Stoppable families of alternative bandit processes

DOI10.2307/3213150zbMath0434.90100OpenAlexW2086464902MaRDI QIDQ3873957

Kevin D. Glazebrook

Publication date: 1979

Published in: Journal of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2307/3213150

zbMATH Keywords

Markov decision processessufficient optimality conditionsoptimal policiessequential design of experimentsinfinite number of stagesmultiarmed bandit problemsdynamic allocation indexresearch planningalternative research projectsisotonic stopping rulesstoppable families of alternative bandit processes

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Operations research and management science (90B99) Sequential estimation (62L12) Optimal stopping in statistics (62L15)

Related Items (6)

The performance of forwards induction policies ⋮ Competing Markov decision processes ⋮ Optimal learning before choice ⋮ Whether or not to open Pandora's box ⋮ Learning while searching for the best alternative ⋮ Optimal stopping problems for multiarmed bandit processes with arms' independence

This page was built for publication: Stoppable families of alternative bandit processes