• Login
    View Item 
    •   DSpace@RPI Home
    • Tetherless World Constellation
    • Tetherless World Publications
    • View Item
    •   DSpace@RPI Home
    • Tetherless World Constellation
    • Tetherless World Publications
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    An Ensemble Architecture for Learning Complex Problem-Solving Techniques from Demonstration

    Author
    Zhang, Xiaoqin; Shrestha, Bhavesh; Yoon, Sungwook; Kambhampati, Subbarao; DiBona, Phillip; Guo, Jinhong; McFarlane, Daniel; Hofmann, Martin; Whitebread, Kenneth; Appling, Darren; Whitaker, Elizabeth; Trewhitt, Ethan; Ding, Li; Michaelis, James; McGuinness, Deborah L.; Hendler, James A.; Doppa, Janardhan; Parker, Charles; Dietterich, Thomas; Tadepalli, Prasad; Wong, Weng-Keen; Green, Derek; Rebguns, Anton; Spears, Diana; Kuter, Ugur; Levine, Geoff; DeJong, Gerald; MacTavish, Reid; Ontanon, Santiago; Radhakrishnan, Jainarayan; Ram, Ashwin; Mostafa, Hala; Zafar, Huzaifa; Zhang, Chongjie; Corkill, Daniel; Lesser, Victor; Song, Zhexuan
    Thumbnail
    Other Contributors
    Date Issued
    2012-09-01
    Degree
    Terms of Use
    Metadata
    Show full item record
    URI
    https://dl.acm.org/doi/10.1145/2337542.2337560; https://hdl.handle.net/20.500.13015/4561
    Abstract
    We present a novel ensemble architecture for learning problem-solving techniques from a very small number of expert solutions and demonstrate its effectiveness in a complex real-world domain. The key feature of our “Generalized Integrated Learning Architecture” (GILA) is a set of heterogeneous independent learning and reasoning (ILR) components, coordinated by a central meta-reasoning executive (MRE). The ILRs are weakly coupled in the sense that all coordination during learning and performance happens through the MRE. Each ILR learns independently from a small number of expert demonstrations of a complex task. During performance, each ILR proposes partial solutions to subproblems posed by the MRE, which are then selected from and pieced together by the MRE to produce a complete solution. The heterogeneity of the learner-reasoners allows both learning and problem solving to be more effective because their abilities and biases are complementary and synergistic. We describe the application of this novel learning and problem solving architecture to the domain of airspace management, where multiple requests for the use of airspaces need to be deconflicted, reconciled, and managed automatically. Formal evaluations show that our system performs as well as or better than humans after learning from the same training data. Furthermore, GILA outperforms any individual ILR run in isolation, thus demonstrating the power of the ensemble architecture for learning and problem solving.;
    Description
    pages 1 - 38
    Department
    Publisher
    ACM Transactions on Intelligent Systems and Technology
    Relationships
    Access
    Collections
    • Tetherless World Publications

    Browse

    All of DSpace@RPICommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    Login

    DSpace software copyright © 2002-2023  DuraSpace
    Contact Us | Send Feedback
    DSpace Express is a service operated by 
    Atmire NV