Show simple item record

dc.contributor.authorZhang, Xiaoqin
dc.contributor.authorYoon, Sungwook
dc.contributor.authorDiBona, Phillip
dc.contributor.authorAppling, Darren
dc.contributor.authorDing, Li
dc.contributor.authorDoppa, Janardhan
dc.contributor.authorGreen, Derek
dc.contributor.authorGuo, Jinhong
dc.contributor.authorKuter, Ugur
dc.contributor.authorLevine, Geoff
dc.contributor.authorMacTavish, Reid
dc.contributor.authorMcFarlane, Daniel
dc.contributor.authorMichaelis, James
dc.contributor.authorMostafa, Hala
dc.contributor.authorOntanon, Santiago
dc.contributor.authorParker, Charles
dc.contributor.authorRadhakrishnan, Jainarayan
dc.contributor.authorRebguns, Anton
dc.contributor.authorShrestha, Bhavesh
dc.contributor.authorSong, Zhexuan
dc.contributor.authorTrewhitt, Ethan
dc.contributor.authorZafar, Huzaifa
dc.contributor.authorZhang, Chongjie
dc.contributor.authorCorkill, Daniel
dc.contributor.authorDeJong, Gerald
dc.contributor.authorDietterich, Thomas
dc.contributor.authorKambhampati, Subbarao
dc.contributor.authorLesser, Victor
dc.contributor.authorMcGuinness, Deborah L.
dc.contributor.authorRam, Ashwin
dc.contributor.authorSpears, Diana
dc.contributor.authorTadepalli, Prasad
dc.contributor.authorWhitaker, Elizabeth
dc.contributor.authorWong, Weng-Keen
dc.contributor.authorHendler, James A.
dc.contributor.authorHofmann, Martin
dc.contributor.authorWhitebread, Kenneth
dc.description.abstractWe 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.
dc.publisherTransactions on Intelligent Systems and Technology
dc.subjectInference Web
dc.titleAn Ensemble Learning and Problem Solving Architecture for Airspace Management

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record