An efficient bandit algorithm for general weight assignments
Kozat, S. S.
2017 25th Signal Processing and Communications Applications Conference, SIU 2017
Institute of Electrical and Electronics Engineers Inc.
Item Usage Stats
MetadataShow full item record
In 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. © 2017 IEEE.
KeywordsAdversarial multi-armed bandit
Multi armed bandit
Multi-armed bandit problem
Published Version (Please cite this version)http://dx.doi.org/10.1109/SIU.2017.7960214
Showing items related by title, author, creator and subject.
Sahin, U.; Yucesoy, V.; Koc, A.; Tekin, C. (Institute of Electrical and Electronics Engineers Inc., 2017)Optimum localization problem, which has a wide range of application areas in real life such as emergency services, command and control systems, warehouse localization, shipment planning, aims to find the best location to ...
Şafak, B. (2005)"The Eskiya", which was written and directed by Yavuz Turgul in 1996 puts the bandits model of the folk narrations into İstanbul, one of the modern metropolises. In this article, on the sample of "The Eskiya", "noble ...
Tekin, C.; Turgay, E. (IEEE Computer Society, 2017)In this paper, we propose a new contextual bandit problem with two objectives, where one of the objectives dominates the other objective. Unlike single-objective bandit problems in which the learner obtains a random scalar ...