Generalized Bandit Problems

DOI10.1007/3-540-27295-X_6zbMATH Open1255.91076OpenAlexW9937762MaRDI QIDQ5486926FDOQ5486926

Authors: Rangarajan K. Sundaram 

Publication date: 18 September 2006

Published in: Social Choice and Strategic Decisions (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/3-540-27295-x_6

Recommendations

• Denumerable-Armed Bandits
• Extensions of the multiarmed bandit problem: The discounted case
• Switching Costs and the Gittins Index
• Evaluating strategies for generalized bandit problems
• Stationary multi-choice bandit problems.

Mathematics Subject Classification ID

Decision theory (91B06) Dynamic programming (90C39)

Cites Work

• Asymptotically efficient adaptive allocation rules
• Arm-acquiring bandits
• Title not available (Why is that?)
• Title not available (Why is that?)
• Discounted Dynamic Programming
• Title not available (Why is that?)
• Optimal learning with costly adjustment
• Title not available (Why is that?)
• Title not available (Why is that?)
• Optimal Search for the Best Alternative
• Bayesian dynamic programming
• Denumerable-Armed Bandits
• On dynamic programming and statistical decision theory
• Asymptotically efficient adaptive allocation rules for the multiarmed bandit problem with switching cost
• Switching Costs and the Gittins Index
• Contributions to the "Two-Armed Bandit" Problem
• The Sequential Design of Bernoulli Experiments Including Switching Costs
• A class of bandit problems yielding myopic optimal strategies

Cited In (31)

• A general theory of multiarmed bandit processes with constrained arm switches
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multi-armed bandits with simple arms
• Stationary multi-choice bandit problems.
• Title not available (Why is that?)
• Batched bandit problems
• Arbitrary side observations in bandit problems
• Branching Bandit Processes
• Switching Costs and the Gittins Index
• A faster index algorithm and a computational study for bandits with switching costs
• Denumerable-Armed Bandits
• Evaluating strategies for generalized bandit problems
• Gaussian process modelling of dependencies in multi-armed bandit problems
• Evaluating policies for generalized bandits via a notion of duality
• Bandits and Experts in Metric Spaces
• A perpetual search for talents across overlapping generations: a learning process
• The multi-armed bandit, with constraints
• The K-armed bandit problem with multiple priors
• Best arm identification in generalized linear bandits
• Branching bandits: A sequential search process with correlated pay-offs.
• Extensions of the multiarmed bandit problem: The discounted case
• Discounted Multiarmed Bandit Problems on a Collection of Machines with Varying Speeds
• Generalized two-stage bandit problem
• A class of bandit problems yielding myopic optimal strategies
• The set-indexed bandit problem.
• Multi-armed bandits under general depreciation and commitment
• Optimal learning and experimentation in bandit problems.
• Title not available (Why is that?)
• Lévy bandits: Multi-armed bandits driven by Lévy processes
• Generalized Restless Bandits and the Knapsack Problem for Perishable Inventories

This page was built for publication: Generalized Bandit Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5486926)