Improved Pure Exploration in Linear Bandits with No-Regret Learning.

Mohammadi Zaki Avi Mohan Aditya Gopalan

Published in: IJCAI (2022)

Keyphrases

online learning
learning algorithm
learning systems
knowledge acquisition
learning problems
learning tasks
learning process
multi armed bandits
active learning
pairwise
supervised learning
mobile robot
background knowledge
mobile learning
multi agent systems
learning scheme
cognitive load
training data