Login / Signup
Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations.
Hongju Park
Mohamad Kazem Shirani Faradonbeh
Published in:
CDC (2022)
Keyphrases
</>
worst case
greedy algorithm
lower bound
context sensitive
machine learning
case study
dynamic programming
contextual information
neural network
feature selection
search algorithm
np hard
sufficient conditions
average case
worst case analysis