This paper investigates how a Bayesian reinforcement learning method can be used to create a tactical decision-making agent for autonomous driving in an intersection scenario, where the agent can estimate the confidence of its decisions. An ensemble of neural networks, with additional randomized prior functions (RPF), are trained by using a bootstrapped experience replay memory. The coefficient of variation in the estimated Q-values of the ensemble members is used to approximate the uncertainty, and a criterion that determines if the agent is sufficiently confident to make a particular decision is introduced. The performance of the ensemble RPF method is evaluated in an intersection scenario and compared to a standard Deep Q-Network method, which does not estimate the uncertainty. It is shown that the trained ensemble RPF agent can detect cases with high uncertainty, both in situations that are far from the training distribution, and in situations that seldom occur within the training distribution. This work demonstrates one possible application of such a confidence estimate, by using this information to choose safe actions in unknown situations, which removes all collisions from within the training distribution, and most collisions outside of the distribution.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Reinforcement Learning with Uncertainty Estimation for Tactical Decision-Making in Intersections


    Contributors:


    Publication date :

    2020-09-20


    Size :

    492111 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    UNCERTAINTY-DIRECTED TRAINING OF A REINFORCEMENT LEARNING AGENT FOR TACTICAL DECISION-MAKING

    HOEL CARL-JOHAN / LAINE LEO | European Patent Office | 2023

    Free access


    Tactical Decision Making

    McKinney, D. / Flight Safety Foundation / International Federation of Airworthiness et al. | British Library Conference Proceedings | 2000


    Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving

    Hoel, Carl-Johan / Driggs-Campbell, Katherine / Wolff, Krister et al. | IEEE | 2020