In this master thesis project a LiDAR-based, depth image-based and semantic segmentation image-based reinforcement learning agent is investigated and compared forlearning in simulation and performing in real-time. The project utilize the Deep Deterministic Policy Gradient architecture for learning continuous actions and was designed to control a RC car. One of the first project to deploy an agent in a real scenario after training in a similar simulation. The project demonstrated that with a proper reward function and by tuning driving parameters such as restricting steering, maximum velocity, minimum velocity and performing input data scaling a LiDAR-based agent could drive indefinitely on a simple but completely unseen track in real-time.


    Access

    Download


    Export, share and cite



    Title :

    Domain Transfer for End-to-end Reinforcement Learning


    Contributors:

    Publication date :

    2020-01-01


    Type of media :

    Theses


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Reinforcement Learning in the Multi-Robot Domain

    Mataric, M. J. | British Library Online Contents | 1997


    Learning and Transfer of Movement Gaits Using Reinforcement Learning

    Waidner, David / Strand, Marcus | TIBKAT | 2022



    Transfer of reinforcement learning for a robotic skill

    Gómez Rosal, Dulce Adriana | BASE | 2018

    Free access

    Modular reinforcement learning : a case study in a robot domain

    Kalmár, Zsolt / Szepesvári, Csaba / Lőrincz, András | BASE | 2000

    Free access