Finding minimax strategy and minimax risk in a random environment (the two-armed bandit problem)

DOI10.1134/S0005117911050092zbMATH Open1235.93268MaRDI QIDQ664264FDOQ664264

Authors: Alex V. Kolnogorov 

Publication date: 1 March 2012

Published in: Automation and Remote Control (Search for Journal in Brave)

Recommendations

• Finding minimax strategy and minimax risk for Bernoulli multi-armed bandit
• Publication:3479957
• Robust normal two-armed bandit and parallel data processing
• Parallel design of robust control in the stochastic environment (the two-armed bandit problem)
• Minimax and bates strategies for the discounted infinite horizon one-armed-bandit.—explicit formulae and structural properties

Mathematics Subject Classification ID

Stochastic learning and adaptive control (93E35)

Cites Work

• Some aspects of the sequential design of experiments
• Title not available (Why is that?)
• An Asymptotic Minimax Theorem for the Two Armed Bandit Problem
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Some Remarks on the Two-Armed Bandit

Cited In (10)

• One-armed bandit problem for parallel data processing systems
• Improving the RHC-strategy
• Robust normal two-armed bandit and parallel data processing
• Finding minimax strategy and minimax risk for Bernoulli multi-armed bandit
• Parallel design of robust control in the stochastic environment (the two-armed bandit problem)
• Poissonian two-armed bandit: a new approach
• Title not available (Why is that?)
• Minimax and bates strategies for the discounted infinite horizon one-armed-bandit.—explicit formulae and structural properties
• Title not available (Why is that?)
• Gaussian two-armed bandit and optimization of batch data processing

This page was built for publication: Finding minimax strategy and minimax risk in a random environment (the two-armed bandit problem)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q664264)