Denumerable-Armed Bandits
From MaRDI portal
Publication:4016224
DOI10.2307/2951539zbMath0771.90100MaRDI 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/
matching; voting; discounting; Gittins index; job search; dynamic allocation; existence of optimal policies; countably infinite number of arms; finite-armed bandit problems; independent arms; stationary bandits
90B35: Deterministic scheduling theory in operations research
91B12: Voting theory
90C40: Markov and semi-Markov decision processes
Related Items
Two-Armed Restless Bandits with Imperfect Information: Stochastic Control and Indexability, JOB MATCHING WITHIN AND ACROSS FIRMS, Generalized Bandit Problems, Electing monetary policymakers according to inflation performance, The interest sensitivity of wealth in the life cycle model, Stationary multi-choice bandit problems., Learning in society, Optimal Bayesian strategies for the infinite-armed Bernoulli bandit, Endogenous supply of fiat money, Experimentation, imitation, and stochastic stability, Jeffrey Scot Banks (1958--2000), Branching bandits: A sequential search process with correlated pay-offs., Optimal learning and experimentation in bandit problems., Keeping your options open, A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions, Optimal search from multiple distributions with infinite horizon, Optimal learning with costly adjustment, Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm, The extraction of natural resources from two sites under uncertainty, Optimal learning of a set: or how to edit a journal if you must, Index policies for discounted bandit problems with availability constraints