Approximation of Lorenz-Optimal Solutions in Multiobjective Markov Decision Processes
Abstract
This paper is devoted to fair optimization in Multiobjective Markov Decision Processes (MOMDPs). A MOMDP is an extension of the MDP model for planning under uncertainty while trying to optimize several reward functions simultaneously. This applies to multiagent problems when rewards define individual utility functions, or in multicriteria problems when rewards refer to different features. In this setting, we study the determination of policies leading to Lorenz-non-dominated tradeoffs. Lorenz dominance is a refinement of Pareto dominance that was introduced in Social Choice for the measurement of inequalities. In this paper, we introduce methods to efficiently approximate the sets of Lorenz-non-dominated solutions of infinite-horizon, discounted MOMDPs. The approximations are polynomial-sized subsets of those solutions.
Cite
Text
Perny et al. "Approximation of Lorenz-Optimal Solutions in Multiobjective Markov Decision Processes." Conference on Uncertainty in Artificial Intelligence, 2013.Markdown
[Perny et al. "Approximation of Lorenz-Optimal Solutions in Multiobjective Markov Decision Processes." Conference on Uncertainty in Artificial Intelligence, 2013.](https://mlanthology.org/uai/2013/perny2013uai-approximation/)BibTeX
@inproceedings{perny2013uai-approximation,
title = {{Approximation of Lorenz-Optimal Solutions in Multiobjective Markov Decision Processes}},
author = {Perny, Patrice and Weng, Paul and Goldsmith, Judy and Hanna, Josiah},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2013},
url = {https://mlanthology.org/uai/2013/perny2013uai-approximation/}
}