Reinforcement learning for traffic control system: Study of Exploration methods using Q-learning (original) (raw)

2017

Abstract

1First Systems Architecture Team, Laboratory of Research in Engineering, University Hassan II Casablanca ENSEM Casablanca 20200, Morocco 2Laboratory of Mechanical Engineering, Industrial Management and Innovation (IMMII) Hassan I University, FST of Settat, B.P. 577, Settat, Morocco. ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract Road congestion problems are becoming more complicated. This is because of static management of the traffic lights. Reinforcement Learning RL is an artificial intelligence approach that enables adaptive real-time control at intersections. RL allows vehicles to cross faster and minimize waiting times in the roadways. The objective of this article is to examine and test the different action selection techniques using the Q-learning algorithm in a case study. We will also present the different signal control systems based on RL, as well as the theoretical frame...

Prof.hicham Medromi hasn't uploaded this paper.

Let Prof.hicham know you want this paper to be uploaded.

Ask for this paper to be uploaded.