Denumerable-Armed Bandits

DOI10.2307/2951539zbMath0771.90100OpenAlexW2052664405MaRDI QIDQ4016224

Jeffrey S. Banks, Rangarajan K. Sundaram

Publication date: 9 December 1992

Published in: Econometrica (Search for Journal in Brave)

Full work available at URL: https://authors.library.caltech.edu/67326/

zbMATH Keywords

matchingvotingdiscountingGittins indexjob searchdynamic allocationexistence of optimal policiescountably infinite number of armsfinite-armed bandit problemsindependent armsstationary bandits

Mathematics Subject Classification ID

Deterministic scheduling theory in operations research (90B35) Voting theory (91B12) Markov and semi-Markov decision processes (90C40)

Related Items

Optimal learning and experimentation in bandit problems., Optimal learning with costly adjustment, Keeping your options open, Topp-Leone distribution with an application to binomial sampling, Index policies for discounted bandit problems with availability constraints, Jeffrey Scot Banks (1958--2000), Optimal Bayesian strategies for the infinite-armed Bernoulli bandit, The extraction of natural resources from two sites under uncertainty, Branching bandits: A sequential search process with correlated pay-offs., Optimal learning of a set: or how to edit a journal if you must, Electing monetary policymakers according to inflation performance, Learning in society, Endogenous supply of fiat money, The interest sensitivity of wealth in the life cycle model, A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions, Optimal search from multiple distributions with infinite horizon, Stationary multi-choice bandit problems., Two-Armed Restless Bandits with Imperfect Information: Stochastic Control and Indexability, Generalized Bandit Problems, Experimentation, imitation, and stochastic stability, Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm, JOB MATCHING WITHIN AND ACROSS FIRMS