Bandit problems with side observations

DOI10.1109/TAC.2005.844079MaRDI QIDQ5274013zbMATH OpenOpenAlexFDO

Authors Chih-Chun Wang, Sanjeev R. Kulkarni, H. Vincent Poor

Publication date 12 July 2017

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cs/0501063

Mathematics Subject Classification ID

General considerations in statistical decision theory (62C05) Bayesian problems; characterization of Bayes procedures (62C10) Decision theory (91B06)

Abstract: An extension of the traditional two-armed bandit problem is considered, in which the decision maker has access to some side information before deciding which arm to pull. At each time t, before making a selection, the decision maker is able to observe a random variable X_t that provides some information on the rewards to be obtained. The focus is on finding uniformly good rules (that minimize the growth rate of the inferior sampling time) and on quantifying how much the additional information helps. Various settings are considered and for each setting, lower bounds on the achievable inferior sampling time are developed and asymptotically optimal adaptive schemes achieving these lower bounds are constructed.

Cited in

(13)

• Multiclass classification with bandit feedback using adaptive regularization
• Bandit and covariate processes, with finite or non-denumerable set of arms
• Arbitrary side observations in bandit problems
• Bayesian Incentive-Compatible Bandit Exploration
• Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback
• Bounded Regret for Finitely Parameterized Multi-Armed Bandits
• Smoothness-Adaptive Contextual Bandits
• Smooth Contextual Bandits: Bridging the Parametric and Nondifferentiable Regret Regimes
• MULTI-ARMED BANDITS WITH COVARIATES:THEORY AND APPLICATIONS
• Infinite Arms Bandit: Optimality via Confidence Bounds
• A Note on Performance Limitations in Bandit Problems With Side Information
• Dealing with expert bias in collective decision-making
• A non-parametric solution to the multi-armed bandit problem with covariates

This page was built for publication: Bandit problems with side observations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5274013)