The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits.

Sepehr Assadi Chen Wang

Published in: CoRR (2023)

Keyphrases

multi armed bandits
lower bound
upper bound
bandit problems
data streams
branch and bound algorithm
objective function
worst case
evolutionary algorithm
machine learning
optical flow
np hard
multi class
decision problems
vc dimension