Optimizing Quantiles in Preference-based Markov Decision Processes
Artificial Intelligence
2016-12-02 v1
Abstract
In the Markov decision process model, policies are usually evaluated by expected cumulative rewards. As this decision criterion is not always suitable, we propose in this paper an algorithm for computing a policy optimal for the quantile criterion. Both finite and infinite horizons are considered. Finally we experimentally evaluate our approach on random MDPs and on a data center control problem.
Cite
@article{arxiv.1612.00094,
title = {Optimizing Quantiles in Preference-based Markov Decision Processes},
author = {Hugo Gilbert and Paul Weng and Yan Xu},
journal= {arXiv preprint arXiv:1612.00094},
year = {2016}
}
Comments
Long version of AAAI 2017 paper. arXiv admin note: text overlap with arXiv:1611.00862