@article{Thompson33, title = {{On the likelihood that one unknown probability exceeds another in view of the evidence of two samples}}, author = {W. R. Thompson}, journal = {{Biometrika}}, volume = {25}, number = {3/4}, pages = {285--294}, year = {1933}, publisher = {JSTOR} } @article{Robbins52, title = {{Some aspects of the sequential design of experiments}}, author = {H. Robbins}, journal = {{Bulletin of the American Mathematical Society}}, pages = {527--535}, volume = {58}, number = {5}, year = {1952} } @article{LaiRobbins85, title = {{Asymptotically efficient adaptive allocation rules}}, author = {Lai, Tze Leung and Robbins, Herbert}, journal = {{Advances in Applied Mathematics}}, volume = {6}, number = {1}, pages = {4--22}, year = {1985}, publisher = {Elsevier} } @article{Mitola99, title = {{Cognitive Radio: making software radios more personal}}, author = {Mitola, Joseph and Maguire, Gerald Q.}, journal = {{IEEE Personal Communications}}, volume = {6}, number = {4}, pages = {13--18}, year = {1999}, publisher = {IEEE} } @article{Auer02, title = {{The Non-Stochastic Multi-Armed Bandit Problem}}, author = {Auer, Peter and Cesa-Bianchi, Nicolo and Freund, Yoav and Schapire, Robert E}, journal = {{SIAM Journal on Computing}}, volume = {32}, number = {1}, pages = {48--77}, year = {2002}, publisher = {SIAM} } @Article{Aueral02, title = {{Finite-Time Analysis of the Multi-Armed Bandit Problem}}, author = {Auer, P. and Cesa-Bianchi, N. and Fischer, P.}, journal = {Machine Learning}, year = {2002}, number = {2}, pages = {235--256}, volume = {47}, publisher = {Springer} } @article{Haykin05, title = {{Cognitive Radio: Brain-Empowered Wireless Communications}}, author = {S. Haykin}, journal = {{IEEE Journal on Selected Areas in Communications}}, year = {2005}, volume = {23}, number = {2}, pages = {201-220}, } @article{Zhao07, title = {{A Survey of Dynamic Spectrum Access}}, author = {Q. Zhao and B. M. Sadler}, journal = {{IEEE Signal Processing magazine}}, volume = {24}, number = {3}, pages = {79--89}, year = {2007}, publisher = {IEEE} } @inproceedings{Audibert07, title = {{Tuning bandit algorithms in stochastic environments}}, author = {Audibert, Jean-Yves and Munos, R{\'e}mi and Szepesv{\'a}ri, Csaba}, booktitle = {{International Conference on Algorithmic Learning Theory}}, pages = {150--165}, year = {2007}, organization = {Springer} } @inproceedings{Lazaric09, title = {{Hybrid stochastic-adversarial on-line learning}}, author = {Lazaric, Alessandro and Munos, R{\'e}mi}, booktitle = {Conference on Learning Theory}, year = {2009} } @article{Bubeck12, title = {{Regret analysis of stochastic and nonstochastic multi-armed bandit problems}}, author = {Bubeck, S{\'e}bastien and Cesa-Bianchi, Nicolo and others}, journal = {{Foundations and Trends{\textregistered} in Machine Learning}}, volume = {5}, number = {1}, pages = {1--122}, year = {2012}, publisher = {Now Publishers, Inc.} } @inproceedings{AgrawalGoyal11, title = {{Analysis of Thompson sampling for the Multi-Armed Bandit problem}}, author = {S. Agrawal and N. Goyal}, booktitle = {{JMLR, Conference On Learning Theory}}, pages = {39--1}, year = {2012} } @inproceedings{Garivier11KL, title = {{The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond}}, author = {A. Garivier and O. Capp{\'e}}, booktitle = {{COLT}}, pages = {359--376}, year = {2011} } @inproceedings{Kaufmann12BUCB, title = {{On Bayesian Upper Confidence Bounds for Bandit Problems}}, author = {E. Kaufmann and O. Capp{\'e} and A. Garivier}, booktitle = {{AISTATS}}, pages = {592--600}, year = {2012} } @inbook{Kaufmann12Thompson, title = {{Thompson Sampling: an Asymptotically Optimal Finite-Time Analysis}}, author = {E. Kaufmann and N. Korda and R. Munos}, bookTitle = {{Algorithmic Learning Theory}}, year = {2012}, publisher = {Springer, Berlin Heidelberg}, pages = {199--213}, } @inproceedings{Jouini09, title = {{Multi-Armed Bandit based policies for Cognitive Radio decision making issues}}, author = {Jouini, Wassim and Ernst, Damien and Moy, Christophe and Palicot, Jacques}, booktitle = {Signals, Circuits and Systems (SCS), 2009 3rd International Conference on}, pages = {1--6}, year = {2009}, organization = {IEEE} } @inproceedings{Jouini10, title = {{Upper Confidence Bound based decision making strategies and Dynamic Spectrum Access}}, author = {Jouini, Wassim and Ernst, Damien and Moy, Christophe and Palicot, Jacques}, booktitle = {{IEEE International Conference on Communications (ICC)}}, pages = {1--5}, year = {2010}, organization = {{IEEE}} } @article{Jouini12, title = {{Decision Making for Cognitive Radio equipment: analysis of the first 10 years of exploration}}, author = {Jouini, Wassim and Moy, Christophe and Palicot, Jacques}, journal = {{EURASIP Journal on Wireless Communications and Networking}}, volume = {2012}, number = {1}, pages = {1--16}, year = {2012}, publisher = {{Springer}}, doi = {10.1186/1687-1499-2012-26} } @inproceedings{Maillard11, title = {{Adaptive Bandits: Towards the best history-dependent strategy}}, author = {Maillard, Odalric-Ambrym and Munos, R{\'e}mi}, booktitle = {{AISTATS}}, pages = {570--578}, year = {2011} } @article{Truzzi13, title = {{AdBandit: A New Algorithm For Multi-Armed Bandits}}, author = {Truzzi, Fl{\'a}vio Sales and da Silva, Valdinei Freire and Costa, Anna Helena Reali and Cozman, Fabio Gagliardi}, journal = {{ENIAC}}, volume = {2013}, number = {1}, year = {2013}, } @article{Agarwal16, title = {{Corralling a Band of Bandit Algorithms}}, author = {Agarwal, Alekh and Luo, Haipeng and Neyshabur, Behnam and Schapire, Robert E}, journal = {arXiv preprint arXiv:1612.06246}, year = {2016} } @article{Singla17, title = {{Learning to Use Learners' Advice}}, author = {Singla, Adish and Hassani, Hamed and Krause, Andreas}, journal = {arXiv preprint arXiv:1702.04825}, year = {2017} } @article{Luo17, title = {{Efficient Contextual Bandits in Non-stationary Worlds}}, author = {Luo, Haipeng and Agarwal, Alekh and Langford, John}, journal = {arXiv preprint arXiv:1708.01799}, year = {2017} }