Results 11 to 20 of about 12,386 (222)
CoRR, 2018 We introduce the factored bandits model, which is a framework for learning with limited (bandit) feedback, where actions can be decomposed into a Cartesian product of atomic actions. Factored bandits incorporate rank-1 bandits as a special case, but significantly relax the assumptions on the form of the reward function.
Zimmert, Julian Ulf, Seldin, Yevgeny
core +5 more sources
2020 59th IEEE Conference on Decision and Control (CDC), 2020 10 pages, 4 figures ...
Simon Lindståhl +2 more
openaire +4 more sources
Beyond the brotherhood: Skoal Bandits’ role in the evolution of marketing moist smokeless tobacco pouches [PDF]
Tobacco Induced Diseases, 2017 Background Since 2006, “snus” smokeless tobacco has been sold in the U.S.. However, U.S. Smokeless Tobacco (USST) and Swedish Match developed and marketed pouched moist snuff tobacco (MST) since 1973.
Yogi H. Hendlin +3 more
doaj +2 more sources
A generalised gittins index for a class of multi-armed bandits with general resource requirements [PDF]
, 2009 We generalise classical multiarmed bandits to allow for the distribution of a (fixed amount of a) divisible resource among the constituent bandits at each decision point.
Minty, R J, Glazebrook, K D
core +5 more sources
Quantum Machine Intelligence, 2020 We consider the quantum version of the bandit problem known as {\em best arm identification} (BAI). We first propose a quantum modeling of the BAI problem, which assumes that both the learning agent and the environment are quantum; we then propose an algorithm based on quantum amplitude amplification to solve BAI.
Giuseppe, Di Molfetta +4 more
openaire +4 more sources
CoRR, 2022 In many online decision processes, the optimizing agent is called to choose between large numbers of alternatives with many inherent similarities; in turn, these similarities imply closely correlated losses that may confound standard discrete choice models and bandit algorithms.
Martin, Matthieu +3 more
openaire +4 more sources
Journal of Computer and System Sciences, 2012 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
N. Cesa-Bianchi, G. Lugosi
openaire +3 more sources
Quantitative Economics, 2021 We experimentally implement a dynamic public‐good problem, where the public good in question is the dynamically evolving information about agents' common state of the world. Subjects' behavior is consistent with free‐riding because of strategic concerns.
Hoelzemann, Johannes, Klein, Nicolas
openaire +3 more sources
2013 IEEE 54th Annual Symposium on Foundations of Computer Science, 2013 Multi-armed bandit problems are the predominant theoretical model of exploration-exploitation tradeoffs in learning, and they have countless applications ranging from medical trials, to communication networks, to Web search and advertising.
Ashwinkumar Badanidiyuru +2 more
openaire +4 more sources