Robust normal two-armed bandit and parallel data processing

MaRDI QIDQ2948357zbMATH OpenFDO

Authors Alex V. Kolnogorov

Publication date 30 September 2015

zbMATH Keywords

control in random environmentminimax and Bayesian approachesparallel processingstochastic robust controltwo-armed bandit problem

Mathematics Subject Classification ID

Large-scale systems (93A15) Sensitivity (robustness) (93B35)

Recommendations

• One-armed bandit problem for parallel data processing systems
• Two-armed bandit problem for parallel data processing systems
• Gaussian two-armed bandit and optimization of batch data processing
• Parallel design of robust control in the stochastic environment (the two-armed bandit problem)
• Finding minimax strategy and minimax risk in a random environment (the two-armed bandit problem)

Cited in

(9)

• Two-armed bandit problem and batch version of the mirror descent algorithm
• Gaussian two-armed bandit and optimization of batch data processing
• Gaussian two-armed bandit: limiting description
• Parallel design of robust control in the stochastic environment (the two-armed bandit problem)
• One-armed bandit problem for parallel data processing systems
• Customization of J. Bather's UCB strategy for a Gaussian multiarmed bandit
• Two-armed bandit problem for parallel data processing systems
• Finding minimax strategy and minimax risk in a random environment (the two-armed bandit problem)
• Robust parallel control in a random environment and data processing optimization

This page was built for publication: Robust normal two-armed bandit and parallel data processing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2948357)