@inproceedings{fa023eb9ca4e47ea939b6951a14cf896,
title = "Multi-objective bandits: Optimizing the Generalized Gini Index",
abstract = "We study the multi-armed bandit (MAB) problem where the agent receives a vectorial feedback that encodes many possibly competing objectives to be optimized. The goal of the agent is to find a policy, which can optimize these objectives simultaneously in a fair way. This multi-objective online optimization problem is formalized by using the Generalized Gini Index (GGI) aggregation function. We propose an online gradient descent algorithm which exploits the convexity of the GGI aggregation function, and controls the exploration in a careful way achieving a distribution-free regret O'tild; (T-1/2) with high probability. We test our algorithm on synthetic data as well as on an electric battery control problem where the goal is to trade off the use of the different cells of a battery in order to balance their respective degradation rates.",
author = "R{\'o}bert Busa-Fekete and Bal{\'a}zs Sz{\"o}r{\'e}nyi and Paul Weng and Shie Mannor",
note = "Publisher Copyright: {\textcopyright} 2017 by the author(s).; 34th International Conference on Machine Learning, ICML 2017 ; Conference date: 06-08-2017 Through 11-08-2017",
year = "2017",
language = "الإنجليزيّة",
series = "34th International Conference on Machine Learning, ICML 2017",
pages = "1018--1038",
booktitle = "34th International Conference on Machine Learning, ICML 2017",
}