Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits.

Yunbei Xu Assaf Zeevi

Published in: CoRR (2020)

Keyphrases

confidence bounds
contextual information
context sensitive
stochastic systems
real time
genetic algorithm
data structure
databases
machine learning
information systems
image sequences
search algorithm
natural language
logical framework
multi armed bandit
multi armed bandits