| CPC G08G 1/081 (2013.01) [G06N 20/00 (2019.01)] | 14 Claims |
|
1. A training method for an optimization of a traffic signal, comprising:
segmenting a large-scale road network into intersection groups each comprising a plurality of intersections;
training a reinforcement learning model by allocating a training agent to each intersection group;
performing traffic signal control through an inference of an optimal traffic signal based on the trained reinforcement learning model;
evaluating whether results of the execution of the traffic signal control satisfy a preset goal of learning for traffic signal optimization; and
repeatedly training the reinforcement learning model based on results of the evaluation,
wherein the segmenting of the large-scale road network into the intersection groups comprises segmenting the large-scale road network by applying at least one of a first segmentation method of segmenting a plurality of intersections that constitute the large-scale road network into intersection groups that are operated according to a fixed traffic signal method and a second segmentation method of segmenting intersections according to predetermined priority into intersection groups on the basis of a degree of vehicle congestion in each intersection.
|