METHOD AND APPARATUS FOR CONTROLLING DISTRIBUTED TRAFFIC SIGNAL BASED ON REINFORCEMENT LEARNING IN MULTI-INTERSECTIONS ENVIRONMENT

摘要

The present invention provides an action of setting a traffic signal as one of a plurality of signal combinations for a state distinguished according to a plurality of traffic directions at an intersection, a specific state, and the vehicle traffic volume of the intersection and average waiting of vehicles at a plurality of intersections adjacent to the intersection setting a reward determined according to time; performing reinforcement learning using predetermined traffic data based on the state, the action, and the reward; and setting traffic signals for a plurality of travel directions of the target intersection based on the result of the reinforcement learning and traffic information of the target intersection corresponding to the intersection. A learning-based distributed traffic signal control method is provided.