GHQ: grouped hybrid Q-learning for cooperative heterogeneous multi-agent reinforcement learning

Abstract Previous deep multi-agent reinforcement learning (MARL) algorithms have achieved impressive results, typically in symmetric and homogeneous scenarios. However, asymmetric heterogeneous scenarios are prevalent and usually harder to solve. In this paper, the main discussion is about the coope...

Description complète

Détails bibliographiques

Auteurs principaux:	Xiaoyang Yu, Youfang Lin, Xiangsen Wang, Sheng Han, Kai Lv
Format:	Artigo
Langue:	Inglês
Publié:	Springer 2024-04-01
Collection:	Complex & Intelligent Systems
Sujets:	Heterogeneous multi-agent reinforcement learning Cooperative multi-agent reinforcement learning Value function factorization StarCraftII multi-agent challenge
Accès en ligne:	https://doi.org/10.1007/s40747-024-01415-1
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!