@inproceedings{erraqabi2017trading,
abstract = {In multi-armed bandits, the most common objective is the maximization of the cumulative reward. Alternative settings include active exploration, where a learner tries to gain accurate estimates of the rewards of all arms. While these objectives are contrasting, in many scenarios it is desirable to trade off rewards and errors. For instance, in educational games the designer wants to gather generalizable knowledge about the behavior of the students and teaching strategies (small estimation errors) but, at the same time, the system needs to avoid giving a bad experience to the players, who may leave the system permanently (large reward). In this paper, we formalize this tradeoff and introduce the ForcingBalance algorithm whose performance is provably close to the best possible tradeoff strategy. Finally, we demonstrate on real-world educational data that ForcingBalance returns useful information about the arms without compromising the overall reward.},
author = {Erraqabi, Akram and Lazaric, Alessandro and Valko, Michal and Brunskill, Emma and Liu, Yun-en},
booktitle = {International Conference on Artificial Intelligence and Statistics},
file = {:Users/miki/Dropbox/research/bandits/educational/2016-AISTATS-discovery-bandit/erraqabi2017trading.pdf:pdf},
title = {{Trading off rewards and errors in multi-armed bandits}},
year = {2017}
}