A Simple Distribution-Free Approach to the Max k-Armed Bandit Problem

DOI10.1007/11889205_40MaRDI QIDQ3524258zbMATH OpenOpenAlexFDO

Authors Matthew J. Streeter, Stephen F. Smith

Publication date 9 September 2008

Published in Principles and Practice of Constraint Programming - CP 2006 (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/11889205_40

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Recommendations

• The multi-armed bandit problem: an efficient nonparametric solution
• A minimax and asymptotically optimal algorithm for stochastic bandits
• The Nonstochastic Multiarmed Bandit Problem
• An asymptotically optimal strategy for constrained multi-armed bandit problems
• A Structured Multiarmed Bandit Problem and the Greedy Policy
• On the k-armed Bernoulli bandit: monotonicity of the total reward under an arbitrary prior distribution
• scientific article; zbMATH DE number 4084786
• Asymptotically optimal multi-armed bandit policies under a cost constraint
• The K-armed bandit problem with multiple priors

Cited in

(6)

• BoostingTree: parallel selection of weak learners in boosting, with application to ranking
• Optimal Learning for Stochastic Optimization with Nonlinear Parametric Belief Models
• Dynamic sample budget allocation in model-based optimization
• Multi-armed bandits with episode context
• Learning dynamic algorithm portfolios
• An analysis of model-based interval estimation for Markov decision processes

This page was built for publication: A Simple Distribution-Free Approach to the Max k-Armed Bandit Problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3524258)