Lévy bandits: Multi-armed bandits driven by Lévy processes
From MaRDI portal
Publication:1901088
DOI10.1214/aoap/1177004777zbMath0830.60065OpenAlexW2044825177MaRDI QIDQ1901088
Haya Kaspi, Avishai Mandelbaum
Publication date: 15 January 1996
Published in: The Annals of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1214/aoap/1177004777
excursionsLévy processeslocal timeWiener-Hopf factorizationmultiparameter processesoptional increasing pathmultiarmed bandits
Stopping times; optimal stopping problems; gambling theory (60G40) Local time and additive functionals (60J55) Markov processes (60J99)
Related Items (8)
On Gittins' index theorem in continuous time ⋮ Common value experimentation ⋮ Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems ⋮ Consumer strategy, vendor strategy and equilibrium in duopoly markets with production costs ⋮ A common value experimentation with multiarmed bandits ⋮ Minimizing the time to a decision ⋮ Optimal learning with non-Gaussian rewards ⋮ Multi-armed bandits in discrete and continuous time
This page was built for publication: Lévy bandits: Multi-armed bandits driven by Lévy processes
