One-armed bandit models with continuous and delayed responses (Q1416785)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | One-armed bandit models with continuous and delayed responses |
scientific article |
Statements
One-armed bandit models with continuous and delayed responses (English)
0 references
16 December 2003
0 references
One-armed bandit processes with continuous delayed responses are considered as controlled stochastic processes. A Gittins-like index is shown to exist, and the existence of an optimal stopping rule is derived for the case of complete observation.
0 references
bandit processes
0 references
delayed responses
0 references
Gittins index
0 references
Markov decision processes
0 references
optimal stopping
0 references