Solving two-armed Bernoulli bandit problems using a Bayesian learning automaton

DOI10.1108/17563781011049179MaRDI QIDQ4932958zbMATH OpenOpenAlexFDO

Authors Ole-Christoffer Granmo

Publication date 7 October 2010

Published in International Journal of Intelligent Computing and Cybernetics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1108/17563781011049179

zbMATH Keywords

automata theorylearning processesprogramming and algorithm theorystochastic processes

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87)

Recommendations

• On the value of learning for Bernoulli bandits with unknown parameters
• scientific article; zbMATH DE number 4059270
• A learning algorithm for the finite-time two-armed bandit problem
• Optimal Bayesian strategies for the infinite-armed Bernoulli bandit
• Small-sample performance of Bernoulli two-armed bandit Bayesian strategies

Cites work

• Discretized pursuit learning automata
• Finite-time analysis of the multiarmed bandit problem
• On the value of learning for Bernoulli bandits with unknown parameters

Cited in

(5)

• Thompson sampling guided stochastic searching on the line for deceptive environments with applications to root-finding problems
• Multi-armed bandit for species discovery: a Bayesian nonparametric approach
• Multi-armed bandit problem with online clustering as side information
• Optimal strategy for Bayesian two-armed bandit problem with an arched reward function
• Information-directed sampling for bandits: a primer

This page was built for publication: Solving two-armed Bernoulli bandit problems using a Bayesian learning automaton

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4932958)