Risk-Aversion in Multi-armed Bandits.

Amir Sani Alessandro Lazaric Rémi Munos

Published in: NIPS (2012)

Keyphrases

multi armed bandits
risk aversion
utility function
expected utility
bandit problems
risk averse
risk neutral
exchange rate
decision makers
multi armed bandit
probabilistic model
upper bound
special case
markov decision processes