Cargando…
Graph MADDPG with RNN for multiagent cooperative environment
Multiagent systems face numerous challenges due to environmental uncertainty, with scalability being a critical issue. To address this, we propose a novel multi-agent cooperative model based on a graph attention network. Our approach considers the relationship between agents and continuous action sp...
Autores principales: | Wei, Xiaolong, Cui, WenPeng, Huang, Xianglin, Yang, LiFang, Tao, Zhulin, Wang, Bing |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10339649/ https://www.ncbi.nlm.nih.gov/pubmed/37457642 http://dx.doi.org/10.3389/fnbot.2023.1185169 |
Ejemplares similares
-
Trans-UTPA: PSO and MADDPG based multi-UAVs trajectory planning algorithm for emergency communication
por: Li, Jie, et al.
Publicado: (2023) -
MW-MADDPG: a meta-learning based decision-making method for collaborative UAV swarm
por: Zhao, Minrui, et al.
Publicado: (2023) -
Multirobot Collaborative Pursuit Target Robot by Improved MADDPG
por: Zhou, Xiao, et al.
Publicado: (2022) -
Retracted: Multirobot Collaborative Pursuit Target Robot by Improved MADDPG
por: Intelligence and Neuroscience, Computational
Publicado: (2023) -
Multiagent cooperation and competition with deep reinforcement learning
por: Tampuu, Ardi, et al.
Publicado: (2017)