Minimax Regret for Cascading Bandits.

Daniel Vial Sujay Sanghavi Sanjay Shakkottai R. Srikant

Published in: NeurIPS (2022)

Keyphrases

minimax regret
preference elicitation
decision problems
utility function
stochastic programming
misclassification costs
reward function
multistage
optimization criterion
decision making
multi agent
active learning
multi class
cost sensitive
decision theory