Rice Univesrity Logo
    • FAQ
    • Deposit your work
    • Login
    View Item 
    •   Rice Scholarship Home
    • Faculty & Staff Research
    • George R. Brown School of Engineering
    • Computer Science
    • Computer Science Technical Reports
    • View Item
    •   Rice Scholarship Home
    • Faculty & Staff Research
    • George R. Brown School of Engineering
    • Computer Science
    • Computer Science Technical Reports
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    How Much Do Unstated Problem Constraints Limit Deep Robotic Reinforcement Learning?

    Thumbnail
    Name:
    TR19-01.pdf
    Size:
    905.5Kb
    Format:
    PDF
    View/Open
    Author
    Lewis, W. Cannon II; Moll, Mark; Kavraki, Lydia E.
    Date
    2019
    Abstract
    Deep Reinforcement Learning is a promising paradigm for robotic control which has been shown to be capable of learning policies for high-dimensional, continuous control of unmodeled systems. However, Robotic Reinforcement Learning currently lacks clearly defined benchmark tasks, which makes it difficult for researchers to reproduce and compare against prior work. “Reacher” tasks, which are fundamental to robotic manipulation, are commonly used as benchmarks, but the lack of a formal specification elides details that are crucial to replication. In this paper we present a novel empirical analysis which shows that the unstated spatial constraints in commonly used implementations of Reacher tasks make it dramatically easier to learn a successful control policy with Deep Deterministic Policy Gradients (DDPG), a state-of-the-art Deep RL algorithm. Our analysis suggests that less constrained Reacher tasks are significantly more difficult to learn, and hence that existing de facto benchmarks are not representative of the difficulty of general robotic manipulation.
    Citation
    Lewis, W. Cannon II, Moll, Mark and Kavraki, Lydia E.. "How Much Do Unstated Problem Constraints Limit Deep Robotic Reinforcement Learning?." (2019) https://doi.org/10.25611/az5z-xt37.
    Published Version
    https://doi.org/10.25611/az5z-xt37
    Type
    Technical report
    Citable link to this page
    https://hdl.handle.net/1911/107403
    Rights
    You are granted permission for the noncommercial reproduction, distribution, display, and performance of this technical report in any format, but this permission is only for a period of forty-five (45) days from the most recent time that you verified that this technical report is still available from the Computer Science Department of Rice University under terms that include this permission. All other rights are reserved by the author(s).
    Metadata
    Show full item record
    Collections
    • Computer Science Technical Reports [245]

    Home | FAQ | Contact Us | Privacy Notice
    Managed by the Digital Scholarship Services at Fondren Library, Rice University
    Physical Address: 6100 Main Street, Houston, Texas 77005
    Mailing Address: MS-44, P.O.BOX 1892, Houston, Texas 77251-1892
    Site Map

     

    Searching scope

    Browse

    Entire ArchiveCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsTypeThis CollectionBy Issue DateAuthorsTitlesSubjectsType

    My Account

    Login

    Statistics

    View Usage Statistics

    Home | FAQ | Contact Us | Privacy Notice
    Managed by the Digital Scholarship Services at Fondren Library, Rice University
    Physical Address: 6100 Main Street, Houston, Texas 77005
    Mailing Address: MS-44, P.O.BOX 1892, Houston, Texas 77251-1892
    Site Map