Monte Carlo Tree Search for Multi-function Radar Task Scheduling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Monte Carlo Tree Search for Multi-function Radar Task Scheduling

Résumé

Multi-function radars require efficient resource management strategies to fulfill their missions. In particular, task scheduling is crucial to mitigate difficult situations such as when all tasks cannot be accomplished. However, current approaches may prove insufficient in the face of emerging threats. In this article, we present a new formulation for the scheduling problem. Our model allows building schedules in a flexible way, which facilitates the discovery of high-value solutions using heuristics or tree search. We show that our algorithms provide noticeable performance improvement over similar methods proposed previously.
Fichier principal
Vignette du fichier
MCTS_for_MFR_scheduling_CAID21_final.pdf (239.28 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03451838 , version 1 (26-11-2021)

Identifiants

  • HAL Id : hal-03451838 , version 1

Citer

Marc Vincent, Amal El Fallah-Seghrouchni, Vincent Corruble, Narayan Bernardin, Rami Kassab, et al.. Monte Carlo Tree Search for Multi-function Radar Task Scheduling. Conference on Artificial Intelligence for Defense, Nov 2021, Rennes, France. ⟨hal-03451838⟩
137 Consultations
178 Téléchargements

Partager

Gmail Facebook X LinkedIn More