The Continuum-Armed Bandit Problem

DOI10.1137/S0363012992237273MaRDI QIDQ4862444zbMATH OpenFDO

Authors Rajeev Agrawal

Publication date 8 February 1996

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

zbMATH Keywords

adaptive controlmultiarmed bandit problemlearning loss

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Sequential statistical design (62L05) Stochastic learning and adaptive control (93E35)

Recommendations

• Improved Rates for the Stochastic Continuum-Armed Bandit Problem
• On two continuum armed bandit problems in high dimensions
• The Nonstochastic Multiarmed Bandit Problem
• Adaptive-treed bandits
• Continuum armed bandit problem of few variables in high dimensions

Cited in

(36)

• A general theory of multiarmed bandit processes with constrained arm switches
• On two continuum armed bandit problems in high dimensions
• Improved Rates for the Stochastic Continuum-Armed Bandit Problem
• Budgeted multi-armed bandit in continuous action space
• A learning algorithm for the finite-time two-armed bandit problem
• Control-data separation and logical condition propagation for efficient inference on probabilistic programs
• Learning in combinatorial optimization: what and how to explore
• Filtered Poisson process bandit on a continuum
• Further contributions to the two-armed bandit problem
• An asymptotically optimal policy for finite support models in the multiarmed bandit problem
• Continuum armed bandit problem of few variables in high dimensions
• Nonparametric pricing analytics with customer covariates
• Optimal learning for sequential sampling with non-parametric beliefs
• Dynamic learning and decision making via basis weight vectors
• Adaptive-treed bandits
• Optimal learning with a local parametric belief model
• Noise free multi-armed bandit game
• Learning approximately optimal contracts
• A revision game of experimentation on a common threshold
• Contextual bandits with continuous actions: smoothing, zooming, and adapting
• Parameterized aspects of distinct Kemeny rank aggregation
• Treatment recommendation with distributional targets
• Active Learning in Multi-armed Bandits
• scientific article; zbMATH DE number 3967731 (Why is no real title available?)
• scientific article; zbMATH DE number 3918239 (Why is no real title available?)
• Infinite Arms Bandit: Optimality via Confidence Bounds
• Smoothness-Adaptive Contextual Bandits
• Learning approximately optimal contracts
• scientific article; zbMATH DE number 4205609 (Why is no real title available?)
• Bandit problems with infinitely many arms
• Emerging directions in Bayesian computation
• The Nonstochastic Multiarmed Bandit Problem
• The Irrevocable Multiarmed Bandit Problem
• Online linear optimization and adaptive routing
• Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm
• Parameterized aspects of distinct Kemeny rank aggregation

This page was built for publication: The Continuum-Armed Bandit Problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4862444)