive and an attractive equilibrium, at which the procedure is noiseless. We show that if the gain parameter is constant or goes to 0 not too fast, the algorithm does fall in the noiseless repulsive equilibrium with positive probability, whereas it always converges to its natural attractive target when the gain parameter goes to zero at some appropriate rates depending on the parameters of the model. We also elucidate the behavior of the constant step algorithm when the step goes to 0. Finally, we highlight the connection between the algorithm and the Polya urn. An application to asset allocation is briefly described.

Cited by in corpus (7)

• Unlearnable Games and "Satisficing'' Decisions: A Simple Model for a Complex World
• On ergodic two-armed bandits
• Computation of VaR and CVaR using stochastic approximations and unconstrained importance sampling
• Periodic Pólya urns and an application to Young tableaux
• Networks of reinforced stochastic processes: probability of asymptotic polarization and related general results
• Penalty-regulated dynamics and robust learning procedures in games
• Convergence in Models with Bounded Expected Relative Hazard Rates