Augmenting Markov Decision Processes with Advising

Loïs Vanhée 1 Laurent Jeanpierre 1 Abdel-Illah Mouaddib 1
1 Equipe MAD - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : This paper introduces Advice-MDPs, an expansion of Markov Decision Processes for generating policies that take into consideration advising on the desirability, undesirability, and prohibition of certain states and actions. Advice-MDPs enable the design of designing semi-autonomous systems (systems that require operator support for at least handling certain situations) that can efficiently handle unexpected complex environments. Operators, through advising, can augment the planning model for covering unexpected real-world irregularities. This advising can swiftly augment the degree of autonomy of the system, so it can work without subsequent human intervention. This paper details the Advice-MDP formalism, a fast Advice-MDP resolution algorithm, and its applicability for real-world tasks, via the design of a professional-class semi-autonomous robot system ready to be deployed in a wide range of unexpected environments and capable of efficiently integrating operator advising.
Type de document :
Communication dans un congrès
The Thirty-Third AAAI Conference on Artificial Intelligence, Jan 2019, Honolulu, United States
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01929336
Contributeur : Loïs Vanhée <>
Soumis le : mercredi 21 novembre 2018 - 10:29:25
Dernière modification le : mercredi 5 décembre 2018 - 01:21:33

Fichier

root.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01929336, version 1

Citation

Loïs Vanhée, Laurent Jeanpierre, Abdel-Illah Mouaddib. Augmenting Markov Decision Processes with Advising. The Thirty-Third AAAI Conference on Artificial Intelligence, Jan 2019, Honolulu, United States. 〈hal-01929336〉

Partager

Métriques

Consultations de la notice

15

Téléchargements de fichiers

10