Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations.

Hongju Park Mohamad Kazem Shirani Faradonbeh

Published in: CoRR (2022)

Keyphrases

worst case
greedy algorithm
data sets
lower bound
contextual information
context sensitive
neural network
state space
upper bound
optimal policy
error bounds
context dependent
machine learning
search algorithm
context aware
average case