Approximation of Lorenz-Optimal Solutions in Multiobjective Markov Decision Processes - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Approximation of Lorenz-Optimal Solutions in Multiobjective Markov Decision Processes

Patrice Perny
Paul Weng
  • Fonction : Auteur
  • PersonId : 952563
Judy Goldsmith
  • Fonction : Auteur
Josiah Hanna
  • Fonction : Auteur

Résumé

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.
Fichier non déposé

Dates et versions

hal-01216091 , version 1 (15-10-2015)

Identifiants

  • HAL Id : hal-01216091 , version 1

Citer

Patrice Perny, Paul Weng, Judy Goldsmith, Josiah Hanna. Approximation of Lorenz-Optimal Solutions in Multiobjective Markov Decision Processes. Conference on Uncertainty in Artificial Intelligence, UAI 2013, Jul 2013, Bellevue, Washington, United States. pp.Id 208. ⟨hal-01216091⟩
49 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More