Reinforcement Learning Method with Dynamic Learning Rate for Real-Time Route Guidance Based on SUMO

The increasing number of vehicles and dynamic changes in traffic situations make real-time route planning strongly necessary. The route-guiding method is supposed to cope with dynamic traffic situations. In addition, the ability to adapt to the second fastest route is very important when traffic congestion suddenly occurs on the fastest path. This paper proposes a method of using reinforcement learning to solve dynamic route planning problems, and the adaptation from a static learning rate to a dynamic learning rate enhances the capability to deal with emergent congestion. Meanwhile, the waiting time before each traffic light also is considered as a reward factor in the proposed algorithm. Contrast experiments have been conducted on the simulation network by SUMO, which has demonstrated well that our proposed method has better performance than other methods.