Reinforcement learning (RL) is gradually being implemented in the hybrid electric vehicle (HEV) supervisory control. Even though RL exhibits significant fuel consumption saving, the long learning time makes it hardly applicable in real-world vehicles. This study aims to reduce the learning iterations of Q-learning in HEV application utilizing warm-start methods. Different from previous studies, which initiated Q-learning with zero or random Q values, this study initiates the Q-learning with different supervisory controls, and the detailed analysis is given. The results show that the proposed warm-start Q-learning requires 68.8% fewer iterations than cold-start Q-learning and improves 10%–16% MPG compared with equivalent consumption minimization strategy control. The results of this study can be used to facilitate the deployment of RL in vehicle applications.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning Time Reduction Using Warm-Start Methods for a Reinforcement Learning-Based Supervisory Control in Hybrid Electric Vehicle Applications


    Contributors:
    Xu, Bin (author) / Hou, Jun (author) / Shi, Junzhe (author) / Li, Huayi (author) / Rathod, Dhruvang (author) / Wang, Zhe (author) / Filipi, Zoran (author)


    Publication date :

    2021-06-01


    Size :

    5666720 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Hybrid Electric Vehicle Powertrain Control Based on Reinforcement Learning

    Yoon, Hwan-Sik / Yao, Zhengyu | SAE Technical Papers | 2021



    Rule-based supervisory control of split-parallel hybrid electric vehicle

    Anbaran, Sajad A. / Idris, N. R. N. / Jannati, M. et al. | IEEE | 2014