Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two predominant problems: behaviors are unexplainable, and they cannot guarantee safety under new scenarios. This paper presents a safe RL algorithm, called Parallel Constrained Policy Optimization (PCPO), for two autonomous driving tasks. PCPO extends today’s common actor-critic architecture to a three-component learning framework, in which three neural networks are used to approximate the policy function, value function and a newly added risk function, respectively. Meanwhile, a trust region constraint is added to allow large update steps without breaking the monotonic improvement condition. To ensure the feasibility of safety constrained problems, synchronized parallel learners are employed to explore different state spaces, which accelerates learning and policy-update. The simulations of two scenarios for autonomous vehicles confirm we can ensure safety while achieving fast learning.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization*


    Contributors:
    Wen, Lu (author) / Duan, Jingliang (author) / Li, Shengbo Eben (author) / Xu, Shaobing (author) / Peng, Huei (author)


    Publication date :

    2020-09-20


    Size :

    2798621 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Safe Reinforcement Learning with Policy-Guided Planning for Autonomous Driving

    Rong, Jikun / Luan, Nan | British Library Conference Proceedings | 2020



    Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles

    Makantasis, Konstantinos / Kontorinaki, Maria / Nikolos, Ioannis | ArXiv | 2019

    Free access

    Deep reinforcement‐learning‐based driving policy for autonomous road vehicles

    Makantasis, Konstantinos / Kontorinaki, Maria / Nikolos, Ioannis | Wiley | 2020

    Free access

    Deep reinforcement-learning-based driving policy for autonomous road vehicles

    Makantasis, Konstantinos / Kontorinaki, Maria / Nikolos, Ioannis | IET | 2019

    Free access