系统工程理论与实践
繫統工程理論與實踐
계통공정이론여실천
Systems Engineering—Theory & Practice
2006年
8期
136~140
,共null页
Q-学习 智能体 交通信号控制
Q-學習 智能體 交通信號控製
Q-학습 지능체 교통신호공제
Q-Learning; agent; traffic signal control
为了减少车辆通过路口时的延误,采用Q-学习方法对智能体控制的单路口进行信号配时的优化,在模糊控制规则集的基础上,通过Q-学习来改进控制规则的组合,从而达到改善信号控制效果的目的.仿真实验的结果表明,基于Q-学习的信号控制方法优于定时控制、感应式控制和基于遗传算法的信号控制方法.研究说明,基于Q-学习的信号控制方法适合城市交通控制.
為瞭減少車輛通過路口時的延誤,採用Q-學習方法對智能體控製的單路口進行信號配時的優化,在模糊控製規則集的基礎上,通過Q-學習來改進控製規則的組閤,從而達到改善信號控製效果的目的.倣真實驗的結果錶明,基于Q-學習的信號控製方法優于定時控製、感應式控製和基于遺傳算法的信號控製方法.研究說明,基于Q-學習的信號控製方法適閤城市交通控製.
위료감소차량통과로구시적연오,채용Q-학습방법대지능체공제적단로구진행신호배시적우화,재모호공제규칙집적기출상,통과Q-학습래개진공제규칙적조합,종이체도개선신호공제효과적목적.방진실험적결과표명,기우Q-학습적신호공제방법우우정시공제、감응식공제화기우유전산법적신호공제방법.연구설명,기우Q-학습적신호공제방법괄합성시교통공제.
In order to reduce the delay of vehicles passing intersection, we optimize the signal timing of agent controlled intersection by Q-Learning method. On the basis of fuzzy rule set for signal control, we improve the effect of signal control through optimizing the combination of control rules with Q-Learning. The result of simulation illustrates that the signal control method based on Q-Learning is better than fixed-time control, actuated control and signal control based on genetic algorithms. The result of this research indicates that the signal control method based on Q-Learning adapt to the urban traffic control.
