- Tytuł:
- On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms
- Autorzy:
- Drabik, Ewa
- Powiązania:
- https://bibliotekanauki.pl/articles/1340247.pdf
- Data publikacji:
- 1996
- Wydawca:
- Polska Akademia Nauk. Instytut Matematyczny PAN
- Tematy:
-
selfoptimizing strategies
adaptative control
invariant measure
multiarmed bandit
stochastic control - Opis:
- Two kinds of strategies for a multiarmed Markov bandit problem with controlled arms are considered: a strategy with forcing and a strategy with randomization. The choice of arm and control function in both cases is based on the current value of the average cost per unit time functional. Some simulation results are also presented.
- Źródło:
-
Applicationes Mathematicae; 1995-1996, 23, 4; 449-473
1233-7234 - Pojawia się w:
- Applicationes Mathematicae
- Dostawca treści:
- Biblioteka Nauki
Artykuł