When can the two-armed bandit algorithm be trusted?

DOI10.1214/105051604000000350zbMath1048.62079arXivmath/0407128OpenAlexW4297424836MaRDI QIDQ1879915

Damien Lamberton, Pierre Tarrès, Gilles Pagès

Publication date: 15 September 2004

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0407128

zbMATH Keywords

asset allocationPolya urnlearning auomata

Mathematics Subject Classification ID

Adaptive control/observation systems (93C40) Strong limit theorems (60F15) Stochastic approximation (62L20) Stopping times; optimal stopping problems; gambling theory (60G40) Sequential statistical design (62L05)

Related Items (12)

On the robustness of learning in games with stochastically perturbed payoff observations ⋮ Stochastic approximation of quasi-stationary distributions on compact spaces and applications ⋮ Penalty-Regulated Dynamics and Robust Learning Procedures in Games ⋮ Randomized urn models revisited using stochastic approximation ⋮ Regret bounds for Narendra-Shapiro bandit algorithms ⋮ Robustness of stochastic bandit policies ⋮ Analysis of the smoothly amnesia-reinforced multidimensional elephant random walk ⋮ How Fast Is the Bandit? ⋮ On ergodic two-armed bandits ⋮ Convergence in models with bounded expected relative hazard rates ⋮ Nonlinear randomized urn models: a stochastic approximation viewpoint ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonconvergence to unstable points in urn models and stochastic approximations
• Stochastic approximation methods for constrained and unconstrained systems
• Stochastic algorithms
• Asymptotic pseudotrajectories and chain recurrent flows, with applications
• Do stochastic algorithms avoid traps?
• On the linear model with two absorbing barriers
• Learning Automata - A Survey
• Decreasing step Stochastic algorithms: a.s. behaviour of weighted empirical measures
• Pièges répulsifs
• Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria

This page was built for publication: When can the two-armed bandit algorithm be trusted?