基于异步优势演员-评论家的交通信号控制方法
叶宝林,孙瑞涛,吴维敏,陈滨,姚青
Traffic signal control method based on asynchronous advantage actor-critic
Baolin YE,Ruitao SUN,Weimin WU,Bin CHEN,Qing YAO
图 8
回合累计奖励
Fig.8
Cumulative round reward