Quality-Based Reinforcement Learning in Intelligent Opportunistic Software Composition - Systèmes Multi-Agents Coopératifs Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Quality-Based Reinforcement Learning in Intelligent Opportunistic Software Composition

Résumé

Internet of Things and cyber-physical systems are characterised by openness and an increasing number of devices and their associated services. In a previous work, we have proposed to exploit opportunistically these services in order to automatically make emerge customised applications that suit user preferences. For that, we have developed a generic solution for bottom-up opportunistic service composition, based on reinforcement learning. In this work, it is extended to handle more efficiently the appearance of new components using \textit{service annotation} and \textit{quality attributes} in order to generalise and share knowledge with new discovered services. A didactic use case is used for illustration and demonstration purposes.
Fichier principal
Vignette du fichier
Quality_based_learning_in_intelligentopportunistic_software_composition___CAMERA_READY.pdf (276.38 Ko) Télécharger le fichier

Dates et versions

hal-03494584 , version 1 (19-12-2021)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

  • HAL Id : hal-03494584 , version 1

Citer

Kahina Hacid, Sylvie Trouilhet, Jean-Paul Arcangeli, Françoise Adreit. Quality-Based Reinforcement Learning in Intelligent Opportunistic Software Composition. 30th IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE 2021), Oct 2021, Bayonne (virtual), France. ⟨hal-03494584⟩
79 Consultations
59 Téléchargements

Partager

Gmail Facebook X LinkedIn More