Cargando…
Mixture of personality improved spiking actor network for efficient multi-agent cooperation
Adaptive multi-agent cooperation with especially unseen partners is becoming more challenging in multi-agent reinforcement learning (MARL) research, whereby conventional deep-learning-based algorithms suffer from the poor new-player-generalization problem, possibly caused by not considering theory-o...
Autores principales: | Li, Xiyun, Ni, Ziyi, Ruan, Jingqing, Meng, Linghui, Shi, Jing, Zhang, Tielin, Xu, Bo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10361619/ https://www.ncbi.nlm.nih.gov/pubmed/37483340 http://dx.doi.org/10.3389/fnins.2023.1219405 |
Ejemplares similares
-
Neural pathway prediction based on multi-neuron spike train data
por: Zeng, Yi, et al.
Publicado: (2014) -
Self-backpropagation of synaptic modifications elevates the efficiency of spiking and artificial neural networks
por: Zhang, Tielin, et al.
Publicado: (2021) -
Efficient Actor Recovery Paradigm for Wireless Sensor and Actor Networks
por: Mahjoub, Reem K., et al.
Publicado: (2017) -
A brain-inspired theory of mind spiking neural network improves multi-agent cooperation and competition
por: Zhao, Zhuoya, et al.
Publicado: (2023) -
Learning multi-agent cooperation
por: Rivera, Corban, et al.
Publicado: (2022)