Regret and Convergence Bounds for a Class of Continuum-Armed Bandit Problems

DOI10.1109/TAC.2009.2019797zbMath1367.93738MaRDI QIDQ4974598

Eric W. Cope

Publication date: 8 August 2017

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

Mathematics Subject Classification ID

Stochastic learning and adaptive control (93E35) Sequential statistical analysis (62L10)

Related Items (12)

Continuous Assortment Optimization with Logit Choice Probabilities and Incomplete Information ⋮ Adaptive-treed bandits ⋮ Technical note: <scp>Finite‐time</scp> regret analysis of <scp>Kiefer‐Wolfowitz</scp> stochastic approximation algorithm and nonparametric <scp>multi‐product</scp> dynamic pricing with unknown demand ⋮ Coordinating Pricing and Inventory Replenishment with Nonparametric Demand Learning ⋮ A pricing problem with unknown arrival rate and price sensitivity ⋮ Infinite Arms Bandit: Optimality via Confidence Bounds ⋮ Non-Stationary Stochastic Optimization ⋮ A revision game of experimentation on a common threshold ⋮ Dynamic Pricing with Multiple Products and Partially Specified Demand Distribution ⋮ Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm ⋮ Optimal Policy for Dynamic Assortment Planning Under Multinomial Logit Models ⋮ On two continuum armed bandit problems in high dimensions

This page was built for publication: Regret and Convergence Bounds for a Class of Continuum-Armed Bandit Problems