The growing trend of fledgling reinforcement learning systems making their way into real-world applications has been accompanied by growing concerns for their safety and robustness. In recent years, a variety of approaches have been put forward to address the challenges of safety-aware reinforcement learning; however, these methods often either require a handcrafted model of the environment to be provided beforehand, or that the environment is relatively simple and low-dimensional. We present a novel approach to safety-aware deep reinforcement learning in high-dimensional environments called latent shielding. Latent shielding leverages internal representations of the environment learnt by model-based agents to "imagine" future trajectories and avoid those deemed unsafe. We experimentally demonstrate that this approach leads to improved adherence to formally-defined safety specifications.


    Access

    Download


    Export, share and cite



    Title :

    Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding


    Contributors:

    Publication date :

    2022-02-28


    Remarks:

    In: Proceedings of the Workshop on Artificial Intelligence Safety 2022 (SafeAI 2022). ceur-ws.org: Virtual. (2022)


    Type of media :

    Paper


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629



    Safety fences and kerbs

    Jehu, V.J. | Engineering Index Backfile | 1964


    Battery-operated electric fences

    Engineering Index Backfile | 1945


    Pedestrian safety device for crosswalks equipped with safety fences

    HAN SUNG MOO | European Patent Office | 2022

    Free access

    RAIL VEHICLE FOR CONSTRUCTING SAFETY BARRIER FENCES

    ROBERTSON MALCOLM | European Patent Office | 2016

    Free access

    Latent Space Reinforcement Learning

    Luck, Kevin Sebastian | BASE | 2014

    Free access