On Upper-Confidence Bound Policies for Switching Bandit Problems
Authors:
Top Cited Papers
- 1 January 2011
- book chapter
- Published by Springer Nature
- p. 174-188
Abstract
No abstract availableKeywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problemsApplied Mathematics and Computation, 2008
- Tuning Bandit Algorithms in Stochastic Environments2007
- Regret Minimization Under Partial MonitoringMathematics of Operations Research, 2006
- Prediction, Learning, and Games2006
- Asymptotic operating characteristics of an optimal change point detection in hidden Markov modelsThe Annals of Statistics, 2004
- Finite-time Analysis of the Multiarmed Bandit ProblemMachine Learning, 2002
- The Nonstochastic Multiarmed Bandit ProblemSIAM Journal on Computing, 2002
- On prediction of individual sequencesThe Annals of Statistics, 1999
- Tracking the Best ExpertMachine Learning, 1998
- A Probabilistic Theory of Pattern Recognition1996