Multi-armed bandits in discrete and continuous time

DOI10.1214/AOAP/1028903380zbMATH Open0940.60063OpenAlexW2129239159MaRDI QIDQ1296724FDOQ1296724

Authors: 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

Recommendations

• Discrete multiarmed bandits and multiparameter processes
• Continuous-time allocation indices and their discrete-time approximation
• Dynamic allocation problems in continuous time
• On the Gittins index for multiarmed bandits
• On Gittins' index theorem in continuous time

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)

Cites Work

• On the Gittins index for multiarmed bandits
• Extensions of the multiarmed bandit problem: The discounted case
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Discrete multiarmed bandits and multiparameter processes
• Title not available (Why is that?)
• Dynamic allocation problems in continuous time
• Applications of Martingale System Theorems
• Title not available (Why is that?)
• Optimal stopping and supermartingales over partially ordered sets
• Title not available (Why is that?)
• Continuous multi-armed bandits and multiparameter processes
• Lévy bandits: Multi-armed bandits driven by Lévy processes
• Title not available (Why is that?)
• General Gittins index processes in discrete time.
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (30)

• Multi-armed bandit processes with optimal selection of the operating times
• Finite-time analysis of the multiarmed bandit problem
• Optimal stopping problems with restricted stopping times
• On Gittins' index theorem in continuous time
• Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems
• Bandit and covariate processes, with finite or non-denumerable set of arms
• Four proofs of Gittins' multiarmed bandit theorem
• An incentive-compatible multi-armed bandit mechanism
• A general approximation method for optimal stopping and random delay
• A Structured Multiarmed Bandit Problem and the Greedy Policy
• Continuous-time allocation indices and their discrete-time approximation
• Multi-armed bandits with episode context
• Two-Armed Bandit Strategies that Discount Past and Future
• Combining multiple strategies for multiarmed bandit problems and asymptotic optimality
• Lévy bandits under Poissonian decision times
• The multi-armed bandit, with constraints
• A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches
• Explicit Gittins Indices for a Class of Superdiffusive Processes
• Title not available (Why is that?)
• Index policy for multiarmed bandit problem with dynamic risk measures
• Multi-armed bandits with censored consumption of resources
• Discrete multiarmed bandits and multiparameter processes
• Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems
• Minimizing the time to a decision
• Title not available (Why is that?)
• The set-indexed bandit problem.
• Multi-armed bandit with sub-exponential rewards
• Multi-armed bandits under general depreciation and commitment
• A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems
• Combinatorial multi-armed bandit and its extension to probabilistically triggered arms

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1296724)