Gökçesu, KaanErgen, TolgaÇiftçi, S.Kozat, Süleyman Serdar2018-04-122018-04-122017http://hdl.handle.net/11693/37602Date of Conference: 15-18 May 2017Conference Name: IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017In this paper, we study the adversarial multi armed bandit problem and present a generally implementable efficient bandit arm selection structure. Since we do not have any statistical assumptions on the bandit arm losses, the results in the paper are guaranteed to hold in an individual sequence manner. The introduced framework is able to achieve the optimal regret bounds by employing general weight assignments on bandit arm selection sequences. Hence, this framework can be used for a wide range of applications.TurkishAdversarial multi-armed banditEfficient implementationGeneral frameworkSwitching banditIndividual sequencesMulti-armed bandit problemOptimal regretSelection sequencesSignal processingConference Paper10.1109/SIU.2017.7960214