Taking a hint: How to leverage loss predictors in contextual bandits?

Chen-Yu Wei Haipeng Luo Alekh Agarwal

Published in: CoRR (2020)

Keyphrases

contextual information
context sensitive
regret bounds
stochastic systems
database
data sets
training data
context dependent
neural network
genetic algorithm
search engine
decision trees
pairwise
error propagation
query performance prediction