Contextual bandits with continuous actions: Smoothing, zooming, and adapting.

Akshay Krishnamurthy John Langford Aleksandrs Slivkins Chicheng Zhang

Published in: COLT (2019)

Keyphrases

contextual information
continuous action
action space
nonparametric regression
smoothing algorithm
multi armed bandits
decision making
least squares
situation calculus
action selection
stochastic systems
image filtering
image smoothing
curve fitting
real time
diffusion equation
human actions
machine learning