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...

Descrición completa

Detalles Bibliográficos

Principais autores:	Xiaoyang Yu, Youfang Lin, Xiangsen Wang, Sheng Han, Kai Lv
Formato:	Artigo
Idioma:	Inglês
Publicado:	Springer 2024-04-01
Series:	Complex & Intelligent Systems
Assuntos:	Heterogeneous multi-agent reinforcement learning Cooperative multi-agent reinforcement learning Value function factorization StarCraftII multi-agent challenge
Acceso en liña:	https://doi.org/10.1007/s40747-024-01415-1
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!