ON THE IDENTIFICATION AND MITIGATION OF WEAKNESSES IN THE KNOWLEDGE GRADIENT POLICY FOR MULTI-ARMED BANDITS

DOI10.1017/S0269964816000279zbMath1414.91105arXiv1607.05970OpenAlexW3104196082MaRDI QIDQ5358114

No author found.

Publication date: 19 September 2017

Published in: Probability in the Engineering and Informational Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1607.05970

zbMATH Keywords

stochastic dynamic programming

Mathematics Subject Classification ID

Decision theory (91B06) Stochastic programming (90C15) Dynamic programming (90C39)

Related Items (1)

Optimal Online Learning for Nonlinear Belief Models Using Discrete Priors

Uses Software

• EGO

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic orders
• On the Gittins index for multiarmed bandits
• Efficient global optimization of expensive black-box functions
• Optimal learning and experimentation in bandit problems.
• Bayesian look ahead one-stage sampling allocations for selection of the best population
• Optimal learning with non-Gaussian rewards
• The Knowledge Gradient Algorithm for a General Class of Online Learning Problems
• The Knowledge-Gradient Policy for Correlated Normal Beliefs
• Multi‐Armed Bandit Allocation Indices
• A Knowledge-Gradient Policy for Sequential Information Collection
• Learning to Optimize via Posterior Sampling

This page was built for publication: ON THE IDENTIFICATION AND MITIGATION OF WEAKNESSES IN THE KNOWLEDGE GRADIENT POLICY FOR MULTI-ARMED BANDITS