Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
Multi-agent learning via gradient ascent activity-based credit assignment
Oussama Sabri (Centre National de la Recherche Scientifique, Université Côte d'Azur), Luc Lehéricy (Centre National de la Recherche Scientifique, Université Côte d'Azur), Alexandre Muzy (Centre National de la Recherche Scientifique, Université Côte d'Azur)
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.