Improved Rates for the Stochastic Continuum-Armed Bandit Problem

DOI10.1007/978-3-540-72927-3_33zbMath1203.68134OpenAlexW1521084402MaRDI QIDQ5434068

Peter Auer, Csaba Szepesvári, Ronald Ortner

Publication date: 3 January 2008

Published in: Learning Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-540-72927-3_33

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic learning and adaptive control (93E35) Probabilistic games; gambling (91A60)

Related Items (18)

Smoothness-Adaptive Contextual Bandits ⋮ Continuous Assortment Optimization with Logit Choice Probabilities and Incomplete Information ⋮ Adaptive-treed bandits ⋮ Learning approximately optimal contracts ⋮ Learning approximately optimal contracts ⋮ Nonparametric learning for impulse control problems -- exploration vs. exploitation ⋮ Estimation and inference for minimizer and minimum of convex functions: optimality, adaptivity and uncertainty principles ⋮ Online Regret Bounds for Markov Decision Processes with Deterministic Transitions ⋮ Coordinating Pricing and Inventory Replenishment with Nonparametric Demand Learning ⋮ Online regret bounds for Markov decision processes with deterministic transitions ⋮ Infinite Arms Bandit: Optimality via Confidence Bounds ⋮ Randomized allocation with arm elimination in a bandit problem with covariates ⋮ On Incomplete Learning and Certainty-Equivalence Control ⋮ Dynamic Pricing with Multiple Products and Partially Specified Demand Distribution ⋮ Nonparametric Pricing Analytics with Customer Covariates ⋮ Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm ⋮ A Primal–Dual Learning Algorithm for Personalized Dynamic Pricing with an Inventory Constraint ⋮ On two continuum armed bandit problems in high dimensions

This page was built for publication: Improved Rates for the Stochastic Continuum-Armed Bandit Problem