Multiagent Hierarchical Cognition Difference Policy for Multiagent Cooperation

Algorithms

Zhen Liu¹  Jianqiang Yi²  Zhiqiang Pu²  Huimu Wang² 

[1] Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China;School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China;

关键词: multiagent system;    deep reinforcement learning;    variational autoencoder;    attention mechanism;   

DOI  :  10.3390/a14030098

来源: DOAJ

【 摘 要 】

Multiagent cooperation is one of the most attractive research fields in multiagent systems. There are many attempts made by researchers in this field to promote cooperation behavior. However, several issues still exist, such as complex interactions among different groups of agents, redundant communication contents of irrelevant agents, which prevents the learning and convergence of agent cooperation behaviors. To address the limitations above, a novel method called multiagent hierarchical cognition difference policy (MA-HCDP) is proposed in this paper. It includes a hierarchical group network (HGN), a cognition difference network (CDN), and a soft communication network (SCN). HGN is designed to distinguish different underlying information of diverse groups’ observations (including friendly group, enemy group, and object group) and extract different high-dimensional state representations of different groups. CDN is designed based on a variational auto-encoder to allow each agent to choose its neighbors (communication targets) adaptively with its environment cognition difference. SCN is designed to handle the complex interactions among the agents with a soft attention mechanism. The results of simulations demonstrate the superior effectiveness of our method compared with existing methods.

【 授权许可】

Unknown