On Bayesian Upper Confidence Bounds for Bandit Problems.
Emilie KaufmannOlivier CappéAurélien GarivierPublished in: AISTATS (2012)
Keyphrases
- bandit problems
- confidence bounds
- exploration exploitation
- multi armed bandits
- decision problems
- posterior probability
- multi armed bandit problems
- bayesian networks
- bayesian estimation
- bayesian inference
- maximum likelihood
- decentralized decision making
- optimal strategy
- expected utility
- bayesian learning
- sensitivity analysis
- upper bound
- active learning
- reinforcement learning
- decision making