ML Anthology

Optimizing Quantiles in Preference-Based Markov Decision Processes

Hugo Gilbert, Paul Weng, Yan Xu
AAAI 2017 pp. 3569-3575
doi:10.1609/AAAI.V31I1.11026 /aaai/2017/gilbert2017aaai-optimizing/

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.

PDF AAAI Semantic Scholar

Cite

Text

Gilbert et al. "Optimizing Quantiles in Preference-Based Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.11026

Markdown

[Gilbert et al. "Optimizing Quantiles in Preference-Based Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/gilbert2017aaai-optimizing/) doi:10.1609/AAAI.V31I1.11026

BibTeX

@inproceedings{gilbert2017aaai-optimizing,
  title     = {{Optimizing Quantiles in Preference-Based Markov Decision Processes}},
  author    = {Gilbert, Hugo and Weng, Paul and Xu, Yan},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {3569-3575},
  doi       = {10.1609/AAAI.V31I1.11026},
  url       = {https://mlanthology.org/aaai/2017/gilbert2017aaai-optimizing/}
}