基于图卷积模仿学习的分布式群集控制

郭策,曾志文,朱鹏铭,周智千,卢惠民

Decentralized swarm control based on graph convolutional imitation learning

Ce GUO,Zhi-wen ZENG,Peng-ming ZHU,Zhi-qian ZHOU,Hui-min LU

表 1 群集控制策略量化评价

Tab.1 Quantitative evaluation of swarm control strategies

群集控制策略 $ \stackrel{-}{\sigma } $ $ \stackrel{-}{{E}_{\mathrm{G}}} $ Acc 集中式专家策略 −52.878 1.891 1.000 IGCNs −126.183 1.876 0.910 DAGNNs −225.831 1.669 0.755 分布式专家策略 −1199.251 1.215 0.080