Combining Multiple Strategies for Multiarmed Bandit Problems and Asymptotic Optimality
| Autor: | Sanghee Choe, Hyeong Soo Chang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2015 |
| Předmět: |
Sequence
Mathematical optimization Article Subject Probabilistic logic lcsh:QA75.5-76.95 Computer Science Applications Set (abstract data type) Asymptotically optimal algorithm lcsh:TA1-2040 Modeling and Simulation lcsh:Electronic computers. Computer science Electrical and Electronic Engineering lcsh:Engineering (General). Civil engineering (General) SIMPLE algorithm Mathematics |
| Zdroj: | Journal of Control Science and Engineering, Vol 2015 (2015) |
| ISSN: | 1687-5257 1687-5249 |
| Popis: | 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 probabilisticϵt-switching in theϵt-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{ϵt}. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text