Explore first, exploit next : the true shape of regret in bandit problems
Year of publication: |
2019
|
---|---|
Authors: | Garivier, Aurélien ; Ménard, Pierre ; Stoltz, Gilles |
Published in: |
Mathematics of operations research. - Catonsville, MD : INFORMS, ISSN 0364-765X, ZDB-ID 195683-8. - Vol. 44.2019, 2, p. 377-399
|
Subject: | multiarmed bandits | cumulative regret | information-theoretic proof techniques | nonasymptotic lower bounds | Theorie | Theory | Entscheidung unter Unsicherheit | Decision under uncertainty | Entscheidung | Decision |
-
Bayesian incentive-compatible bandit exploration
Mansour, Yishay, (2020)
-
Does personalized information improve health plan choices when individuals are distracted?
Kaumann, Cornel, (2018)
-
Optimal screening for hepatocellular carcinoma : a restless bandit model
Lee, Elliot, (2019)
- More ...
-
Joint Estimation of Intersecting Context Tree Models
GALVES, ANTONIO, (2013)
-
Ménard, Pierre, (1994)
-
Trente ans de traduction poétique en France
Ménard, Pierre, (1994)
- More ...