Traffic signal control is one of the most effective methods of traffic management in urban areas . In recent years, traffic control methods based on deep reinforcement learning (DRL) have gained attention due to their ability to exploit real-time traffic data . In order to address these issues, we introduce two notions of fairness: delay-based and throughput-basedfairness . We evaluate the performance of our proposed methods using three traffic arrival distributions,and find that our methods outperform the baselines in the tested scenarios . We find that . our methods . outperform . the baseline in the testing scenarios, which are based on traffic arrival distribution, and that can achieve a high throughput as well. We also find that these methods outperformed the basinals in the . tested scenarios in the test scenarios. The methods outperforming the . testing scenarios. are based based on three traffic .

Author(s) : Majid Raeis, Alberto Leon-Garcia

Links : PDF - Abstract

Code :

Keywords : traffic - methods - scenarios - based - find -

Leave a Reply

Your email address will not be published. Required fields are marked *