Traffic signal control method and device, electronic equipment and readable storage medium

Abstract

The embodiment of the invention discloses a traffic signal control method and device, electronic equipment and a readable storage medium, and the method comprises the steps: obtaining the state information of a current stage of a current intersection; receiving a control action of the previous stage of the adjacent intersection of the current intersection; determining an average value of the codesof the control actions of the previous stage close to the intersection; and determining the control action of the current stage of the current intersection based on the state information of the current stage of the current intersection and the average value of the codes of the control action of the previous stage of the adjacent intersection, thereby taking the interaction between all intelligentagents and the traffic flow environment as a random game problem. The dimension of an action space is reduced through average field approximation, the interaction problem of the intelligent agent andother intelligent agents is converted into the interaction problem of a certain average effect of the intelligent agent and an adjacent intelligent agent, and the problem of dimension disasters is avoided.

Description

technical field [0001] The present disclosure relates to the technical field of intelligent transportation, in particular to a traffic signal control method, device, electronic equipment and readable storage medium. Background technique [0002] With the rapid development of China's social economy and the continuous increase in the number of cars owned by urban residents, the phenomenon of road congestion is becoming more and more frequent. This problem also directly affects the quality of life and travel experience of urban residents. As a key part of traffic flow management, traffic signal timing plays an important role in traffic flow control, road congestion mitigation, and regional traffic flow coordination. [0003] Research on traffic light intelligent control based on deep reinforcement learning introduces deep reinforcement learning algorithm into traffic light timing, builds an agent at each intersection, obtains traffic flow information at the current intersection...

AI Technical Summary

Problems solved by technology

[0004] However, the inventors found that there are at least the following problems in the prior art: if the agents at each intersection are regarded as independent individuals, each agent collects local state information and makes action decisions independently, lacking the state, Action information interaction, which is easy to cause local traffic jams, can not achieve better regional coordination effect; if the interaction between all agents and the environment is regarded as a random game problem, the action space that the agent needs to deal with includes all agents. Action selection, in the case of dealing with multiple intersections or even large-scale road networks, will cause the dimension of the action space to increase exponentially with the increase in the number of intersections, causing the "curse of dimensionality"

Images