Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits
- 1 January 2011
- book chapter
- Published by Springer Nature
- p. 189-203
Abstract
No abstract availableKeywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Pure exploration in finitely-armed and continuous-armed banditsTheoretical Computer Science, 2011
- Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits2011
- Active learning in heteroscedastic noiseTheoretical Computer Science, 2010
- Exploration–exploitation tradeoff using variance estimates in multi-armed banditsTheoretical Computer Science, 2009
- Adaptive Optimal Allocation in Stratified Sampling MethodsMethodology and Computing in Applied Probability, 2008