Stochastic Linear Contextual Bandits with Diverse Contexts.

Weiqiang Wu Jing Yang Cong Shen

Published in: CoRR (2020)

Keyphrases

stochastic systems
regret bounds
contextual information
contextual knowledge
stochastic optimization
linear systems
learning algorithm
wide variety
monte carlo
user browsing behavior
linear complexity
decision problems
real time
lower bound
reinforcement learning
machine learning
real world
data sets