Online Limited Memory Neural-Linear Bandits with Likelihood Matching.

Ofir Nabati Tom Zahavy Shie Mannor

Published in: ICML (2021)

Keyphrases

limited memory
real time
memory space
data streams
sliding window
online learning
quasi newton method
influence diagrams
continuous data streams
neural network
image matching
stream mining
sufficient conditions
multi agent
stochastic systems
graphical models
learning algorithm
data mining
past observations