Continuous multi-armed bandits and multiparameter processes

DOI10.1214/aop/1176991992zbMath0657.62098OpenAlexW2061367129MaRDI QIDQ1110966

Avishai Mandelbaum

Publication date: 1987

Published in: The Annals of Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aop/1176991992

zbMATH Keywords

local timesdynamic allocationoptional increasing pathcontinuous time banditcontinuous time dynamic allocation modelsGittins' indexmulti-armed bandit modelstrong solution of diffusion-type bandits

Mathematics Subject Classification ID

Sequential statistical methods (62L99) Optimal stochastic control (93E20) Diffusion processes (60J60) Sample path properties (60G17) Applications of renewal theory (reliability, demand theory, etc.) (60K10) Local time and additive functionals (60J55)

Related Items (20)

Optimal unrestricted dynamic stochastic scheduling with partial losses of work due to breakdowns ⋮ Multi-armed bandit problem revisited ⋮ Bandit and covariate processes, with finite or non-denumerable set of arms ⋮ On Gittins' index theorem in continuous time ⋮ On an Optimal Stopping Problem for Multi-Parameter Diffusion Processes ⋮ The system of quasi-variational inequalities attached to the two-armed bandit problem ⋮ Poissonian two-armed bandit: a new approach ⋮ A general approximation method for optimal stopping and random delay ⋮ Minimizing the time to a decision ⋮ Jordan curves in the level sets of additive Brownian motion ⋮ A generalized Gittins index for a Markov chain and its recursive calculation ⋮ Sensitivity of the gittins index in the contiuous time two-armed bandit problem ⋮ Optimal learning with non-Gaussian rewards ⋮ Two-Armed Restless Bandits with Imperfect Information: Stochastic Control and Indexability ⋮ When to Abandon a Research Project and Search for a New One ⋮ A Method for Computing Double Band Policies for Switching between Two Diffusions ⋮ Unnamed Item ⋮ Multi-armed bandits in discrete and continuous time ⋮ The set-indexed bandit problem. ⋮ A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches

This page was built for publication: Continuous multi-armed bandits and multiparameter processes