The Multi-Armed Bandit Problem: Decomposition and Computation

DOI10.1287/MOOR.12.2.262zbMATH Open0618.90097DBLPjournals/mor/KatehakisV87OpenAlexW2118309135WikidataQ29306812 ScholiaQ29306812MaRDI QIDQ3755256FDOQ3755256

Arthur F. jun. Veinott, Michael N. Katehakis

Publication date: 1987

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/e4fe28113fed71999a0db30a930e0b42d3ce55f1

Recommendations

• On the Gittins index for multiarmed bandits
• scientific article; zbMATH DE number 194374
• scientific article
• Extensions of the multiarmed bandit problem: The discounted case
• Computing a classic index for finite-horizon bandits

zbMATH Keywords

multi-armed bandit problemapproximately optimal policyapproximate largest-index rulelargest-index rulesparse transition matrices

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Cited In (67)

• Title not available (Why is that?)
• The performance of forwards induction policies
• Finite state multi-armed bandit problems: Sensitive-discount, average-reward and average-overtaking optimality
• Incentivizing Exploration with Heterogeneous Value of Money
• Finite-time analysis of the multiarmed bandit problem
• Optimal learning with non-Gaussian rewards
• A tutorial on Gaussian process regression: modelling, exploring, and exploiting functions
• ASYMPTOTICALLY OPTIMAL MULTI-ARMED BANDIT POLICIES UNDER A COST CONSTRAINT
• Optimal stopping of Markov chains and three abstract optimization problems
• Title not available (Why is that?)
• On the solution of stochastic optimization and variational problems in imperfect information regimes
• The learning component of dynamic allocation indices
• Tax problems in the undiscounted case
• Branching Bandit Processes
• Four proofs of Gittins' multiarmed bandit theorem
• City streets parking enforcement inspection decisions: the Chinese postman's perspective
• On the optimal allocation of service to impatient tasks
• The \(K\)-armed dueling bandits problem
• Optimal Online Learning for Nonlinear Belief Models Using Discrete Priors
• Dynamic allocation policies for the finite horizon one armed bandit problem
• Robust control of the multi-armed bandit problem
• Index policies for discounted bandit problems with availability constraints
• An asymptotically optimal policy for finite support models in the multiarmed bandit problem
• Denumerable-Armed Bandits
• Title not available (Why is that?)
• A Structured Multiarmed Bandit Problem and the Greedy Policy
• An Approximation Approach for Response-Adaptive Clinical Trial Design
• Title not available (Why is that?)
• Ameso optimization: a relaxation of discrete midpoint convexity
• Response-adaptive designs for clinical trials: simultaneous learning from multiple patients
• A perpetual search for talents across overlapping generations: a learning process
• An optimal stopping policy for car rental businesses with purchasing customers
• Continue, quit, restart probability model
• Perspectives of approximate dynamic programming
• Resource capacity allocation to stochastic dynamic competitors: knapsack problem for perishable items and index-knapsack heuristic
• On Solving Finite State Multi-Armed Bandit Problem by Linear Programming
• Derman's book as inspiration: some results on LP for MDPs
• The multi-armed bandit, with constraints
• Optimal control of single-server queueing networks
• MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT
• A Note on M. N. Katehakis' and Y.-R. Chen's Computation of the Gittins Index
• Enhancing gene expression programming based on space partition and jump for symbolic regression
• Consumer strategy, vendor strategy and equilibrium in duopoly markets with production costs
• Polynomial-Time Algorithms for Multiple-Arm Identification with Full-Bandit Feedback
• A generalized Gittins index for a Markov chain and its recursive calculation
• DES AND RES PROCESSES AND THEIR EXPLICIT SOLUTIONS
• Stochastic scheduling: a short history of index policies and new approaches to index generation for dynamic resource allocation
• Extensions of the multiarmed bandit problem: The discounted case
• On the resolution of misspecified convex optimization and monotone variational inequality problems
• Survey of linear programming for standard and nonstandard Markovian control problems. Part II: Applications
• Discounted Multiarmed Bandit Problems on a Collection of Machines with Varying Speeds
• Stochastic scheduling and forwards induction
• Competing Markov decision processes
• A bisection/successive approximation method for computing Gittins indices
• Adaptive approaches to stochastic programming
• The Nonstochastic Multiarmed Bandit Problem
• The Irrevocable Multiarmed Bandit Problem
• The efficacy of league formats in ranking teams
• A common value experimentation with multiarmed bandits
• Combinatorial multi-armed bandit and its extension to probabilistically triggered arms
• Optimal and Efficient Auctions for the Gradual Procurement of Strategic Service Provider Agents
• A Verification Theorem for Threshold-Indexability of Real-State Discounted Restless Bandits
• Optimal activation of halting multi‐armed bandit models
• A stochastic differential equation driven by Poisson random measure and its application in a duopoly market
• Index policy for multiarmed bandit problem with dynamic risk measures
• Optimistic Gittins Indices
• Testing indexability and computing Whittle and Gittins index in subcubic time

This page was built for publication: The Multi-Armed Bandit Problem: Decomposition and Computation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3755256)