Multi-agent learning via gradient ascent activity-based credit assignment - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Scientific Reports Année : 2023

Multi-agent learning via gradient ascent activity-based credit assignment

Résumé

We consider the situation in which cooperating agents learn to achieve a common goal based solely on a global return that results from all agents’ behavior. The method proposed is based on taking into account the agents’ activity , which can be any additional information to help solving multi-agent decentralized learning problems. We propose a gradient ascent algorithm and assess its performance on synthetic data.
Fichier principal
Vignette du fichier
s41598-023-42448-9-2.pdf (2.06 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04297262 , version 1 (21-11-2023)

Identifiants

Citer

Oussama Sabri, Luc Lehéricy, Alexandre Muzy. Multi-agent learning via gradient ascent activity-based credit assignment. Scientific Reports, 2023, 13 (1), pp.15256. ⟨10.1038/s41598-023-42448-9⟩. ⟨hal-04297262⟩
17 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More