Asymptotically efficient rules in multiarmed bandit problems

2006 ◽  
pp. 1-9
Author(s):  
V. Anantharam ◽  
P. Varaiya
Keyword(s):  
Bandit Problems ◽  
Asymptotically Efficient ◽  
Multiarmed Bandit

scholarly journals Corrections to “Satisficing in Multiarmed Bandit Problems”

2021 ◽  
Vol 66 (1) ◽  
pp. 476-478
Author(s):  
Paul Reverdy ◽  
Vaibhav Srivastava ◽  
Naomi Ehrich Leonard
Keyword(s):  
Bandit Problems ◽  
Multiarmed Bandit

scholarly journals Index policies for discounted bandit problems with availability constraints

2008 ◽  
Vol 40 (02) ◽  
pp. 377-400 ◽  
Author(s):  
Savas Dayanik ◽  
Warren Powell ◽  
Kazutoshi Yamazaki
Keyword(s):  
Bandit Problem ◽  
Bandit Problems ◽  
Index Policy ◽  
State Action ◽  
Index Policies ◽  
Availability Constraints ◽  
Whittle Index ◽  
Multiarmed Bandit

A multiarmed bandit problem is studied when the arms are not always available. The arms are first assumed to be intermittently available with some state/action-dependent probabilities. It is proven that no index policy can attain the maximum expected total discounted reward in every instance of that problem. The Whittle index policy is derived, and its properties are studied. Then it is assumed that the arms may break down, but repair is an option at some cost, and the new Whittle index policy is derived. Both problems are indexable. The proposed index policies cannot be dominated by any other index policy over all multiarmed bandit problems considered here. Whittle indices are evaluated for Bernoulli arms with unknown success probabilities.

scholarly journals Index policies for discounted bandit problems with availability constraints

2008 ◽  
Vol 40 (2) ◽  
pp. 377-400 ◽  
Author(s):  
Savas Dayanik ◽  
Warren Powell ◽  
Kazutoshi Yamazaki
Keyword(s):  
Bandit Problem ◽  
Bandit Problems ◽  
Index Policy ◽  
State Action ◽  
Index Policies ◽  
Availability Constraints ◽  
Whittle Index ◽  
Multiarmed Bandit

A multiarmed bandit problem is studied when the arms are not always available. The arms are first assumed to be intermittently available with some state/action-dependent probabilities. It is proven that no index policy can attain the maximum expected total discounted reward in every instance of that problem. The Whittle index policy is derived, and its properties are studied. Then it is assumed that the arms may break down, but repair is an option at some cost, and the new Whittle index policy is derived. Both problems are indexable. The proposed index policies cannot be dominated by any other index policy over all multiarmed bandit problems considered here. Whittle indices are evaluated for Bernoulli arms with unknown success probabilities.

Robust Multiarmed Bandit Problems

2015 ◽  
pp. 150805104205004 ◽  
Author(s):  
Michael Jong Kim ◽  
Andrew E.B. Lim
Keyword(s):  
Bandit Problems ◽  
Multiarmed Bandit
Sign in / Sign up

Export Citation Format

Share Document