Intelligent traffic lights in smart cities can optimally reduce traffic congestion. In this study, we employ reinforcement learning to train the control agent of a traffic light on a simulator of urban mobility. As a difference from existing works, a policy-based deep reinforcement learning method, Proximal Policy Optimization (PPO), is utilized rather than value-based methods such as Deep Q Network (DQN) and Double DQN (DDQN). First, the obtained optimal policy from PPO is compared to those from DQN and DDQN. It is found that the policy from PPO performs better than the others. Next, instead of fixed-interval traffic light phases, we adopt light phases with variable time intervals, which result in a better policy to pass the traffic flow. Then, the effects of environment and action disturbances are studied to demonstrate that the learning-based controller is robust. Finally, we consider unbalanced traffic flows and find that an intelligent traffic light can perform moderately well for the unbalanced traffic scenarios, although it learns the optimal policy from the balanced traffic scenarios only.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Intelligent Traffic Light via Policy-based Deep Reinforcement Learning


    Additional title:

    Int. J. ITS Res.


    Contributors:
    Zhu, Yue (author) / Cai, Mingyu (author) / Schwarz, Chris W. (author) / Li, Junchao (author) / Xiao, Shaoping (author)


    Publication date :

    2022-12-01


    Size :

    11 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Traffic Management of Autonomous Vehicles using Policy Based Deep Reinforcement Learning and Intelligent Routing

    Mushtaq, Anum / Haq, Irfan ul / Sarwar, Muhammad Azeem et al. | ArXiv | 2022

    Free access

    Traffic light control using deep policy-gradient and value-function-based reinforcement learning

    Mousavi, Seyed Sajad / Schukat, Michael / Howley, Enda | IET | 2017

    Free access

    Traffic light control using deep policy‐gradient and value‐function‐based reinforcement learning

    Mousavi, Seyed Sajad / Schukat, Michael / Howley, Enda | Wiley | 2017

    Free access

    Deep reinforcement learning traffic light control method

    KONG YAN / LI YING / CHIH-CHAO YANG | European Patent Office | 2024

    Free access