METHOD FOR JOINT OPTIMIZATION FEEDFORWARD ARTIFICIAL NEURAL NETWORKS WEIGHTS AND STRUCTURE IN DEEP MULTI-AGENT REINFORCEMENT LEARNING

Increasing the intelligence of tasks solved using mobile cyber-physical systems (MCPS) requires the use of artificial neural networks (ANNs) and methods of multi-agent deep reinforcement learning (MDRL).

Enregistré dans:
Détails bibliographiques
Auteur principal: V. I. Petrenko
Format: Article
Langue:russe
Publié: North-Caucasus Federal University 2022-08-01
Collection:Современная наука и инновации
Sujets:
Accès en ligne:https://msi.elpub.ru/jour/article/view/309
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!