Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedback.

Zongqi Wan Xiaoming Sun Jialin Zhang

Published in: CoRR (2022)

Keyphrases

bounded memory
delayed feedback
data streams
multi armed bandits
stochastic systems
hopf bifurcation
artificial intelligence
multi agent
databases
data mining
machine learning
expert systems
special case
monte carlo