Multi-Objective Reinforcement Learning based on Decomposition: A taxonomy and framework

Felten, Florian; Talbi, El-Ghazali; Danoy, Grégoire

Type de document :

Rapport de recherche

DOI :

10.48550/arXiv.2311.12495

Titre :

Multi-Objective Reinforcement Learning based on Decomposition: A taxonomy and framework

Auteur(s) :

Felten, Florian [Auteur]
Université du Luxembourg = University of Luxembourg = Universität Luxemburg [uni.lu]
Talbi, El-Ghazali [Auteur]
Université de Lille
Inria Lille - Nord Europe
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Optimisation de grande taille et calcul large échelle [BONUS]
Danoy, Grégoire [Auteur]
Université du Luxembourg = University of Luxembourg = Universität Luxemburg [uni.lu]

Éditeur :

arXiv

Institution :

University of Luxembourg

Date de publication :

2023

Mot(s)-clé(s) en anglais :

Machine Learning (cs.LG)
FOS: Computer and information sciences

Discipline(s) HAL :

Informatique [cs]

Résumé en anglais : [en]

Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies making different compromises among conflicting objectives. The recent surge of interest in MORL has led to diverse studies and solving ...
Lire la suite >Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies making different compromises among conflicting objectives. The recent surge of interest in MORL has led to diverse studies and solving methods, often drawing from existing knowledge in multi-objective optimization based on decomposition (MOO/D). Yet, a clear categorization based on both RL and MOO/D is lacking in the existing literature. Consequently, MORL researchers face difficulties when trying to classify contributions within a broader context due to the absence of a standardized taxonomy. To tackle such an issue, this paper introduces Multi-Objective Reinforcement Learning based on Decomposition (MORL/D), a novel methodology bridging RL and MOO literature. A comprehensive taxonomy for MORL/D is presented, providing a structured foundation for categorizing existing and potential MORL works. The introduced taxonomy is then used to scrutinize MORL research, enhancing clarity and conciseness through well-defined categorization. Moreover, a flexible framework derived from the taxonomy is introduced. This framework accommodates diverse instantiations using tools from both RL and MOO/D. Implementation across various configurations demonstrates its versatility, assessed against benchmark problems. Results indicate MORL/D instantiations achieve comparable performance with significantly greater versatility than current state-of-the-art approaches. By presenting the taxonomy and framework, this paper offers a comprehensive perspective and a unified vocabulary for MORL. This not only facilitates the identification of algorithmic contributions but also lays the groundwork for novel research avenues in MORL, contributing to the continued advancement of this field.Lire moins >

Langue :

Anglais

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Fichiers

2311.12495
Accès libre
Accéder au document

Multi-Objective Reinforcement Learning ... BibTeX CSV Excel RIS

Fichiers

Multi-Objective Reinforcement Learning ...

BibTeX

CSV

Excel

RIS