Continuous-time allocation indices and their discrete-time approximation

DOI10.2307/1427185zbMath0606.60072OpenAlexW2316836242MaRDI QIDQ3745006

W. J. R. Eplett

Publication date: 1986

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

Full work available at URL: https://doi.org/10.2307/1427185

zbMATH Keywords

allocationstrong Markov processesoptimal expected rewardsoptimal policy in multi-armed bandit problems

Mathematics Subject Classification ID

Dynamic programming (90C39) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40)

Related Items (3)

Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems ⋮ Sensitivity of the gittins index in the contiuous time two-armed bandit problem ⋮ A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches

This page was built for publication: Continuous-time allocation indices and their discrete-time approximation