Machine learning and nonparametric bandit theory

DOI10.1109/9.400491zbMath0883.62090OpenAlexW2143552356MaRDI QIDQ4850249

Sidney Yakowitz, Tze Leung Lai

Publication date: 9 October 1995

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

Full work available at URL: https://semanticscholar.org/paper/fe611ab14edf4c19fa90e03da42589b0e9c5d5ec

zbMATH Keywords

controlled Markov processesrisk growth

Mathematics Subject Classification ID

Stochastic learning and adaptive control (93E35) Optimal stopping in statistics (62L15) Nonparametric inference (62G99)

Related Items (10)

Bandit and covariate processes, with finite or non-denumerable set of arms ⋮ A linear response bandit problem ⋮ MULTI-ARMED BANDITS WITH COVARIATES:THEORY AND APPLICATIONS ⋮ Tuning Bandit Algorithms in Stochastic Environments ⋮ Arbitrary side observations in bandit problems ⋮ Active learning in heteroscedastic noise ⋮ Convergence of least squares learning in self-referential discontinuous stochastic models. ⋮ Exploration-exploitation tradeoff using variance estimates in multi-armed bandits ⋮ Randomized allocation with nonparametric estimation for a multi-armed bandit problem with covariates ⋮ Sequential design with applications to the trim-loss problem

This page was built for publication: Machine learning and nonparametric bandit theory