@inproceedings{91a398a173534edf862c1b004cf5a70b,
title = "Algorithmic models of human decision making in Gaussian multi-armed bandit problems",
abstract = "We consider a heuristic Bayesian algorithm as a model of human decision making in multi-armed bandit problems with Gaussian rewards. We derive a novel upper bound on the Gaussian inverse cumulative distribution function and use it to show that the algorithm achieves logarithmic regret. We extend the algorithm to allow for stochastic decision making using Boltzmann action selection with a dynamic temperature parameter and provide a feedback rule for tuning the temperature parameter such that the stochastic algorithm achieves logarithmic regret. The stochastic algorithm encodes many of the observed features of human decision making.",
author = "Paul Reverdy and Vaibhav Srivastava and Leonard, {Naomi E.}",
note = "Publisher Copyright: {\textcopyright} 2014 EUCA.; 13th European Control Conference, ECC 2014 ; Conference date: 24-06-2014 Through 27-06-2014",
year = "2014",
month = jul,
day = "22",
doi = "10.1109/ECC.2014.6862580",
language = "English (US)",
series = "2014 European Control Conference, ECC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2210--2215",
booktitle = "2014 European Control Conference, ECC 2014",
address = "United States",
}