Statistically Robust, Risk-Averse Best Arm Identification in Multi-Armed Bandits.

Anmol Kagrecha Jayakrishnan Nair Krishna P. Jagannathan

Published in: CoRR (2020)

Keyphrases

risk averse
multi armed bandits
risk neutral
decision makers
utility function
risk aversion
stochastic programming
bandit problems
graphical models
multistage