Boston University Libraries OpenBU
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    View Item 
    •   OpenBU
    • BU Open Access Articles
    • BU Open Access Articles
    • View Item
    •   OpenBU
    • BU Open Access Articles
    • BU Open Access Articles
    • View Item

    Safety-guided deep reinforcement learning via online gaussian process estimation

    Thumbnail
    Date Issued
    2019-04-20
    Author(s)
    Fan, Jiameng
    Li, Wenchao
    Share to FacebookShare to TwitterShare by Email
    Export Citation
    Download to BibTex
    Download to EndNote/RefMan (RIS)
    Metadata
    Show full item record
    Permanent Link
    https://hdl.handle.net/2144/40703
    Version
    Accepted manuscript
    Citation (published version)
    Jiameng Fan, Wenchao Li. 2019. "Safety-Guided Deep Reinforcement Learning via Online Gaussian Process Estimation." International Conference on Learning Representation (ICLR), Workshop on Safe Machine Learning: Specification, Robustness, and Assurance. New Orleans, 2019-05-06 - 2019-05-09.
    Abstract
    An important facet of reinforcement learning (RL) has to do with how the agent goes about exploring the environment. Traditional exploration strategies typically focus on efficiency and ignore safety. However, for practical applications, ensuring safety of the agent during exploration is crucial since performing an unsafe action or reaching an unsafe state could result in irreversible damage to the agent. The main challenge of safe exploration is that characterizing the unsafe states and actions is difficult for large continuous state or action spaces and unknown environments. In this paper, we propose a novel approach to incorporate estimations of safety to guide exploration and policy search in deep reinforcement learning. By using a cost function to capture trajectory-based safety, our key idea is to formulate the state-action value function of this safety cost as a candidate Lyapunov function and extend control-theoretic results to approximate its derivative using online Gaussian Process (GP) estimation. We show how to use these statistical models to guide the agent in unknown environments to obtain high-performance control policies with provable stability certificates.
    Collections
    • ENG: Electrical and Computer Engineering: Scholarly Papers [257]
    • BU Open Access Articles [3730]


    Boston University
    Contact Us | Send Feedback | Help
     

     

    Browse

    All of OpenBUCommunities & CollectionsIssue DateAuthorsTitlesSubjectsThis CollectionIssue DateAuthorsTitlesSubjects

    Deposit Materials

    LoginNon-BU Registration

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Boston University
    Contact Us | Send Feedback | Help