Maneuvering in dense traffic is a challenging task for autonomous vehicles because it requires reasoning about the stochastic behaviors of many other participants. In addition, the agent must achieve the maneuver within a limited time and distance. In this work, we propose a combination of reinforcement learning and game theory to learn merging behaviors. We design a training curriculum for a reinforcement learning agent using the concept of level-k behavior. This approach exposes the agent to a broad variety of behaviors during training, which promotes learning policies that are robust to model discrepancies. We show that our approach learns more efficient policies than traditional training methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic


    Beteiligte:


    Erscheinungsdatum :

    20.09.2020


    Format / Umfang :

    895571 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic

    Bouton, Maxime / Nakhaei, Alireza / Fujimura, Kikuo et al. | ArXiv | 2019

    Freier Zugriff

    Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic

    Bouton, Maxime / Nakhaei, Alireza / Fujimura, Kikuo et al. | IEEE | 2019


    COMMUNICATION STRATEGIES FOR AUTOMATED MERGING IN DENSE TRAFFIC

    Potzy, Johannes / Feuerbach, Magdalena / Bengler, Klaus | British Library Conference Proceedings | 2019


    Communication Strategies for Automated Merging in Dense Traffic

    Potzy, Johannes / Feuerbach, Magdalena / Bengler, Klaus | IEEE | 2019


    Driving in Dense Traffic with Model-Free Reinforcement Learning

    Saxena, Dhruv Mauria / Bae, Sangjae / Nakhaei, Alireza et al. | ArXiv | 2019

    Freier Zugriff