SELF-ORGANIZED CONTROL OF TRAFFIC SIGNALS BASED ON REINFORCEMENT LEARNING AND GENETIC ALGORITHM
基于再励学习与遗传算法的交通信号自组织控制

A combinative algorithm of reinforcement learning and genetic algorithm is proposed in this paper and is applied to self-organized control of the traffic signals. The reinforcement learning focuses on the optimization of intersection's traffic flow which modifies the split of traffic signal cycle, while the genetic algorithm intends to introduce a global optimization criterion to each of the local learning processes which modifies the cycle itself of traffic signals. This approach overcomes the drawbacks in existing control method such as huge data transfer and communication, accurate traffic model and so on.