Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedback.

Zongqi Wan Xiaoming Sun Jialin Zhang

Published in: IJCAI (2022)

Keyphrases

bounded memory
delayed feedback
data streams
multi agent
stochastic systems
expert systems
peer to peer
digital signature scheme
real time
computer vision
image segmentation
markov chain
multi armed bandit
multi armed bandits