Multi-armed bandits with discount factor near one: The Bernoulli case
From MaRDI portal
Publication:1161450
DOI10.1214/aos/1176345578zbMath0478.90073MaRDI QIDQ1161450
Publication date: 1981
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1214/aos/1176345578
Gittins index; asymptotic bounds; multi-armed bandit; discount optimality; Bernoulli bandit process; expected average reward optimality; infinite sequence of Bernoulli random variables; least failures rule; limit rule; optimal arm pulling strategy; play-the-winner rule
90C40: Markov and semi-Markov decision processes
62L05: Sequential statistical design
62L15: Optimal stopping in statistics
Related Items
An asymptotically optimal heuristic for general nonstationary finite-horizon restless multi-armed, multi-action bandits, Dynamic priority allocation via restless bandit marginal productivity indices, On optimal search with unknown detection probabilities, Gittins' theorem under uncertainty, Finite state multi-armed bandit problems: Sensitive-discount, average-reward and average-overtaking optimality, Sequential allocation in clinical trials, Branching Bandit Processes