Multi-armed bandits in discrete and continuous time

DOI10.1214/aoap/1028903380zbMath0940.60063OpenAlexW2129239159MaRDI QIDQ1296724

Haya Kaspi, Avishai Mandelbaum

Publication date: 19 July 2000

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

Full work available at URL: https://doi.org/10.1214/aoap/1028903380

zbMATH Keywords

local timemulti-armed banditsexcursionmultiparameter processdual predictable projectionoptimal increasing paths

Mathematics Subject Classification ID

Stopping times; optimal stopping problems; gambling theory (60G40) Martingales with continuous parameter (60G44) Local time and additive functionals (60J55)

Related Items (16)

Optimal stopping problems with restricted stopping times ⋮ Bandit and covariate processes, with finite or non-denumerable set of arms ⋮ On Gittins' index theorem in continuous time ⋮ Four proofs of Gittins' multiarmed bandit theorem ⋮ The multi-armed bandit, with constraints ⋮ Index policy for multiarmed bandit problem with dynamic risk measures ⋮ MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT ⋮ Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems ⋮ A general approximation method for optimal stopping and random delay ⋮ Minimizing the time to a decision ⋮ A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems ⋮ Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems ⋮ Explicit Gittins Indices for a Class of Superdiffusive Processes ⋮ Unnamed Item ⋮ The set-indexed bandit problem. ⋮ A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Continuous multi-armed bandits and multiparameter processes
• On the Gittins index for multiarmed bandits
• Discrete multiarmed bandits and multiparameter processes
• Dynamic allocation problems in continuous time
• Lévy bandits: Multi-armed bandits driven by Lévy processes
• Extensions of the multiarmed bandit problem: The discounted case
• Optimal stopping and supermartingales over partially ordered sets
• General Gittins index processes in discrete time.
• Applications of Martingale System Theorems

This page was built for publication: Multi-armed bandits in discrete and continuous time