Finite-time Analysis of the Multiarmed Bandit Problem

Peter Auer; Nicolò Cesa‐Bianchi; Paul Fischer

doi:10.1023/a:1013689704352

Keywords

RegretDilemmaReinforcement learningLogarithmMathematical optimizationComputer scienceMathematical economicsAction (physics)Bounded functionSimple (philosophy)MathematicsArtificial intelligenceMachine learning

Affiliated Institutions

Related Publications

Competing in the dark: An efficient algorithm for bandit linear optimization

Jacob Abernethy , Elad Hazan , Alexander Rakhlin

We introduce an efficient algorithm for the problem of online linear optimization in the bandit setting which achieves the optimal O*(√T)regret. The setting is a natural general...

2008 ScholarlyCommons (University of Penns... 192 citations

Multi-armed bandits with episode context

Christopher D. Rosin

2011 Annals of Mathematics and Artificial ... 201 citations

Logarithmic Regret Algorithms for Online Convex Optimization

Elad Hazan , Adam Tauman Kalai , Satyen Kale +1 more

2006 Lecture notes in computer science 207 citations

Learning control of finite Markov chains with an explicit trade-off between estimation and control

Mitsuo Satõ , K. Abe , Hiroshi Takeda

An efficient scheme is presented for a learning control problem of finite Markov chains with unknown dynamics, i.e. with unknown transition probabilities. The scheme is designed...

1988 IEEE Transactions on Systems Man and ... 34 citations

Decentralized learning in finite Markov chains

Richard M. Wheeler , Kumpati S. Narendra

The principal contribution of this paper is a new result on the decentralized control of finite Markov chains with unknown transition probabilities and rewords. One decentralize...

1986 IEEE Transactions on Automatic Control 100 citations

Publication Info

Year: 2002
Type: article
Volume: 47
Issue: 2-3
Pages: 235-256
Citations: 5589
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Finite-time Analysis of the Multiarmed Bandit Problem

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

5589

OpenAlex

Cite This

APA Style

                            
                                    Peter Auer, 
                                
                                    Nicolò Cesa‐Bianchi, 
                                
                                    Paul Fischer
                                
                            (2002). 
                            Finite-time Analysis of the Multiarmed Bandit Problem. 
                            Machine Learning
                            , 47
                            (2-3)
                            , 235-256.
                            https://doi.org/10.1023/a:1013689704352

Identifiers

DOI: 10.1023/a:1013689704352