Combining Multiple Strategies for Multiarmed Bandit Problems and Asymptotic Optimality
Joint Authors
Choe, Sanghee
Chang, Hyeong Soo
Source
Journal of Control Science and Engineering
Issue
Vol. 2015, Issue 2015 (31 Dec. 2015), pp.1-7, 7 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2015-03-25
Country of Publication
Egypt
No. of Pages
7
Main Subjects
Electronic engineering
Information Technology and Computer Science
Abstract EN
This brief paper provides a simple algorithm that selects a strategy at each time in a given set of multiple strategies for stochastic multiarmed bandit problems, thereby playing the arm by the chosen strategy at each time.
The algorithm follows the idea of the probabilistic ϵ t -switching in the ϵ t -greedy strategy and is asymptotically optimal in the sense that the selected strategy converges to the best in the set under some conditions on the strategies in the set and the sequence of { ϵ t } .
American Psychological Association (APA)
Chang, Hyeong Soo& Choe, Sanghee. 2015. Combining Multiple Strategies for Multiarmed Bandit Problems and Asymptotic Optimality. Journal of Control Science and Engineering،Vol. 2015, no. 2015, pp.1-7.
https://search.emarefa.net/detail/BIM-1067760
Modern Language Association (MLA)
Chang, Hyeong Soo& Choe, Sanghee. Combining Multiple Strategies for Multiarmed Bandit Problems and Asymptotic Optimality. Journal of Control Science and Engineering No. 2015 (2015), pp.1-7.
https://search.emarefa.net/detail/BIM-1067760
American Medical Association (AMA)
Chang, Hyeong Soo& Choe, Sanghee. Combining Multiple Strategies for Multiarmed Bandit Problems and Asymptotic Optimality. Journal of Control Science and Engineering. 2015. Vol. 2015, no. 2015, pp.1-7.
https://search.emarefa.net/detail/BIM-1067760
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1067760