Exploration and exploitation of scratch games

DOI10.1007/S10994-013-5359-2MaRDI QIDQ374139zbMATH OpenOpenAlexFDO

Authors Raphaël Féraud, Tanguy Urvoy

Publication date 22 October 2013

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-013-5359-2

zbMATH Keywords

adversarial multi-armed banditsfinite sequencesscratch gamesstochastic multi-armed bandits

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Inequalities; stochastic orderings (60E15) Applications of game theory (91A80) Stochastic games, stochastic differential games (91A15) Probabilistic games; gambling (91A60)

Recommendations

• The Nonstochastic Multiarmed Bandit Problem
• Mechanisms with learning for stochastic multi-armed bandit problems
• Algorithms for adversarial bandit problems with multiple plays
• Bandits with knapsacks
• Pure exploration in multi-armed bandits problems

Cites work

• Asymptotically efficient adaptive allocation rules
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Finite-time analysis of the multiarmed bandit problem
• Prediction, Learning, and Games
• Probability inequalities for the sum in sampling without replacement
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• The Nonstochastic Multiarmed Bandit Problem

Cited in

(1)

• Concentration inequalities for sampling without replacement

This page was built for publication: Exploration and exploitation of scratch games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q374139)